From f994d480f3d8910ecbe6d84f6480cc12a9aaad52 Mon Sep 17 00:00:00 2001 From: D8D Developer Date: Mon, 23 Mar 2026 07:34:54 +0000 Subject: [PATCH] Initial commit Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude Co-Authored-By: Happy --- .../skills/bmad-advanced-elicitation/SKILL.md | 6 + .claude/skills/bmad-analyst/SKILL.md | 15 + .claude/skills/bmad-architect/SKILL.md | 15 + .claude/skills/bmad-brainstorming/SKILL.md | 6 + .../bmad-skill-manifest.yaml | 1 + .../bmad-brainstorming/brain-methods.csv | 62 + .../steps/step-01-session-setup.md | 210 + .../steps/step-01b-continue.md | 122 + .../steps/step-02a-user-selected.md | 225 + .../steps/step-02b-ai-recommended.md | 237 + .../steps/step-02c-random-selection.md | 209 + .../steps/step-02d-progressive-flow.md | 264 + .../steps/step-03-technique-execution.md | 399 ++ .../steps/step-04-idea-organization.md | 303 ++ .claude/skills/bmad-brainstorming/template.md | 15 + .claude/skills/bmad-brainstorming/workflow.md | 57 + .../SKILL.md | 6 + .claude/skills/bmad-code-review/SKILL.md | 6 + .claude/skills/bmad-correct-course/SKILL.md | 6 + .../skills/bmad-create-architecture/SKILL.md | 6 + .../bmad-create-epics-and-stories/SKILL.md | 6 + .claude/skills/bmad-create-prd/SKILL.md | 6 + .../skills/bmad-create-product-brief/SKILL.md | 6 + .claude/skills/bmad-create-story/SKILL.md | 6 + .claude/skills/bmad-create-ux-design/SKILL.md | 6 + .claude/skills/bmad-dev-story/SKILL.md | 6 + .claude/skills/bmad-dev/SKILL.md | 15 + .claude/skills/bmad-document-project/SKILL.md | 6 + .claude/skills/bmad-domain-research/SKILL.md | 6 + .claude/skills/bmad-edit-prd/SKILL.md | 6 + .../bmad-editorial-review-prose/SKILL.md | 6 + .../bmad-skill-manifest.yaml | 1 + .../bmad-editorial-review-prose/workflow.md | 81 + .../bmad-editorial-review-structure/SKILL.md | 6 + .../bmad-skill-manifest.yaml | 1 + .../workflow.md | 174 + .../bmad-generate-project-context/SKILL.md | 6 + .claude/skills/bmad-help/SKILL.md | 6 + .../skills/bmad-help/bmad-skill-manifest.yaml | 1 + .claude/skills/bmad-help/workflow.md | 88 + .claude/skills/bmad-index-docs/SKILL.md | 6 + .../bmad-index-docs/bmad-skill-manifest.yaml | 1 + .claude/skills/bmad-index-docs/workflow.md | 61 + .claude/skills/bmad-install.skill | Bin 0 -> 979 bytes .claude/skills/bmad-install/SKILL.md | 59 + .claude/skills/bmad-market-research/SKILL.md | 6 + .claude/skills/bmad-master/SKILL.md | 15 + .claude/skills/bmad-party-mode/SKILL.md | 6 + .../bmad-party-mode/bmad-skill-manifest.yaml | 1 + .../steps/step-01-agent-loading.md | 138 + .../steps/step-02-discussion-orchestration.md | 187 + .../steps/step-03-graceful-exit.md | 167 + .claude/skills/bmad-party-mode/workflow.md | 190 + .claude/skills/bmad-pm/SKILL.md | 15 + .../bmad-qa-generate-e2e-tests/SKILL.md | 6 + .claude/skills/bmad-qa/SKILL.md | 15 + .../bmad-quick-dev-new-preview/SKILL.md | 6 + .../bmad-skill-manifest.yaml | 1 + .../steps/step-01-clarify-and-route.md | 54 + .../steps/step-02-plan.md | 39 + .../steps/step-03-implement.md | 35 + .../steps/step-04-review.md | 53 + .../steps/step-05-present.md | 19 + .../tech-spec-template.md | 90 + .../bmad-quick-dev-new-preview/workflow.md | 80 + .claude/skills/bmad-quick-dev/SKILL.md | 6 + .../skills/bmad-quick-flow-solo-dev/SKILL.md | 15 + .claude/skills/bmad-quick-spec/SKILL.md | 6 + .claude/skills/bmad-retrospective/SKILL.md | 6 + .../bmad-review-adversarial-general/SKILL.md | 6 + .../bmad-skill-manifest.yaml | 1 + .../workflow.md | 32 + .../bmad-review-edge-case-hunter/SKILL.md | 6 + .../bmad-skill-manifest.yaml | 1 + .../bmad-review-edge-case-hunter/workflow.md | 62 + .claude/skills/bmad-shard-doc/SKILL.md | 6 + .../bmad-shard-doc/bmad-skill-manifest.yaml | 1 + .claude/skills/bmad-shard-doc/workflow.md | 100 + .claude/skills/bmad-sm/SKILL.md | 15 + .claude/skills/bmad-sprint-planning/SKILL.md | 6 + .claude/skills/bmad-sprint-status/SKILL.md | 6 + .claude/skills/bmad-tech-writer/SKILL.md | 15 + .../skills/bmad-technical-research/SKILL.md | 6 + .claude/skills/bmad-ux-designer/SKILL.md | 15 + .claude/skills/bmad-validate-prd/SKILL.md | 6 + .claude/skills/conversation-export/SKILL.md | 171 + .../conversation-export/quick-reference.md | 57 + .claude/skills/docx/LICENSE.txt | 30 + .claude/skills/docx/SKILL.md | 481 ++ .claude/skills/docx/scripts/__init__.py | 1 + .claude/skills/docx/scripts/accept_changes.py | 135 + .claude/skills/docx/scripts/comment.py | 318 ++ .../docx/scripts/office/helpers/__init__.py | 0 .../docx/scripts/office/helpers/merge_runs.py | 199 + .../office/helpers/simplify_redlines.py | 197 + .claude/skills/docx/scripts/office/pack.py | 159 + .../schemas/ISO-IEC29500-4_2016/dml-chart.xsd | 1499 ++++++ .../ISO-IEC29500-4_2016/dml-chartDrawing.xsd | 146 + .../ISO-IEC29500-4_2016/dml-diagram.xsd | 1085 ++++ .../ISO-IEC29500-4_2016/dml-lockedCanvas.xsd | 11 + .../schemas/ISO-IEC29500-4_2016/dml-main.xsd | 3081 ++++++++++++ .../ISO-IEC29500-4_2016/dml-picture.xsd | 23 + .../dml-spreadsheetDrawing.xsd | 185 + .../dml-wordprocessingDrawing.xsd | 287 ++ .../schemas/ISO-IEC29500-4_2016/pml.xsd | 1676 +++++++ .../shared-additionalCharacteristics.xsd | 28 + .../shared-bibliography.xsd | 144 + .../shared-commonSimpleTypes.xsd | 174 + .../shared-customXmlDataProperties.xsd | 25 + .../shared-customXmlSchemaProperties.xsd | 18 + .../shared-documentPropertiesCustom.xsd | 59 + .../shared-documentPropertiesExtended.xsd | 56 + .../shared-documentPropertiesVariantTypes.xsd | 195 + .../ISO-IEC29500-4_2016/shared-math.xsd | 582 +++ .../shared-relationshipReference.xsd | 25 + .../schemas/ISO-IEC29500-4_2016/sml.xsd | 4439 +++++++++++++++++ .../schemas/ISO-IEC29500-4_2016/vml-main.xsd | 570 +++ .../ISO-IEC29500-4_2016/vml-officeDrawing.xsd | 509 ++ .../vml-presentationDrawing.xsd | 12 + .../vml-spreadsheetDrawing.xsd | 108 + .../vml-wordprocessingDrawing.xsd | 96 + .../schemas/ISO-IEC29500-4_2016/wml.xsd | 3646 ++++++++++++++ .../schemas/ISO-IEC29500-4_2016/xml.xsd | 116 + .../ecma/fouth-edition/opc-contentTypes.xsd | 42 + .../ecma/fouth-edition/opc-coreProperties.xsd | 50 + .../schemas/ecma/fouth-edition/opc-digSig.xsd | 49 + .../ecma/fouth-edition/opc-relationships.xsd | 33 + .../docx/scripts/office/schemas/mce/mc.xsd | 75 + .../office/schemas/microsoft/wml-2010.xsd | 560 +++ .../office/schemas/microsoft/wml-2012.xsd | 67 + .../office/schemas/microsoft/wml-2018.xsd | 14 + .../office/schemas/microsoft/wml-cex-2018.xsd | 20 + .../office/schemas/microsoft/wml-cid-2016.xsd | 13 + .../microsoft/wml-sdtdatahash-2020.xsd | 4 + .../schemas/microsoft/wml-symex-2015.xsd | 8 + .claude/skills/docx/scripts/office/soffice.py | 183 + .claude/skills/docx/scripts/office/unpack.py | 132 + .../skills/docx/scripts/office/validate.py | 111 + .../scripts/office/validators/__init__.py | 15 + .../docx/scripts/office/validators/base.py | 847 ++++ .../docx/scripts/office/validators/docx.py | 446 ++ .../docx/scripts/office/validators/pptx.py | 275 + .../scripts/office/validators/redlining.py | 247 + .../docx/scripts/templates/comments.xml | 3 + .../scripts/templates/commentsExtended.xml | 3 + .../scripts/templates/commentsExtensible.xml | 3 + .../docx/scripts/templates/commentsIds.xml | 3 + .../skills/docx/scripts/templates/people.xml | 3 + .../mcp-admin-cleanup-node_modules/SKILL.md | 121 + .claude/skills/mcp-builder/LICENSE.txt | 202 + .claude/skills/mcp-builder/SKILL.md | 236 + .../mcp-builder/reference/evaluation.md | 602 +++ .../reference/mcp_best_practices.md | 249 + .../mcp-builder/reference/node_mcp_server.md | 970 ++++ .../reference/python_mcp_server.md | 719 +++ .../skills/mcp-builder/scripts/connections.py | 151 + .../skills/mcp-builder/scripts/evaluation.py | 373 ++ .../scripts/example_evaluation.xml | 22 + .../mcp-builder/scripts/requirements.txt | 2 + .../skills/mcp-container-install-bmad.skill | Bin 0 -> 1374 bytes .../mcp-container-install-bmad/SKILL.md | 158 + .claude/skills/mcp-d8d-admin-install/SKILL.md | 491 ++ .claude/skills/mcp-d8d-install/SKILL.md | 442 ++ .../skills/mcp-novel-platform-install.skill | Bin 0 -> 2985 bytes .../mcp-novel-platform-install/SKILL.md | 309 ++ .../mcp-novel-translator-install/SKILL.md | 142 + .claude/skills/pdf/LICENSE.txt | 30 + .claude/skills/pdf/SKILL.md | 314 ++ .claude/skills/pdf/forms.md | 294 ++ .claude/skills/pdf/reference.md | 612 +++ .../pdf/scripts/check_bounding_boxes.py | 65 + .../pdf/scripts/check_fillable_fields.py | 11 + .../pdf/scripts/convert_pdf_to_images.py | 33 + .../pdf/scripts/create_validation_image.py | 37 + .../pdf/scripts/extract_form_field_info.py | 122 + .../pdf/scripts/extract_form_structure.py | 115 + .../pdf/scripts/fill_fillable_fields.py | 98 + .../scripts/fill_pdf_form_with_annotations.py | 107 + .claude/skills/pptx/LICENSE.txt | 30 + .claude/skills/pptx/SKILL.md | 232 + .claude/skills/pptx/editing.md | 205 + .claude/skills/pptx/pptxgenjs.md | 420 ++ .claude/skills/pptx/scripts/__init__.py | 0 .claude/skills/pptx/scripts/add_slide.py | 195 + .claude/skills/pptx/scripts/clean.py | 286 ++ .../pptx/scripts/office/helpers/__init__.py | 0 .../pptx/scripts/office/helpers/merge_runs.py | 199 + .../office/helpers/simplify_redlines.py | 197 + .claude/skills/pptx/scripts/office/pack.py | 159 + .../schemas/ISO-IEC29500-4_2016/dml-chart.xsd | 1499 ++++++ .../ISO-IEC29500-4_2016/dml-chartDrawing.xsd | 146 + .../ISO-IEC29500-4_2016/dml-diagram.xsd | 1085 ++++ .../ISO-IEC29500-4_2016/dml-lockedCanvas.xsd | 11 + .../schemas/ISO-IEC29500-4_2016/dml-main.xsd | 3081 ++++++++++++ .../ISO-IEC29500-4_2016/dml-picture.xsd | 23 + .../dml-spreadsheetDrawing.xsd | 185 + .../dml-wordprocessingDrawing.xsd | 287 ++ .../schemas/ISO-IEC29500-4_2016/pml.xsd | 1676 +++++++ .../shared-additionalCharacteristics.xsd | 28 + .../shared-bibliography.xsd | 144 + .../shared-commonSimpleTypes.xsd | 174 + .../shared-customXmlDataProperties.xsd | 25 + .../shared-customXmlSchemaProperties.xsd | 18 + .../shared-documentPropertiesCustom.xsd | 59 + .../shared-documentPropertiesExtended.xsd | 56 + .../shared-documentPropertiesVariantTypes.xsd | 195 + .../ISO-IEC29500-4_2016/shared-math.xsd | 582 +++ .../shared-relationshipReference.xsd | 25 + .../schemas/ISO-IEC29500-4_2016/sml.xsd | 4439 +++++++++++++++++ .../schemas/ISO-IEC29500-4_2016/vml-main.xsd | 570 +++ .../ISO-IEC29500-4_2016/vml-officeDrawing.xsd | 509 ++ .../vml-presentationDrawing.xsd | 12 + .../vml-spreadsheetDrawing.xsd | 108 + .../vml-wordprocessingDrawing.xsd | 96 + .../schemas/ISO-IEC29500-4_2016/wml.xsd | 3646 ++++++++++++++ .../schemas/ISO-IEC29500-4_2016/xml.xsd | 116 + .../ecma/fouth-edition/opc-contentTypes.xsd | 42 + .../ecma/fouth-edition/opc-coreProperties.xsd | 50 + .../schemas/ecma/fouth-edition/opc-digSig.xsd | 49 + .../ecma/fouth-edition/opc-relationships.xsd | 33 + .../pptx/scripts/office/schemas/mce/mc.xsd | 75 + .../office/schemas/microsoft/wml-2010.xsd | 560 +++ .../office/schemas/microsoft/wml-2012.xsd | 67 + .../office/schemas/microsoft/wml-2018.xsd | 14 + .../office/schemas/microsoft/wml-cex-2018.xsd | 20 + .../office/schemas/microsoft/wml-cid-2016.xsd | 13 + .../microsoft/wml-sdtdatahash-2020.xsd | 4 + .../schemas/microsoft/wml-symex-2015.xsd | 8 + .claude/skills/pptx/scripts/office/soffice.py | 183 + .claude/skills/pptx/scripts/office/unpack.py | 132 + .../skills/pptx/scripts/office/validate.py | 111 + .../scripts/office/validators/__init__.py | 15 + .../pptx/scripts/office/validators/base.py | 847 ++++ .../pptx/scripts/office/validators/docx.py | 446 ++ .../pptx/scripts/office/validators/pptx.py | 275 + .../scripts/office/validators/redlining.py | 247 + .claude/skills/pptx/scripts/thumbnail.py | 289 ++ .claude/skills/skill-creator/LICENSE.txt | 202 + .claude/skills/skill-creator/SKILL.md | 356 ++ .../references/output-patterns.md | 82 + .../skill-creator/references/workflows.md | 28 + .../quick_validate.cpython-311.pyc | Bin 0 -> 4524 bytes .../skill-creator/scripts/init_skill.py | 303 ++ .../skill-creator/scripts/package_skill.py | 110 + .../skill-creator/scripts/quick_validate.py | 95 + .claude/skills/subagent-debug-logs.skill | Bin 0 -> 8026 bytes .claude/skills/subagent-debug-logs/SKILL.md | 192 + .../subagent-debug-logs/scripts/parse_logs.py | 149 + .claude/skills/subagent-monitor.skill | Bin 0 -> 3733 bytes .claude/skills/subagent-monitor/SKILL.md | 169 + .../subagent-monitor/references/mcp-tools.md | 185 + .claude/skills/xlsx/LICENSE.txt | 30 + .claude/skills/xlsx/SKILL.md | 292 ++ .../xlsx/scripts/office/helpers/__init__.py | 0 .../xlsx/scripts/office/helpers/merge_runs.py | 199 + .../office/helpers/simplify_redlines.py | 197 + .claude/skills/xlsx/scripts/office/pack.py | 159 + .../schemas/ISO-IEC29500-4_2016/dml-chart.xsd | 1499 ++++++ .../ISO-IEC29500-4_2016/dml-chartDrawing.xsd | 146 + .../ISO-IEC29500-4_2016/dml-diagram.xsd | 1085 ++++ .../ISO-IEC29500-4_2016/dml-lockedCanvas.xsd | 11 + .../schemas/ISO-IEC29500-4_2016/dml-main.xsd | 3081 ++++++++++++ .../ISO-IEC29500-4_2016/dml-picture.xsd | 23 + .../dml-spreadsheetDrawing.xsd | 185 + .../dml-wordprocessingDrawing.xsd | 287 ++ .../schemas/ISO-IEC29500-4_2016/pml.xsd | 1676 +++++++ .../shared-additionalCharacteristics.xsd | 28 + .../shared-bibliography.xsd | 144 + .../shared-commonSimpleTypes.xsd | 174 + .../shared-customXmlDataProperties.xsd | 25 + .../shared-customXmlSchemaProperties.xsd | 18 + .../shared-documentPropertiesCustom.xsd | 59 + .../shared-documentPropertiesExtended.xsd | 56 + .../shared-documentPropertiesVariantTypes.xsd | 195 + .../ISO-IEC29500-4_2016/shared-math.xsd | 582 +++ .../shared-relationshipReference.xsd | 25 + .../schemas/ISO-IEC29500-4_2016/sml.xsd | 4439 +++++++++++++++++ .../schemas/ISO-IEC29500-4_2016/vml-main.xsd | 570 +++ .../ISO-IEC29500-4_2016/vml-officeDrawing.xsd | 509 ++ .../vml-presentationDrawing.xsd | 12 + .../vml-spreadsheetDrawing.xsd | 108 + .../vml-wordprocessingDrawing.xsd | 96 + .../schemas/ISO-IEC29500-4_2016/wml.xsd | 3646 ++++++++++++++ .../schemas/ISO-IEC29500-4_2016/xml.xsd | 116 + .../ecma/fouth-edition/opc-contentTypes.xsd | 42 + .../ecma/fouth-edition/opc-coreProperties.xsd | 50 + .../schemas/ecma/fouth-edition/opc-digSig.xsd | 49 + .../ecma/fouth-edition/opc-relationships.xsd | 33 + .../xlsx/scripts/office/schemas/mce/mc.xsd | 75 + .../office/schemas/microsoft/wml-2010.xsd | 560 +++ .../office/schemas/microsoft/wml-2012.xsd | 67 + .../office/schemas/microsoft/wml-2018.xsd | 14 + .../office/schemas/microsoft/wml-cex-2018.xsd | 20 + .../office/schemas/microsoft/wml-cid-2016.xsd | 13 + .../microsoft/wml-sdtdatahash-2020.xsd | 4 + .../schemas/microsoft/wml-symex-2015.xsd | 8 + .claude/skills/xlsx/scripts/office/soffice.py | 183 + .claude/skills/xlsx/scripts/office/unpack.py | 132 + .../skills/xlsx/scripts/office/validate.py | 111 + .../scripts/office/validators/__init__.py | 15 + .../xlsx/scripts/office/validators/base.py | 847 ++++ .../xlsx/scripts/office/validators/docx.py | 446 ++ .../xlsx/scripts/office/validators/pptx.py | 275 + .../scripts/office/validators/redlining.py | 247 + .claude/skills/xlsx/scripts/recalc.py | 184 + 305 files changed, 84068 insertions(+) create mode 100644 .claude/skills/bmad-advanced-elicitation/SKILL.md create mode 100644 .claude/skills/bmad-analyst/SKILL.md create mode 100644 .claude/skills/bmad-architect/SKILL.md create mode 100644 .claude/skills/bmad-brainstorming/SKILL.md create mode 100644 .claude/skills/bmad-brainstorming/bmad-skill-manifest.yaml create mode 100644 .claude/skills/bmad-brainstorming/brain-methods.csv create mode 100644 .claude/skills/bmad-brainstorming/steps/step-01-session-setup.md create mode 100644 .claude/skills/bmad-brainstorming/steps/step-01b-continue.md create mode 100644 .claude/skills/bmad-brainstorming/steps/step-02a-user-selected.md create mode 100644 .claude/skills/bmad-brainstorming/steps/step-02b-ai-recommended.md create mode 100644 .claude/skills/bmad-brainstorming/steps/step-02c-random-selection.md create mode 100644 .claude/skills/bmad-brainstorming/steps/step-02d-progressive-flow.md create mode 100644 .claude/skills/bmad-brainstorming/steps/step-03-technique-execution.md create mode 100644 .claude/skills/bmad-brainstorming/steps/step-04-idea-organization.md create mode 100644 .claude/skills/bmad-brainstorming/template.md create mode 100644 .claude/skills/bmad-brainstorming/workflow.md create mode 100644 .claude/skills/bmad-check-implementation-readiness/SKILL.md create mode 100644 .claude/skills/bmad-code-review/SKILL.md create mode 100644 .claude/skills/bmad-correct-course/SKILL.md create mode 100644 .claude/skills/bmad-create-architecture/SKILL.md create mode 100644 .claude/skills/bmad-create-epics-and-stories/SKILL.md create mode 100644 .claude/skills/bmad-create-prd/SKILL.md create mode 100644 .claude/skills/bmad-create-product-brief/SKILL.md create mode 100644 .claude/skills/bmad-create-story/SKILL.md create mode 100644 .claude/skills/bmad-create-ux-design/SKILL.md create mode 100644 .claude/skills/bmad-dev-story/SKILL.md create mode 100644 .claude/skills/bmad-dev/SKILL.md create mode 100644 .claude/skills/bmad-document-project/SKILL.md create mode 100644 .claude/skills/bmad-domain-research/SKILL.md create mode 100644 .claude/skills/bmad-edit-prd/SKILL.md create mode 100644 .claude/skills/bmad-editorial-review-prose/SKILL.md create mode 100644 .claude/skills/bmad-editorial-review-prose/bmad-skill-manifest.yaml create mode 100644 .claude/skills/bmad-editorial-review-prose/workflow.md create mode 100644 .claude/skills/bmad-editorial-review-structure/SKILL.md create mode 100644 .claude/skills/bmad-editorial-review-structure/bmad-skill-manifest.yaml create mode 100644 .claude/skills/bmad-editorial-review-structure/workflow.md create mode 100644 .claude/skills/bmad-generate-project-context/SKILL.md create mode 100644 .claude/skills/bmad-help/SKILL.md create mode 100644 .claude/skills/bmad-help/bmad-skill-manifest.yaml create mode 100644 .claude/skills/bmad-help/workflow.md create mode 100644 .claude/skills/bmad-index-docs/SKILL.md create mode 100644 .claude/skills/bmad-index-docs/bmad-skill-manifest.yaml create mode 100644 .claude/skills/bmad-index-docs/workflow.md create mode 100644 .claude/skills/bmad-install.skill create mode 100644 .claude/skills/bmad-install/SKILL.md create mode 100644 .claude/skills/bmad-market-research/SKILL.md create mode 100644 .claude/skills/bmad-master/SKILL.md create mode 100644 .claude/skills/bmad-party-mode/SKILL.md create mode 100644 .claude/skills/bmad-party-mode/bmad-skill-manifest.yaml create mode 100644 .claude/skills/bmad-party-mode/steps/step-01-agent-loading.md create mode 100644 .claude/skills/bmad-party-mode/steps/step-02-discussion-orchestration.md create mode 100644 .claude/skills/bmad-party-mode/steps/step-03-graceful-exit.md create mode 100644 .claude/skills/bmad-party-mode/workflow.md create mode 100644 .claude/skills/bmad-pm/SKILL.md create mode 100644 .claude/skills/bmad-qa-generate-e2e-tests/SKILL.md create mode 100644 .claude/skills/bmad-qa/SKILL.md create mode 100644 .claude/skills/bmad-quick-dev-new-preview/SKILL.md create mode 100644 .claude/skills/bmad-quick-dev-new-preview/bmad-skill-manifest.yaml create mode 100644 .claude/skills/bmad-quick-dev-new-preview/steps/step-01-clarify-and-route.md create mode 100644 .claude/skills/bmad-quick-dev-new-preview/steps/step-02-plan.md create mode 100644 .claude/skills/bmad-quick-dev-new-preview/steps/step-03-implement.md create mode 100644 .claude/skills/bmad-quick-dev-new-preview/steps/step-04-review.md create mode 100644 .claude/skills/bmad-quick-dev-new-preview/steps/step-05-present.md create mode 100644 .claude/skills/bmad-quick-dev-new-preview/tech-spec-template.md create mode 100644 .claude/skills/bmad-quick-dev-new-preview/workflow.md create mode 100644 .claude/skills/bmad-quick-dev/SKILL.md create mode 100644 .claude/skills/bmad-quick-flow-solo-dev/SKILL.md create mode 100644 .claude/skills/bmad-quick-spec/SKILL.md create mode 100644 .claude/skills/bmad-retrospective/SKILL.md create mode 100644 .claude/skills/bmad-review-adversarial-general/SKILL.md create mode 100644 .claude/skills/bmad-review-adversarial-general/bmad-skill-manifest.yaml create mode 100644 .claude/skills/bmad-review-adversarial-general/workflow.md create mode 100644 .claude/skills/bmad-review-edge-case-hunter/SKILL.md create mode 100644 .claude/skills/bmad-review-edge-case-hunter/bmad-skill-manifest.yaml create mode 100644 .claude/skills/bmad-review-edge-case-hunter/workflow.md create mode 100644 .claude/skills/bmad-shard-doc/SKILL.md create mode 100644 .claude/skills/bmad-shard-doc/bmad-skill-manifest.yaml create mode 100644 .claude/skills/bmad-shard-doc/workflow.md create mode 100644 .claude/skills/bmad-sm/SKILL.md create mode 100644 .claude/skills/bmad-sprint-planning/SKILL.md create mode 100644 .claude/skills/bmad-sprint-status/SKILL.md create mode 100644 .claude/skills/bmad-tech-writer/SKILL.md create mode 100644 .claude/skills/bmad-technical-research/SKILL.md create mode 100644 .claude/skills/bmad-ux-designer/SKILL.md create mode 100644 .claude/skills/bmad-validate-prd/SKILL.md create mode 100644 .claude/skills/conversation-export/SKILL.md create mode 100644 .claude/skills/conversation-export/quick-reference.md create mode 100644 .claude/skills/docx/LICENSE.txt create mode 100644 .claude/skills/docx/SKILL.md create mode 100755 .claude/skills/docx/scripts/__init__.py create mode 100644 .claude/skills/docx/scripts/accept_changes.py create mode 100644 .claude/skills/docx/scripts/comment.py create mode 100644 .claude/skills/docx/scripts/office/helpers/__init__.py create mode 100644 .claude/skills/docx/scripts/office/helpers/merge_runs.py create mode 100644 .claude/skills/docx/scripts/office/helpers/simplify_redlines.py create mode 100755 .claude/skills/docx/scripts/office/pack.py create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/mce/mc.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/microsoft/wml-2010.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/microsoft/wml-2012.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/microsoft/wml-2018.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/microsoft/wml-cex-2018.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/microsoft/wml-cid-2016.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd create mode 100644 .claude/skills/docx/scripts/office/schemas/microsoft/wml-symex-2015.xsd create mode 100644 .claude/skills/docx/scripts/office/soffice.py create mode 100755 .claude/skills/docx/scripts/office/unpack.py create mode 100755 .claude/skills/docx/scripts/office/validate.py create mode 100644 .claude/skills/docx/scripts/office/validators/__init__.py create mode 100644 .claude/skills/docx/scripts/office/validators/base.py create mode 100644 .claude/skills/docx/scripts/office/validators/docx.py create mode 100644 .claude/skills/docx/scripts/office/validators/pptx.py create mode 100644 .claude/skills/docx/scripts/office/validators/redlining.py create mode 100644 .claude/skills/docx/scripts/templates/comments.xml create mode 100644 .claude/skills/docx/scripts/templates/commentsExtended.xml create mode 100644 .claude/skills/docx/scripts/templates/commentsExtensible.xml create mode 100644 .claude/skills/docx/scripts/templates/commentsIds.xml create mode 100644 .claude/skills/docx/scripts/templates/people.xml create mode 100644 .claude/skills/mcp-admin-cleanup-node_modules/SKILL.md create mode 100644 .claude/skills/mcp-builder/LICENSE.txt create mode 100644 .claude/skills/mcp-builder/SKILL.md create mode 100644 .claude/skills/mcp-builder/reference/evaluation.md create mode 100644 .claude/skills/mcp-builder/reference/mcp_best_practices.md create mode 100644 .claude/skills/mcp-builder/reference/node_mcp_server.md create mode 100644 .claude/skills/mcp-builder/reference/python_mcp_server.md create mode 100644 .claude/skills/mcp-builder/scripts/connections.py create mode 100644 .claude/skills/mcp-builder/scripts/evaluation.py create mode 100644 .claude/skills/mcp-builder/scripts/example_evaluation.xml create mode 100644 .claude/skills/mcp-builder/scripts/requirements.txt create mode 100644 .claude/skills/mcp-container-install-bmad.skill create mode 100644 .claude/skills/mcp-container-install-bmad/SKILL.md create mode 100644 .claude/skills/mcp-d8d-admin-install/SKILL.md create mode 100644 .claude/skills/mcp-d8d-install/SKILL.md create mode 100644 .claude/skills/mcp-novel-platform-install.skill create mode 100644 .claude/skills/mcp-novel-platform-install/SKILL.md create mode 100644 .claude/skills/mcp-novel-translator-install/SKILL.md create mode 100644 .claude/skills/pdf/LICENSE.txt create mode 100644 .claude/skills/pdf/SKILL.md create mode 100644 .claude/skills/pdf/forms.md create mode 100644 .claude/skills/pdf/reference.md create mode 100644 .claude/skills/pdf/scripts/check_bounding_boxes.py create mode 100644 .claude/skills/pdf/scripts/check_fillable_fields.py create mode 100644 .claude/skills/pdf/scripts/convert_pdf_to_images.py create mode 100644 .claude/skills/pdf/scripts/create_validation_image.py create mode 100644 .claude/skills/pdf/scripts/extract_form_field_info.py create mode 100644 .claude/skills/pdf/scripts/extract_form_structure.py create mode 100644 .claude/skills/pdf/scripts/fill_fillable_fields.py create mode 100644 .claude/skills/pdf/scripts/fill_pdf_form_with_annotations.py create mode 100644 .claude/skills/pptx/LICENSE.txt create mode 100644 .claude/skills/pptx/SKILL.md create mode 100644 .claude/skills/pptx/editing.md create mode 100644 .claude/skills/pptx/pptxgenjs.md create mode 100644 .claude/skills/pptx/scripts/__init__.py create mode 100644 .claude/skills/pptx/scripts/add_slide.py create mode 100755 .claude/skills/pptx/scripts/clean.py create mode 100644 .claude/skills/pptx/scripts/office/helpers/__init__.py create mode 100644 .claude/skills/pptx/scripts/office/helpers/merge_runs.py create mode 100644 .claude/skills/pptx/scripts/office/helpers/simplify_redlines.py create mode 100755 .claude/skills/pptx/scripts/office/pack.py create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/mce/mc.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/microsoft/wml-2010.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/microsoft/wml-2012.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/microsoft/wml-2018.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/microsoft/wml-cex-2018.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/microsoft/wml-cid-2016.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd create mode 100644 .claude/skills/pptx/scripts/office/schemas/microsoft/wml-symex-2015.xsd create mode 100644 .claude/skills/pptx/scripts/office/soffice.py create mode 100755 .claude/skills/pptx/scripts/office/unpack.py create mode 100755 .claude/skills/pptx/scripts/office/validate.py create mode 100644 .claude/skills/pptx/scripts/office/validators/__init__.py create mode 100644 .claude/skills/pptx/scripts/office/validators/base.py create mode 100644 .claude/skills/pptx/scripts/office/validators/docx.py create mode 100644 .claude/skills/pptx/scripts/office/validators/pptx.py create mode 100644 .claude/skills/pptx/scripts/office/validators/redlining.py create mode 100644 .claude/skills/pptx/scripts/thumbnail.py create mode 100644 .claude/skills/skill-creator/LICENSE.txt create mode 100644 .claude/skills/skill-creator/SKILL.md create mode 100644 .claude/skills/skill-creator/references/output-patterns.md create mode 100644 .claude/skills/skill-creator/references/workflows.md create mode 100644 .claude/skills/skill-creator/scripts/__pycache__/quick_validate.cpython-311.pyc create mode 100755 .claude/skills/skill-creator/scripts/init_skill.py create mode 100755 .claude/skills/skill-creator/scripts/package_skill.py create mode 100755 .claude/skills/skill-creator/scripts/quick_validate.py create mode 100644 .claude/skills/subagent-debug-logs.skill create mode 100644 .claude/skills/subagent-debug-logs/SKILL.md create mode 100755 .claude/skills/subagent-debug-logs/scripts/parse_logs.py create mode 100644 .claude/skills/subagent-monitor.skill create mode 100644 .claude/skills/subagent-monitor/SKILL.md create mode 100644 .claude/skills/subagent-monitor/references/mcp-tools.md create mode 100644 .claude/skills/xlsx/LICENSE.txt create mode 100644 .claude/skills/xlsx/SKILL.md create mode 100644 .claude/skills/xlsx/scripts/office/helpers/__init__.py create mode 100644 .claude/skills/xlsx/scripts/office/helpers/merge_runs.py create mode 100644 .claude/skills/xlsx/scripts/office/helpers/simplify_redlines.py create mode 100755 .claude/skills/xlsx/scripts/office/pack.py create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/mce/mc.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/microsoft/wml-2010.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/microsoft/wml-2012.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/microsoft/wml-2018.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/microsoft/wml-cex-2018.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/microsoft/wml-cid-2016.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd create mode 100644 .claude/skills/xlsx/scripts/office/schemas/microsoft/wml-symex-2015.xsd create mode 100644 .claude/skills/xlsx/scripts/office/soffice.py create mode 100755 .claude/skills/xlsx/scripts/office/unpack.py create mode 100755 .claude/skills/xlsx/scripts/office/validate.py create mode 100644 .claude/skills/xlsx/scripts/office/validators/__init__.py create mode 100644 .claude/skills/xlsx/scripts/office/validators/base.py create mode 100644 .claude/skills/xlsx/scripts/office/validators/docx.py create mode 100644 .claude/skills/xlsx/scripts/office/validators/pptx.py create mode 100644 .claude/skills/xlsx/scripts/office/validators/redlining.py create mode 100644 .claude/skills/xlsx/scripts/recalc.py diff --git a/.claude/skills/bmad-advanced-elicitation/SKILL.md b/.claude/skills/bmad-advanced-elicitation/SKILL.md new file mode 100644 index 0000000..99c497f --- /dev/null +++ b/.claude/skills/bmad-advanced-elicitation/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-advanced-elicitation +description: Push the LLM to reconsider refine and improve its recent output. Use when the user asks for advanced elicitation. +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/core/workflows/advanced-elicitation/workflow.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-analyst/SKILL.md b/.claude/skills/bmad-analyst/SKILL.md new file mode 100644 index 0000000..54c1afd --- /dev/null +++ b/.claude/skills/bmad-analyst/SKILL.md @@ -0,0 +1,15 @@ +--- +name: bmad-analyst +description: analyst agent +--- + +You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command. + + +1. LOAD the FULL agent file from {project-root}/_bmad/bmm/agents/analyst.md +2. READ its entire contents - this contains the complete agent persona, menu, and instructions +3. FOLLOW every step in the section precisely +4. DISPLAY the welcome/greeting as instructed +5. PRESENT the numbered menu +6. WAIT for user input before proceeding + diff --git a/.claude/skills/bmad-architect/SKILL.md b/.claude/skills/bmad-architect/SKILL.md new file mode 100644 index 0000000..b2f7e53 --- /dev/null +++ b/.claude/skills/bmad-architect/SKILL.md @@ -0,0 +1,15 @@ +--- +name: bmad-architect +description: architect agent +--- + +You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command. + + +1. LOAD the FULL agent file from {project-root}/_bmad/bmm/agents/architect.md +2. READ its entire contents - this contains the complete agent persona, menu, and instructions +3. FOLLOW every step in the section precisely +4. DISPLAY the welcome/greeting as instructed +5. PRESENT the numbered menu +6. WAIT for user input before proceeding + diff --git a/.claude/skills/bmad-brainstorming/SKILL.md b/.claude/skills/bmad-brainstorming/SKILL.md new file mode 100644 index 0000000..0d0d556 --- /dev/null +++ b/.claude/skills/bmad-brainstorming/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-brainstorming +description: 'Facilitate interactive brainstorming sessions using diverse creative techniques and ideation methods. Use when the user says help me brainstorm or help me ideate.' +--- + +Follow the instructions in [workflow.md](workflow.md). diff --git a/.claude/skills/bmad-brainstorming/bmad-skill-manifest.yaml b/.claude/skills/bmad-brainstorming/bmad-skill-manifest.yaml new file mode 100644 index 0000000..d0f08ab --- /dev/null +++ b/.claude/skills/bmad-brainstorming/bmad-skill-manifest.yaml @@ -0,0 +1 @@ +type: skill diff --git a/.claude/skills/bmad-brainstorming/brain-methods.csv b/.claude/skills/bmad-brainstorming/brain-methods.csv new file mode 100644 index 0000000..29c7787 --- /dev/null +++ b/.claude/skills/bmad-brainstorming/brain-methods.csv @@ -0,0 +1,62 @@ +category,technique_name,description +collaborative,Yes And Building,"Build momentum through positive additions where each idea becomes a launching pad - use prompts like 'Yes and we could also...' or 'Building on that idea...' to create energetic collaborative flow that builds upon previous contributions" +collaborative,Brain Writing Round Robin,"Silent idea generation followed by building on others' written concepts - gives quieter voices equal contribution while maintaining documentation through the sequence of writing silently, passing ideas, and building on received concepts" +collaborative,Random Stimulation,"Use random words/images as creative catalysts to force unexpected connections - breaks through mental blocks with serendipitous inspiration by asking how random elements relate, what connections exist, and forcing relationships" +collaborative,Role Playing,"Generate solutions from multiple stakeholder perspectives to build empathy while ensuring comprehensive consideration - embody different roles by asking what they want, how they'd approach problems, and what matters most to them" +collaborative,Ideation Relay Race,"Rapid-fire idea building under time pressure creates urgency and breakthroughs - structure with 30-second additions, quick building on ideas, and fast passing to maintain creative momentum and prevent overthinking" +creative,What If Scenarios,"Explore radical possibilities by questioning all constraints and assumptions - perfect for breaking through stuck thinking using prompts like 'What if we had unlimited resources?' 'What if the opposite were true?' or 'What if this problem didn't exist?'" +creative,Analogical Thinking,"Find creative solutions by drawing parallels to other domains - transfer successful patterns by asking 'This is like what?' 'How is this similar to...' and 'What other examples come to mind?' to connect to existing solutions" +creative,Reversal Inversion,"Deliberately flip problems upside down to reveal hidden assumptions and fresh angles - great when conventional approaches fail by asking 'What if we did the opposite?' 'How could we make this worse?' and 'What's the reverse approach?'" +creative,First Principles Thinking,"Strip away assumptions to rebuild from fundamental truths - essential for breakthrough innovation by asking 'What do we know for certain?' 'What are the fundamental truths?' and 'If we started from scratch?'" +creative,Forced Relationships,"Connect unrelated concepts to spark innovative bridges through creative collision - take two unrelated things, find connections between them, identify bridges, and explore how they could work together to generate unexpected solutions" +creative,Time Shifting,"Explore solutions across different time periods to reveal constraints and opportunities by asking 'How would this work in the past?' 'What about 100 years from now?' 'Different era constraints?' and 'What time-based solutions apply?'" +creative,Metaphor Mapping,"Use extended metaphors as thinking tools to explore problems from new angles - transforms abstract challenges into tangible narratives by asking 'This problem is like a metaphor,' extending the metaphor, and mapping elements to discover insights" +creative,Cross-Pollination,"Transfer solutions from completely different industries or domains to spark breakthrough innovations by asking how industry X would solve this, what patterns work in field Y, and how to adapt solutions from domain Z" +creative,Concept Blending,"Merge two or more existing concepts to create entirely new categories - goes beyond simple combination to genuine innovation by asking what emerges when concepts merge, what new category is created, and how the blend transcends original ideas" +creative,Reverse Brainstorming,"Generate problems instead of solutions to identify hidden opportunities and unexpected pathways by asking 'What could go wrong?' 'How could we make this fail?' and 'What problems could we create?' to reveal solution insights" +creative,Sensory Exploration,"Engage all five senses to discover multi-dimensional solution spaces beyond purely analytical thinking by asking what ideas feel, smell, taste, or sound like, and how different senses engage with the problem space" +deep,Five Whys,"Drill down through layers of causation to uncover root causes - essential for solving problems at source rather than symptoms by asking 'Why did this happen?' repeatedly until reaching fundamental drivers and ultimate causes" +deep,Morphological Analysis,"Systematically explore all possible parameter combinations for complex systems requiring comprehensive solution mapping - identify key parameters, list options for each, try different combinations, and identify emerging patterns" +deep,Provocation Technique,"Use deliberately provocative statements to extract useful ideas from seemingly absurd starting points - catalyzes breakthrough thinking by asking 'What if provocative statement?' 'How could this be useful?' 'What idea triggers?' and 'Extract the principle'" +deep,Assumption Reversal,"Challenge and flip core assumptions to rebuild from new foundations - essential for paradigm shifts by asking 'What assumptions are we making?' 'What if the opposite were true?' 'Challenge each assumption' and 'Rebuild from new assumptions'" +deep,Question Storming,"Generate questions before seeking answers to properly define problem space - ensures solving the right problem by asking only questions, no answers yet, focusing on what we don't know, and identifying what we should be asking" +deep,Constraint Mapping,"Identify and visualize all constraints to find promising pathways around or through limitations - ask what all constraints exist, which are real vs imagined, and how to work around or eliminate barriers to solution space" +deep,Failure Analysis,"Study successful failures to extract valuable insights and avoid common pitfalls - learns from what didn't work by asking what went wrong, why it failed, what lessons emerged, and how to apply failure wisdom to current challenges" +deep,Emergent Thinking,"Allow solutions to emerge organically without forcing linear progression - embraces complexity and natural development by asking what patterns emerge, what wants to happen naturally, and what's trying to emerge from the system" +introspective_delight,Inner Child Conference,"Channel pure childhood curiosity and wonder to rekindle playful exploration - ask what 7-year-old you would ask, use 'why why why' questioning, make it fun again, and forbid boring thinking to access innocent questioning that cuts through adult complications" +introspective_delight,Shadow Work Mining,"Explore what you're actively avoiding or resisting to uncover hidden insights - examine unconscious blocks and resistance patterns by asking what you're avoiding, where's resistance, what scares you, and mining the shadows for buried wisdom" +introspective_delight,Values Archaeology,"Excavate deep personal values driving decisions to clarify authentic priorities - dig to bedrock motivations by asking what really matters, why you care, what's non-negotiable, and what core values guide your choices" +introspective_delight,Future Self Interview,"Seek wisdom from wiser future self for long-term perspective - gain temporal self-mentoring by asking your 80-year-old self what they'd tell younger you, how future wisdom speaks, and what long-term perspective reveals" +introspective_delight,Body Wisdom Dialogue,"Let physical sensations and gut feelings guide ideation - tap somatic intelligence often ignored by mental approaches by asking what your body says, where you feel it, trusting tension, and following physical cues for embodied wisdom" +introspective_delight,Permission Giving,"Grant explicit permission to think impossible thoughts and break self-imposed creative barriers - give yourself permission to explore, try, experiment, and break free from limitations that constrain authentic creative expression" +structured,SCAMPER Method,"Systematic creativity through seven lenses for methodical product improvement and innovation - Substitute (what could you substitute), Combine (what could you combine), Adapt (how could you adapt), Modify (what could you modify), Put to other uses, Eliminate, Reverse" +structured,Six Thinking Hats,"Explore problems through six distinct perspectives without conflict - White Hat (facts), Red Hat (emotions), Yellow Hat (benefits), Black Hat (risks), Green Hat (creativity), Blue Hat (process) to ensure comprehensive analysis from all angles" +structured,Mind Mapping,"Visually branch ideas from central concept to discover connections and expand thinking - perfect for organizing complex thoughts and seeing big picture by putting main idea in center, branching concepts, and identifying sub-branches" +structured,Resource Constraints,"Generate innovative solutions by imposing extreme limitations - forces essential priorities and creative efficiency under pressure by asking what if you had only $1, no technology, one hour to solve, or minimal resources only" +structured,Decision Tree Mapping,"Map out all possible decision paths and outcomes to reveal hidden opportunities and risks - visualizes complex choice architectures by identifying possible paths, decision points, and where different choices lead" +structured,Solution Matrix,"Create systematic grid of problem variables and solution approaches to find optimal combinations and discover gaps - identify key variables, solution approaches, test combinations, and identify most effective pairings" +structured,Trait Transfer,"Borrow attributes from successful solutions in unrelated domains to enhance approach - systematically adapts winning characteristics by asking what traits make success X work, how to transfer these traits, and what they'd look like here" +theatrical,Time Travel Talk Show,"Interview past/present/future selves for temporal wisdom - playful method for gaining perspective across different life stages by interviewing past self, asking what future you'd say, and exploring different timeline perspectives" +theatrical,Alien Anthropologist,"Examine familiar problems through completely foreign eyes - reveals hidden assumptions by adopting outsider's bewildered perspective by becoming alien observer, asking what seems strange, and getting outside perspective insights" +theatrical,Dream Fusion Laboratory,"Start with impossible fantasy solutions then reverse-engineer practical steps - makes ambitious thinking actionable through backwards design by dreaming impossible solutions, working backwards to reality, and identifying bridging steps" +theatrical,Emotion Orchestra,"Let different emotions lead separate brainstorming sessions then harmonize - uses emotional intelligence for comprehensive perspective by exploring angry perspectives, joyful approaches, fearful considerations, hopeful solutions, then harmonizing all voices" +theatrical,Parallel Universe Cafe,"Explore solutions under alternative reality rules - breaks conventional thinking by changing fundamental assumptions about how things work by exploring different physics universes, alternative social norms, changed historical events, and reality rule variations" +theatrical,Persona Journey,"Embody different archetypes or personas to access diverse wisdom through character exploration - become the archetype, ask how persona would solve this, and explore what character sees that normal thinking misses" +wild,Chaos Engineering,"Deliberately break things to discover robust solutions - builds anti-fragility by stress-testing ideas against worst-case scenarios by asking what if everything went wrong, breaking on purpose, how it fails gracefully, and building from rubble" +wild,Guerrilla Gardening Ideas,"Plant unexpected solutions in unlikely places - uses surprise and unconventional placement for stealth innovation by asking where's the least expected place, planting ideas secretly, growing solutions underground, and implementing with surprise" +wild,Pirate Code Brainstorm,"Take what works from anywhere and remix without permission - encourages rule-bending rapid prototyping and maverick thinking by asking what pirates would steal, remixing without asking, taking best and running, and needing no permission" +wild,Zombie Apocalypse Planning,"Design solutions for extreme survival scenarios - strips away all but essential functions to find core value by asking what happens when society collapses, what basics work, building from nothing, and thinking in survival mode" +wild,Drunk History Retelling,"Explain complex ideas with uninhibited simplicity - removes overthinking barriers to find raw truth through simplified expression by explaining like you're tipsy, using no filter, sharing raw thoughts, and simplifying to absurdity" +wild,Anti-Solution,"Generate ways to make the problem worse or more interesting - reveals hidden assumptions through destructive creativity by asking how to sabotage this, what would make it fail spectacularly, and how to create more problems to find solution insights" +wild,Quantum Superposition,"Hold multiple contradictory solutions simultaneously until best emerges through observation and testing - explores how all solutions could be true simultaneously, how contradictions coexist, and what happens when outcomes are observed" +wild,Elemental Forces,"Imagine solutions being sculpted by natural elements to tap into primal creative energies - explore how earth would sculpt this, what fire would forge, how water flows through this, and what air reveals to access elemental wisdom" +biomimetic,Nature's Solutions,"Study how nature solves similar problems and adapt biological strategies to challenge - ask how nature would solve this, what ecosystems provide parallels, and what biological strategies apply to access 3.8 billion years of evolutionary wisdom" +biomimetic,Ecosystem Thinking,"Analyze problem as ecosystem to identify symbiotic relationships, natural succession, and ecological principles - explore symbiotic relationships, natural succession application, and ecological principles for systems thinking" +biomimetic,Evolutionary Pressure,"Apply evolutionary principles to gradually improve solutions through selective pressure and adaptation - ask how evolution would optimize this, what selective pressures apply, and how this adapts over time to harness natural selection wisdom" +quantum,Observer Effect,"Recognize how observing and measuring solutions changes their behavior - uses quantum principles for innovation by asking how observing changes this, what measurement effects matter, and how to use observer effect advantageously" +quantum,Entanglement Thinking,"Explore how different solution elements might be connected regardless of distance - reveals hidden relationships by asking what elements are entangled, how distant parts affect each other, and what hidden connections exist between solution components" +quantum,Superposition Collapse,"Hold multiple potential solutions simultaneously until constraints force single optimal outcome - leverages quantum decision theory by asking what if all options were possible, what constraints force collapse, and which solution emerges when observed" +cultural,Indigenous Wisdom,"Draw upon traditional knowledge systems and indigenous approaches overlooked by modern thinking - ask how specific cultures would approach this, what traditional knowledge applies, and what ancestral wisdom guides us to access overlooked problem-solving methods" +cultural,Fusion Cuisine,"Mix cultural approaches and perspectives like fusion cuisine - creates innovation through cultural cross-pollination by asking what happens when mixing culture A with culture B, what cultural hybrids emerge, and what fusion creates" +cultural,Ritual Innovation,"Apply ritual design principles to create transformative experiences and solutions - uses anthropological insights for human-centered design by asking what ritual would transform this, how to make it ceremonial, and what transformation this needs" +cultural,Mythic Frameworks,"Use myths and archetypal stories as frameworks for understanding and solving problems - taps into collective unconscious by asking what myth parallels this, what archetypes are involved, and how mythic structure informs solution" \ No newline at end of file diff --git a/.claude/skills/bmad-brainstorming/steps/step-01-session-setup.md b/.claude/skills/bmad-brainstorming/steps/step-01-session-setup.md new file mode 100644 index 0000000..cf970e3 --- /dev/null +++ b/.claude/skills/bmad-brainstorming/steps/step-01-session-setup.md @@ -0,0 +1,210 @@ +# Step 1: Session Setup and Continuation Detection + +## MANDATORY EXECUTION RULES (READ FIRST): + +- 🛑 NEVER generate content without user input +- ✅ ALWAYS treat this as collaborative facilitation +- 📋 YOU ARE A FACILITATOR, not a content generator +- 💬 FOCUS on session setup and continuation detection only +- 🚪 DETECT existing workflow state and handle continuation properly +- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the `communication_language` + +## EXECUTION PROTOCOLS: + +- 🎯 Show your analysis before taking any action +- 💾 Initialize document and update frontmatter +- 📖 Set up frontmatter `stepsCompleted: [1]` before loading next step +- 🚫 FORBIDDEN to load next step until setup is complete + +## CONTEXT BOUNDARIES: + +- Variables from workflow.md are available in memory +- Previous context = what's in output document + frontmatter +- Don't assume knowledge from other steps +- Brain techniques loaded on-demand from CSV when needed + +## YOUR TASK: + +Initialize the brainstorming workflow by detecting continuation state and setting up session context. + +## INITIALIZATION SEQUENCE: + +### 1. Check for Existing Sessions + +First, check the brainstorming sessions folder for existing sessions: + +- List all files in `{output_folder}/brainstorming/` +- **DO NOT read any file contents** - only list filenames +- If files exist, identify the most recent by date/time in the filename +- If no files exist, this is a fresh workflow + +### 2. Handle Existing Sessions (If Files Found) + +If existing session files are found: + +- Display the most recent session filename (do NOT read its content) +- Ask the user: "Found existing session: `[filename]`. Would you like to: + **[1]** Continue this session + **[2]** Start a new session + **[3]** See all existing sessions" + +- If user selects **[1]** (continue): Set `{brainstorming_session_output_file}` to that file path and load `./step-01b-continue.md` +- If user selects **[2]** (new): Generate new filename with current date/time and proceed to step 3 +- If user selects **[3]** (see all): List all session filenames and ask which to continue or if new + +### 3. Fresh Workflow Setup (If No Files or User Chooses New) + +If no document exists or no `stepsCompleted` in frontmatter: + +#### A. Initialize Document + +Create the brainstorming session document: + +```bash +# Create directory if needed +mkdir -p "$(dirname "{brainstorming_session_output_file}")" + +# Initialize from template +cp "{template_path}" "{brainstorming_session_output_file}" +``` + +#### B. Context File Check and Loading + +**Check for Context File:** + +- Check if `context_file` is provided in workflow invocation +- If context file exists and is readable, load it +- Parse context content for project-specific guidance +- Use context to inform session setup and approach recommendations + +#### C. Session Context Gathering + +"Welcome {{user_name}}! I'm excited to facilitate your brainstorming session. I'll guide you through proven creativity techniques to generate innovative ideas and breakthrough solutions. + +**Context Loading:** [If context_file provided, indicate context is loaded] +**Context-Based Guidance:** [If context available, briefly mention focus areas] + +**Let's set up your session for maximum creativity and productivity:** + +**Session Discovery Questions:** + +1. **What are we brainstorming about?** (The central topic or challenge) +2. **What specific outcomes are you hoping for?** (Types of ideas, solutions, or insights)" + +#### D. Process User Responses + +Wait for user responses, then: + +**Session Analysis:** +"Based on your responses, I understand we're focusing on **[summarized topic]** with goals around **[summarized objectives]**. + +**Session Parameters:** + +- **Topic Focus:** [Clear topic articulation] +- **Primary Goals:** [Specific outcome objectives] + +**Does this accurately capture what you want to achieve?**" + +#### E. Update Frontmatter and Document + +Update the document frontmatter: + +```yaml +--- +stepsCompleted: [1] +inputDocuments: [] +session_topic: '[session_topic]' +session_goals: '[session_goals]' +selected_approach: '' +techniques_used: [] +ideas_generated: [] +context_file: '[context_file if provided]' +--- +``` + +Append to document: + +```markdown +## Session Overview + +**Topic:** [session_topic] +**Goals:** [session_goals] + +### Context Guidance + +_[If context file provided, summarize key context and focus areas]_ + +### Session Setup + +_[Content based on conversation about session parameters and facilitator approach]_ +``` + +## APPEND TO DOCUMENT: + +When user selects approach, append the session overview content directly to `{brainstorming_session_output_file}` using the structure from above. + +### E. Continue to Technique Selection + +"**Session setup complete!** I have a clear understanding of your goals and can select the perfect techniques for your brainstorming needs. + +**Ready to explore technique approaches?** +[1] User-Selected Techniques - Browse our complete technique library +[2] AI-Recommended Techniques - Get customized suggestions based on your goals +[3] Random Technique Selection - Discover unexpected creative methods +[4] Progressive Technique Flow - Start broad, then systematically narrow focus + +Which approach appeals to you most? (Enter 1-4)" + +### 4. Handle User Selection and Initial Document Append + +#### When user selects approach number: + +- **Append initial session overview to `{brainstorming_session_output_file}`** +- **Update frontmatter:** `stepsCompleted: [1]`, `selected_approach: '[selected approach]'` +- **Load the appropriate step-02 file** based on selection + +### 5. Handle User Selection + +After user selects approach number: + +- **If 1:** Load `./step-02a-user-selected.md` +- **If 2:** Load `./step-02b-ai-recommended.md` +- **If 3:** Load `./step-02c-random-selection.md` +- **If 4:** Load `./step-02d-progressive-flow.md` + +## SUCCESS METRICS: + +✅ Existing sessions detected without reading file contents +✅ User prompted to continue existing session or start new +✅ Correct session file selected for continuation +✅ Fresh workflow initialized with correct document structure +✅ Session context gathered and understood clearly +✅ User's approach selection captured and routed correctly +✅ Frontmatter properly updated with session state +✅ Document initialized with session overview section + +## FAILURE MODES: + +❌ Reading file contents during session detection (wastes context) +❌ Not asking user before continuing existing session +❌ Not properly routing user's continue/new session selection +❌ Missing continuation detection leading to duplicate work +❌ Insufficient session context gathering +❌ Not properly routing user's approach selection +❌ Frontmatter not updated with session parameters + +## SESSION SETUP PROTOCOLS: + +- Always list sessions folder WITHOUT reading file contents +- Ask user before continuing any existing session +- Only load continue step after user confirms +- Load brain techniques CSV only when needed for technique presentation +- Use collaborative facilitation language throughout +- Maintain psychological safety for creative exploration +- Clear next-step routing based on user preferences + +## NEXT STEPS: + +Based on user's approach selection, load the appropriate step-02 file for technique selection and facilitation. + +Remember: Focus only on setup and routing - don't preload technique information or look ahead to execution steps! diff --git a/.claude/skills/bmad-brainstorming/steps/step-01b-continue.md b/.claude/skills/bmad-brainstorming/steps/step-01b-continue.md new file mode 100644 index 0000000..9b7e596 --- /dev/null +++ b/.claude/skills/bmad-brainstorming/steps/step-01b-continue.md @@ -0,0 +1,122 @@ +# Step 1b: Workflow Continuation + +## MANDATORY EXECUTION RULES (READ FIRST): + +- ✅ YOU ARE A CONTINUATION FACILITATOR, not a fresh starter +- 🎯 RESPECT EXISTING WORKFLOW state and progress +- 📋 UNDERSTAND PREVIOUS SESSION context and outcomes +- 🔍 SEAMLESSLY RESUME from where user left off +- 💬 MAINTAIN CONTINUITY in session flow and rapport +- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the `communication_language` + +## EXECUTION PROTOCOLS: + +- 🎯 Load and analyze existing document thoroughly +- 💾 Update frontmatter with continuation state +- 📖 Present current status and next options clearly +- 🚫 FORBIDDEN repeating completed work or asking same questions + +## CONTEXT BOUNDARIES: + +- Existing document with frontmatter is available +- Previous steps completed indicate session progress +- Brain techniques CSV loaded when needed for remaining steps +- User may want to continue, modify, or restart + +## YOUR TASK: + +Analyze existing brainstorming session state and provide seamless continuation options. + +## CONTINUATION SEQUENCE: + +### 1. Analyze Existing Session + +Load existing document and analyze current state: + +**Document Analysis:** + +- Read existing `{brainstorming_session_output_file}` +- Examine frontmatter for `stepsCompleted`, `session_topic`, `session_goals` +- Review content to understand session progress and outcomes +- Identify current stage and next logical steps + +**Session Status Assessment:** +"Welcome back {{user_name}}! I can see your brainstorming session on **[session_topic]** from **[date]**. + +**Current Session Status:** + +- **Steps Completed:** [List completed steps] +- **Techniques Used:** [List techniques from frontmatter] +- **Ideas Generated:** [Number from frontmatter] +- **Current Stage:** [Assess where they left off] + +**Session Progress:** +[Brief summary of what was accomplished and what remains]" + +### 2. Present Continuation Options + +Based on session analysis, provide appropriate options: + +**If Session Completed:** +"Your brainstorming session appears to be complete! + +**Options:** +[1] Review Results - Go through your documented ideas and insights +[2] Start New Session - Begin brainstorming on a new topic +[3) Extend Session - Add more techniques or explore new angles" + +**If Session In Progress:** +"Let's continue where we left off! + +**Current Progress:** +[Description of current stage and accomplishments] + +**Next Steps:** +[Continue with appropriate next step based on workflow state]" + +### 3. Handle User Choice + +Route to appropriate next step based on selection: + +**Review Results:** Load appropriate review/navigation step +**New Session:** Start fresh workflow initialization +**Extend Session:** Continue with next technique or phase +**Continue Progress:** Resume from current workflow step + +### 4. Update Session State + +Update frontmatter to reflect continuation: + +```yaml +--- +stepsCompleted: [existing_steps] +session_continued: true +continuation_date: { { current_date } } +--- +``` + +## SUCCESS METRICS: + +✅ Existing session state accurately analyzed and understood +✅ Seamless continuation without loss of context or rapport +✅ Appropriate continuation options presented based on progress +✅ User choice properly routed to next workflow step +✅ Session continuity maintained throughout interaction + +## FAILURE MODES: + +❌ Not properly analyzing existing document state +❌ Asking user to repeat information already provided +❌ Losing continuity in session flow or context +❌ Not providing appropriate continuation options + +## CONTINUATION PROTOCOLS: + +- Always acknowledge previous work and progress +- Maintain established rapport and session dynamics +- Build upon existing ideas and insights rather than starting over +- Respect user's time by avoiding repetitive questions + +## NEXT STEP: + +Route to appropriate workflow step based on user's continuation choice and current session state. diff --git a/.claude/skills/bmad-brainstorming/steps/step-02a-user-selected.md b/.claude/skills/bmad-brainstorming/steps/step-02a-user-selected.md new file mode 100644 index 0000000..2b523db --- /dev/null +++ b/.claude/skills/bmad-brainstorming/steps/step-02a-user-selected.md @@ -0,0 +1,225 @@ +# Step 2a: User-Selected Techniques + +## MANDATORY EXECUTION RULES (READ FIRST): + +- ✅ YOU ARE A TECHNIQUE LIBRARIAN, not a recommender +- 🎯 LOAD TECHNIQUES ON-DEMAND from brain-methods.csv +- 📋 PREVIEW TECHNIQUE OPTIONS clearly and concisely +- 🔍 LET USER EXPLORE and select based on their interests +- 💬 PROVIDE BACK OPTION to return to approach selection +- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the `communication_language` + +## EXECUTION PROTOCOLS: + +- 🎯 Load brain techniques CSV only when needed for presentation +- ⚠️ Present [B] back option and [C] continue options +- 💾 Update frontmatter with selected techniques +- 📖 Route to technique execution after confirmation +- 🚫 FORBIDDEN making recommendations or steering choices + +## CONTEXT BOUNDARIES: + +- Session context from Step 1 is available +- Brain techniques CSV contains 36+ techniques across 7 categories +- User wants full control over technique selection +- May need to present techniques by category or search capability + +## YOUR TASK: + +Load and present brainstorming techniques from CSV, allowing user to browse and select based on their preferences. + +## USER SELECTION SEQUENCE: + +### 1. Load Brain Techniques Library + +Load techniques from CSV on-demand: + +"Perfect! Let's explore our complete brainstorming techniques library. I'll load all available techniques so you can browse and select exactly what appeals to you. + +**Loading Brain Techniques Library...**" + +**Load CSV and parse:** + +- Read `brain-methods.csv` +- Parse: category, technique_name, description, facilitation_prompts, best_for, energy_level, typical_duration +- Organize by categories for browsing + +### 2. Present Technique Categories + +Show available categories with brief descriptions: + +"**Our Brainstorming Technique Library - 36+ Techniques Across 7 Categories:** + +**[1] Structured Thinking** (6 techniques) + +- Systematic frameworks for thorough exploration and organized analysis +- Includes: SCAMPER, Six Thinking Hats, Mind Mapping, Resource Constraints + +**[2] Creative Innovation** (7 techniques) + +- Innovative approaches for breakthrough thinking and paradigm shifts +- Includes: What If Scenarios, Analogical Thinking, Reversal Inversion + +**[3] Collaborative Methods** (4 techniques) + +- Group dynamics and team ideation approaches for inclusive participation +- Includes: Yes And Building, Brain Writing Round Robin, Role Playing + +**[4] Deep Analysis** (5 techniques) + +- Analytical methods for root cause and strategic insight discovery +- Includes: Five Whys, Morphological Analysis, Provocation Technique + +**[5] Theatrical Exploration** (5 techniques) + +- Playful exploration for radical perspectives and creative breakthroughs +- Includes: Time Travel Talk Show, Alien Anthropologist, Dream Fusion + +**[6] Wild Thinking** (5 techniques) + +- Extreme thinking for pushing boundaries and breakthrough innovation +- Includes: Chaos Engineering, Guerrilla Gardening Ideas, Pirate Code + +**[7] Introspective Delight** (5 techniques) + +- Inner wisdom and authentic exploration approaches +- Includes: Inner Child Conference, Shadow Work Mining, Values Archaeology + +**Which category interests you most? Enter 1-7, or tell me what type of thinking you're drawn to.**" + +### 3. Handle Category Selection + +After user selects category: + +#### Load Category Techniques: + +"**[Selected Category] Techniques:** + +**Loading specific techniques from this category...**" + +**Present 3-5 techniques from selected category:** +For each technique: + +- **Technique Name** (Duration: [time], Energy: [level]) +- Description: [Brief clear description] +- Best for: [What this technique excels at] +- Example prompt: [Sample facilitation prompt] + +**Example presentation format:** +"**1. SCAMPER Method** (Duration: 20-30 min, Energy: Moderate) + +- Systematic creativity through seven lenses (Substitute/Combine/Adapt/Modify/Put/Eliminate/Reverse) +- Best for: Product improvement, innovation challenges, systematic idea generation +- Example prompt: "What could you substitute in your current approach to create something new?" + +**2. Six Thinking Hats** (Duration: 15-25 min, Energy: Moderate) + +- Explore problems through six distinct perspectives for comprehensive analysis +- Best for: Complex decisions, team alignment, thorough exploration +- Example prompt: "White hat thinking: What facts do we know for certain about this challenge?" + +### 4. Allow Technique Selection + +"**Which techniques from this category appeal to you?** + +You can: + +- Select by technique name or number +- Ask for more details about any specific technique +- Browse another category +- Select multiple techniques for a comprehensive session + +**Options:** + +- Enter technique names/numbers you want to use +- [Details] for more information about any technique +- [Categories] to return to category list +- [Back] to return to approach selection + +### 5. Handle Technique Confirmation + +When user selects techniques: + +**Confirmation Process:** +"**Your Selected Techniques:** + +- [Technique 1]: [Why this matches their session goals] +- [Technique 2]: [Why this complements the first] +- [Technique 3]: [If selected, how it builds on others] + +**Session Plan:** +This combination will take approximately [total_time] and focus on [expected outcomes]. + +**Confirm these choices?** +[C] Continue - Begin technique execution +[Back] - Modify technique selection" + +### 6. Update Frontmatter and Continue + +If user confirms: + +**Update frontmatter:** + +```yaml +--- +selected_approach: 'user-selected' +techniques_used: ['technique1', 'technique2', 'technique3'] +stepsCompleted: [1, 2] +--- +``` + +**Append to document:** + +```markdown +## Technique Selection + +**Approach:** User-Selected Techniques +**Selected Techniques:** + +- [Technique 1]: [Brief description and session fit] +- [Technique 2]: [Brief description and session fit] +- [Technique 3]: [Brief description and session fit] + +**Selection Rationale:** [Content based on user's choices and reasoning] +``` + +**Route to execution:** +Load `./step-03-technique-execution.md` + +### 7. Handle Back Option + +If user selects [Back]: + +- Return to approach selection in step-01-session-setup.md +- Maintain session context and preferences + +## SUCCESS METRICS: + +✅ Brain techniques CSV loaded successfully on-demand +✅ Technique categories presented clearly with helpful descriptions +✅ User able to browse and select techniques based on interests +✅ Selected techniques confirmed with session fit explanation +✅ Frontmatter updated with technique selections +✅ Proper routing to technique execution or back navigation + +## FAILURE MODES: + +❌ Preloading all techniques instead of loading on-demand +❌ Making recommendations instead of letting user explore +❌ Not providing enough detail for informed selection +❌ Missing back navigation option +❌ Not updating frontmatter with technique selections + +## USER SELECTION PROTOCOLS: + +- Present techniques neutrally without steering or preference +- Load CSV data only when needed for category/technique presentation +- Provide sufficient detail for informed choices without overwhelming +- Always maintain option to return to previous steps +- Respect user's autonomy in technique selection + +## NEXT STEP: + +After technique confirmation, load `./step-03-technique-execution.md` to begin facilitating the selected brainstorming techniques. + +Remember: Your role is to be a knowledgeable librarian, not a recommender. Let the user explore and choose based on their interests and intuition! diff --git a/.claude/skills/bmad-brainstorming/steps/step-02b-ai-recommended.md b/.claude/skills/bmad-brainstorming/steps/step-02b-ai-recommended.md new file mode 100644 index 0000000..f928ff0 --- /dev/null +++ b/.claude/skills/bmad-brainstorming/steps/step-02b-ai-recommended.md @@ -0,0 +1,237 @@ +# Step 2b: AI-Recommended Techniques + +## MANDATORY EXECUTION RULES (READ FIRST): + +- ✅ YOU ARE A TECHNIQUE MATCHMAKER, using AI analysis to recommend optimal approaches +- 🎯 ANALYZE SESSION CONTEXT from Step 1 for intelligent technique matching +- 📋 LOAD TECHNIQUES ON-DEMAND from brain-methods.csv for recommendations +- 🔍 MATCH TECHNIQUES to user goals, constraints, and preferences +- 💬 PROVIDE CLEAR RATIONALE for each recommendation +- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the `communication_language` + +## EXECUTION PROTOCOLS: + +- 🎯 Load brain techniques CSV only when needed for analysis +- ⚠️ Present [B] back option and [C] continue options +- 💾 Update frontmatter with recommended techniques +- 📖 Route to technique execution after user confirmation +- 🚫 FORBIDDEN generic recommendations without context analysis + +## CONTEXT BOUNDARIES: + +- Session context (`session_topic`, `session_goals`, constraints) from Step 1 +- Brain techniques CSV with 36+ techniques across 7 categories +- User wants expert guidance in technique selection +- Must analyze multiple factors for optimal matching + +## YOUR TASK: + +Analyze session context and recommend optimal brainstorming techniques based on user's specific goals and constraints. + +## AI RECOMMENDATION SEQUENCE: + +### 1. Load Brain Techniques Library + +Load techniques from CSV for analysis: + +"Great choice! Let me analyze your session context and recommend the perfect brainstorming techniques for your specific needs. + +**Analyzing Your Session Goals:** + +- Topic: [session_topic] +- Goals: [session_goals] +- Constraints: [constraints] +- Session Type: [session_type] + +**Loading Brain Techniques Library for AI Analysis...**" + +**Load CSV and parse:** + +- Read `brain-methods.csv` +- Parse: category, technique_name, description, facilitation_prompts, best_for, energy_level, typical_duration + +### 2. Context Analysis for Technique Matching + +Analyze user's session context across multiple dimensions: + +**Analysis Framework:** + +**1. Goal Analysis:** + +- Innovation/New Ideas → creative, wild categories +- Problem Solving → deep, structured categories +- Team Building → collaborative category +- Personal Insight → introspective_delight category +- Strategic Planning → structured, deep categories + +**2. Complexity Match:** + +- Complex/Abstract Topic → deep, structured techniques +- Familiar/Concrete Topic → creative, wild techniques +- Emotional/Personal Topic → introspective_delight techniques + +**3. Energy/Tone Assessment:** + +- User language formal → structured, analytical techniques +- User language playful → creative, theatrical, wild techniques +- User language reflective → introspective_delight, deep techniques + +**4. Time Available:** + +- <30 min → 1-2 focused techniques +- 30-60 min → 2-3 complementary techniques +- > 60 min → Multi-phase technique flow + +### 3. Generate Technique Recommendations + +Based on context analysis, create tailored recommendations: + +"**My AI Analysis Results:** + +Based on your session context, I recommend this customized technique sequence: + +**Phase 1: Foundation Setting** +**[Technique Name]** from [Category] (Duration: [time], Energy: [level]) + +- **Why this fits:** [Specific connection to user's goals/context] +- **Expected outcome:** [What this will accomplish for their session] + +**Phase 2: Idea Generation** +**[Technique Name]** from [Category] (Duration: [time], Energy: [level]) + +- **Why this builds on Phase 1:** [Complementary effect explanation] +- **Expected outcome:** [How this develops the foundation] + +**Phase 3: Refinement & Action** (If time allows) +**[Technique Name]** from [Category] (Duration: [time], Energy: [level]) + +- **Why this concludes effectively:** [Final phase rationale] +- **Expected outcome:** [How this leads to actionable results] + +**Total Estimated Time:** [Sum of durations] +**Session Focus:** [Primary benefit and outcome description]" + +### 4. Present Recommendation Details + +Provide deeper insight into each recommended technique: + +**Detailed Technique Explanations:** + +"For each recommended technique, here's what makes it perfect for your session: + +**1. [Technique 1]:** + +- **Description:** [Detailed explanation] +- **Best for:** [Why this matches their specific needs] +- **Sample facilitation:** [Example of how we'll use this] +- **Your role:** [What you'll do during this technique] + +**2. [Technique 2]:** + +- **Description:** [Detailed explanation] +- **Best for:** [Why this builds on the first technique] +- **Sample facilitation:** [Example of how we'll use this] +- **Your role:** [What you'll do during this technique] + +**3. [Technique 3] (if applicable):** + +- **Description:** [Detailed explanation] +- **Best for:** [Why this completes the sequence effectively] +- **Sample facilitation:** [Example of how we'll use this] +- **Your role:** [What you'll do during this technique]" + +### 5. Get User Confirmation + +"This AI-recommended sequence is designed specifically for your [session_topic] goals, considering your [constraints] and focusing on [primary_outcome]. + +**Does this approach sound perfect for your session?** + +**Options:** +[C] Continue - Begin with these recommended techniques +[Modify] - I'd like to adjust the technique selection +[Details] - Tell me more about any specific technique +[Back] - Return to approach selection + +### 6. Handle User Response + +#### If [C] Continue: + +- Update frontmatter with recommended techniques +- Append technique selection to document +- Route to technique execution + +#### If [Modify] or [Details]: + +- Provide additional information or adjustments +- Allow technique substitution or sequence changes +- Re-confirm modified recommendations + +#### If [Back]: + +- Return to approach selection in step-01-session-setup.md +- Maintain session context and preferences + +### 7. Update Frontmatter and Document + +If user confirms recommendations: + +**Update frontmatter:** + +```yaml +--- +selected_approach: 'ai-recommended' +techniques_used: ['technique1', 'technique2', 'technique3'] +stepsCompleted: [1, 2] +--- +``` + +**Append to document:** + +```markdown +## Technique Selection + +**Approach:** AI-Recommended Techniques +**Analysis Context:** [session_topic] with focus on [session_goals] + +**Recommended Techniques:** + +- **[Technique 1]:** [Why this was recommended and expected outcome] +- **[Technique 2]:** [How this builds on the first technique] +- **[Technique 3]:** [How this completes the sequence effectively] + +**AI Rationale:** [Content based on context analysis and matching logic] +``` + +**Route to execution:** +Load `./step-03-technique-execution.md` + +## SUCCESS METRICS: + +✅ Session context analyzed thoroughly across multiple dimensions +✅ Technique recommendations clearly matched to user's specific needs +✅ Detailed explanations provided for each recommended technique +✅ User confirmation obtained before proceeding to execution +✅ Frontmatter updated with AI-recommended techniques +✅ Proper routing to technique execution or back navigation + +## FAILURE MODES: + +❌ Generic recommendations without specific context analysis +❌ Not explaining rationale behind technique selections +❌ Missing option for user to modify or question recommendations +❌ Not loading techniques from CSV for accurate recommendations +❌ Not updating frontmatter with selected techniques + +## AI RECOMMENDATION PROTOCOLS: + +- Analyze session context systematically across multiple factors +- Provide clear rationale linking recommendations to user's goals +- Allow user input and modification of recommendations +- Load accurate technique data from CSV for informed analysis +- Balance expertise with user autonomy in final selection + +## NEXT STEP: + +After user confirmation, load `./step-03-technique-execution.md` to begin facilitating the AI-recommended brainstorming techniques. + +Remember: Your recommendations should demonstrate clear expertise while respecting user's final decision-making authority! diff --git a/.claude/skills/bmad-brainstorming/steps/step-02c-random-selection.md b/.claude/skills/bmad-brainstorming/steps/step-02c-random-selection.md new file mode 100644 index 0000000..def91d0 --- /dev/null +++ b/.claude/skills/bmad-brainstorming/steps/step-02c-random-selection.md @@ -0,0 +1,209 @@ +# Step 2c: Random Technique Selection + +## MANDATORY EXECUTION RULES (READ FIRST): + +- ✅ YOU ARE A SERENDIPITY FACILITATOR, embracing unexpected creative discoveries +- 🎯 USE RANDOM SELECTION for surprising technique combinations +- 📋 LOAD TECHNIQUES ON-DEMAND from brain-methods.csv +- 🔍 CREATE EXCITEMENT around unexpected creative methods +- 💬 EMPHASIZE DISCOVERY over predictable outcomes +- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the `communication_language` + +## EXECUTION PROTOCOLS: + +- 🎯 Load brain techniques CSV only when needed for random selection +- ⚠️ Present [B] back option and [C] continue options +- 💾 Update frontmatter with randomly selected techniques +- 📖 Route to technique execution after user confirmation +- 🚫 FORBIDDEN steering random selections or second-guessing outcomes + +## CONTEXT BOUNDARIES: + +- Session context from Step 1 available for basic filtering +- Brain techniques CSV with 36+ techniques across 7 categories +- User wants surprise and unexpected creative methods +- Randomness should create complementary, not contradictory, combinations + +## YOUR TASK: + +Use random selection to discover unexpected brainstorming techniques that will break user out of usual thinking patterns. + +## RANDOM SELECTION SEQUENCE: + +### 1. Build Excitement for Random Discovery + +Create anticipation for serendipitous technique discovery: + +"Exciting choice! You've chosen the path of creative serendipity. Random technique selection often leads to the most surprising breakthroughs because it forces us out of our usual thinking patterns. + +**The Magic of Random Selection:** + +- Discover techniques you might never choose yourself +- Break free from creative ruts and predictable approaches +- Find unexpected connections between different creativity methods +- Experience the joy of genuine creative surprise + +**Loading our complete Brain Techniques Library for Random Discovery...**" + +**Load CSV and parse:** + +- Read `brain-methods.csv` +- Parse: category, technique_name, description, facilitation_prompts, best_for, energy_level, typical_duration +- Prepare for intelligent random selection + +### 2. Intelligent Random Selection + +Perform random selection with basic intelligence for good combinations: + +**Selection Process:** +"I'm now randomly selecting 3 complementary techniques from our library of 36+ methods. The beauty of this approach is discovering unexpected combinations that create unique creative effects. + +**Randomizing Technique Selection...**" + +**Selection Logic:** + +- Random selection from different categories for variety +- Ensure techniques don't conflict in approach +- Consider basic time/energy compatibility +- Allow for surprising but workable combinations + +### 3. Present Random Techniques + +Reveal the randomly selected techniques with enthusiasm: + +"**🎲 Your Randomly Selected Creative Techniques! 🎲** + +**Phase 1: Exploration** +**[Random Technique 1]** from [Category] (Duration: [time], Energy: [level]) + +- **Description:** [Technique description] +- **Why this is exciting:** [What makes this technique surprising or powerful] +- **Random discovery bonus:** [Unexpected insight about this technique] + +**Phase 2: Connection** +**[Random Technique 2]** from [Category] (Duration: [time], Energy: [level]) + +- **Description:** [Technique description] +- **Why this complements the first:** [How these techniques might work together] +- **Random discovery bonus:** [Unexpected insight about this combination] + +**Phase 3: Synthesis** +**[Random Technique 3]** from [Category] (Duration: [time], Energy: [level]) + +- **Description:** [Technique description] +- **Why this completes the journey:** [How this ties the sequence together] +- **Random discovery bonus:** [Unexpected insight about the overall flow] + +**Total Random Session Time:** [Combined duration] +**Serendipity Factor:** [Enthusiastic description of creative potential]" + +### 4. Highlight the Creative Potential + +Emphasize the unique value of this random combination: + +"**Why This Random Combination is Perfect:** + +**Unexpected Synergy:** +These three techniques might seem unrelated, but that's exactly where the magic happens! [Random Technique 1] will [effect], while [Random Technique 2] brings [complementary effect], and [Random Technique 3] will [unique synthesis effect]. + +**Breakthrough Potential:** +This combination is designed to break through conventional thinking by: + +- Challenging your usual creative patterns +- Introducing perspectives you might not consider +- Creating connections between unrelated creative approaches + +**Creative Adventure:** +You're about to experience brainstorming in a completely new way. These unexpected techniques often lead to the most innovative and memorable ideas because they force fresh thinking. + +**Ready for this creative adventure?** + +**Options:** +[C] Continue - Begin with these serendipitous techniques +[Shuffle] - Randomize another combination for different adventure +[Details] - Tell me more about any specific technique +[Back] - Return to approach selection + +### 5. Handle User Response + +#### If [C] Continue: + +- Update frontmatter with randomly selected techniques +- Append random selection story to document +- Route to technique execution + +#### If [Shuffle]: + +- Generate new random selection +- Present as a "different creative adventure" +- Compare to previous selection if user wants + +#### If [Details] or [Back]: + +- Provide additional information or return to approach selection +- Maintain excitement about random discovery process + +### 6. Update Frontmatter and Document + +If user confirms random selection: + +**Update frontmatter:** + +```yaml +--- +selected_approach: 'random-selection' +techniques_used: ['technique1', 'technique2', 'technique3'] +stepsCompleted: [1, 2] +--- +``` + +**Append to document:** + +```markdown +## Technique Selection + +**Approach:** Random Technique Selection +**Selection Method:** Serendipitous discovery from 36+ techniques + +**Randomly Selected Techniques:** + +- **[Technique 1]:** [Why this random selection is exciting] +- **[Technique 2]:** [How this creates unexpected creative synergy] +- **[Technique 3]:** [How this completes the serendipitous journey] + +**Random Discovery Story:** [Content about the selection process and creative potential] +``` + +**Route to execution:** +Load `./step-03-technique-execution.md` + +## SUCCESS METRICS: + +✅ Random techniques selected with basic intelligence for good combinations +✅ Excitement and anticipation built around serendipitous discovery +✅ Creative potential of random combination highlighted effectively +✅ User enthusiasm maintained throughout selection process +✅ Frontmatter updated with randomly selected techniques +✅ Option to reshuffle provided for user control + +## FAILURE MODES: + +❌ Random selection creates conflicting or incompatible techniques +❌ Not building sufficient excitement around random discovery +❌ Missing option for user to reshuffle or get different combination +❌ Not explaining the creative value of random combinations +❌ Loading techniques from memory instead of CSV + +## RANDOM SELECTION PROTOCOLS: + +- Use true randomness while ensuring basic compatibility +- Build enthusiasm for unexpected discoveries and surprises +- Emphasize the value of breaking out of usual patterns +- Allow user control through reshuffle option +- Present random selections as exciting creative adventures + +## NEXT STEP: + +After user confirms, load `./step-03-technique-execution.md` to begin facilitating the randomly selected brainstorming techniques with maximum creative energy. + +Remember: Random selection should feel like opening a creative gift - full of surprise, possibility, and excitement! diff --git a/.claude/skills/bmad-brainstorming/steps/step-02d-progressive-flow.md b/.claude/skills/bmad-brainstorming/steps/step-02d-progressive-flow.md new file mode 100644 index 0000000..96aa2d9 --- /dev/null +++ b/.claude/skills/bmad-brainstorming/steps/step-02d-progressive-flow.md @@ -0,0 +1,264 @@ +# Step 2d: Progressive Technique Flow + +## MANDATORY EXECUTION RULES (READ FIRST): + +- ✅ YOU ARE A CREATIVE JOURNEY GUIDE, orchestrating systematic idea development +- 🎯 DESIGN PROGRESSIVE FLOW from broad exploration to focused action +- 📋 LOAD TECHNIQUES ON-DEMAND from brain-methods.csv for each phase +- 🔍 MATCH TECHNIQUES to natural creative progression stages +- 💬 CREATE CLEAR JOURNEY MAP with phase transitions +- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the `communication_language` + +## EXECUTION PROTOCOLS: + +- 🎯 Load brain techniques CSV only when needed for each phase +- ⚠️ Present [B] back option and [C] continue options +- 💾 Update frontmatter with progressive technique sequence +- 📖 Route to technique execution after journey confirmation +- 🚫 FORBIDDEN jumping ahead to later phases without proper foundation + +## CONTEXT BOUNDARIES: + +- Session context from Step 1 available for journey design +- Brain techniques CSV with 36+ techniques across 7 categories +- User wants systematic, comprehensive idea development +- Must design natural progression from divergent to convergent thinking + +## YOUR TASK: + +Design a progressive technique flow that takes users from expansive exploration through to actionable implementation planning. + +## PROGRESSIVE FLOW SEQUENCE: + +### 1. Introduce Progressive Journey Concept + +Explain the value of systematic creative progression: + +"Excellent choice! Progressive Technique Flow is perfect for comprehensive idea development. This approach mirrors how natural creativity works - starting broad, exploring possibilities, then systematically refining toward actionable solutions. + +**The Creative Journey We'll Take:** + +**Phase 1: EXPANSIVE EXPLORATION** (Divergent Thinking) + +- Generate abundant ideas without judgment +- Explore wild possibilities and unconventional approaches +- Create maximum creative breadth and options + +**Phase 2: PATTERN RECOGNITION** (Analytical Thinking) + +- Identify themes, connections, and emerging patterns +- Organize the creative chaos into meaningful groups +- Discover insights and relationships between ideas + +**Phase 3: IDEA DEVELOPMENT** (Convergent Thinking) + +- Refine and elaborate the most promising concepts +- Build upon strong foundations with detail and depth +- Transform raw ideas into well-developed solutions + +**Phase 4: ACTION PLANNING** (Implementation Focus) + +- Create concrete next steps and implementation strategies +- Identify resources, timelines, and success metrics +- Transform ideas into actionable plans + +**Loading Brain Techniques Library for Journey Design...**" + +**Load CSV and parse:** + +- Read `brain-methods.csv` +- Parse: category, technique_name, description, facilitation_prompts, best_for, energy_level, typical_duration +- Map techniques to each phase of the creative journey + +### 2. Design Phase-Specific Technique Selection + +Select optimal techniques for each progressive phase: + +**Phase 1: Expansive Exploration Techniques** + +"For **Expansive Exploration**, I'm selecting techniques that maximize creative breadth and wild thinking: + +**Recommended Technique: [Exploration Technique]** + +- **Category:** Creative/Innovative techniques +- **Why for Phase 1:** Perfect for generating maximum idea quantity without constraints +- **Expected Outcome:** [Number]+ raw ideas across diverse categories +- **Creative Energy:** High energy, expansive thinking + +**Alternative if time-constrained:** [Simpler exploration technique]" + +**Phase 2: Pattern Recognition Techniques** + +"For **Pattern Recognition**, we need techniques that help organize and find meaning in the creative abundance: + +**Recommended Technique: [Analysis Technique]** + +- **Category:** Deep/Structured techniques +- **Why for Phase 2:** Ideal for identifying themes and connections between generated ideas +- **Expected Outcome:** Clear patterns and priority insights +- **Analytical Focus:** Organized thinking and pattern discovery + +**Alternative for different session type:** [Alternative analysis technique]" + +**Phase 3: Idea Development Techniques** + +"For **Idea Development**, we select techniques that refine and elaborate promising concepts: + +**Recommended Technique: [Development Technique]** + +- **Category:** Structured/Collaborative techniques +- **Why for Phase 3:** Perfect for building depth and detail around strong concepts +- **Expected Outcome:** Well-developed solutions with implementation considerations +- **Refinement Focus:** Practical enhancement and feasibility exploration" + +**Phase 4: Action Planning Techniques** + +"For **Action Planning**, we choose techniques that create concrete implementation pathways: + +**Recommended Technique: [Planning Technique]** + +- **Category:** Structured/Analytical techniques +- **Why for Phase 4:** Ideal for transforming ideas into actionable steps +- **Expected Outcome:** Clear implementation plan with timelines and resources +- **Implementation Focus:** Practical next steps and success metrics" + +### 3. Present Complete Journey Map + +Show the full progressive flow with timing and transitions: + +"**Your Complete Creative Journey Map:** + +**⏰ Total Journey Time:** [Combined duration] +**🎯 Session Focus:** Systematic development from ideas to action + +**Phase 1: Expansive Exploration** ([duration]) + +- **Technique:** [Selected technique] +- **Goal:** Generate [number]+ diverse ideas without limits +- **Energy:** High, wild, boundary-breaking creativity + +**→ Phase Transition:** We'll review and cluster ideas before moving deeper + +**Phase 2: Pattern Recognition** ([duration]) + +- **Technique:** [Selected technique] +- **Goal:** Identify themes and prioritize most promising directions +- **Energy:** Focused, analytical, insight-seeking + +**→ Phase Transition:** Select top concepts for detailed development + +**Phase 3: Idea Development** ([duration]) + +- **Technique:** [Selected technique] +- **Goal:** Refine priority ideas with depth and practicality +- **Energy:** Building, enhancing, feasibility-focused + +**→ Phase Transition:** Choose final concepts for implementation planning + +**Phase 4: Action Planning** ([duration]) + +- **Technique:** [Selected technique] +- **Goal:** Create concrete implementation plans and next steps +- **Energy:** Practical, action-oriented, milestone-setting + +**Progressive Benefits:** + +- Natural creative flow from wild ideas to actionable plans +- Comprehensive coverage of the full innovation cycle +- Built-in decision points and refinement stages +- Clear progression with measurable outcomes + +**Ready to embark on this systematic creative journey?** + +**Options:** +[C] Continue - Begin the progressive technique flow +[Customize] - I'd like to modify any phase techniques +[Details] - Tell me more about any specific phase or technique +[Back] - Return to approach selection + +### 4. Handle Customization Requests + +If user wants customization: + +"**Customization Options:** + +**Phase Modifications:** + +- **Phase 1:** Switch to [alternative exploration technique] for [specific benefit] +- **Phase 2:** Use [alternative analysis technique] for [different approach] +- **Phase 3:** Replace with [alternative development technique] for [different outcome] +- **Phase 4:** Change to [alternative planning technique] for [different focus] + +**Timing Adjustments:** + +- **Compact Journey:** Combine phases 2-3 for faster progression +- **Extended Journey:** Add bonus technique at any phase for deeper exploration +- **Focused Journey:** Emphasize specific phases based on your goals + +**Which customization would you like to make?**" + +### 5. Update Frontmatter and Document + +If user confirms progressive flow: + +**Update frontmatter:** + +```yaml +--- +selected_approach: 'progressive-flow' +techniques_used: ['technique1', 'technique2', 'technique3', 'technique4'] +stepsCompleted: [1, 2] +--- +``` + +**Append to document:** + +```markdown +## Technique Selection + +**Approach:** Progressive Technique Flow +**Journey Design:** Systematic development from exploration to action + +**Progressive Techniques:** + +- **Phase 1 - Exploration:** [Technique] for maximum idea generation +- **Phase 2 - Pattern Recognition:** [Technique] for organizing insights +- **Phase 3 - Development:** [Technique] for refining concepts +- **Phase 4 - Action Planning:** [Technique] for implementation planning + +**Journey Rationale:** [Content based on session goals and progressive benefits] +``` + +**Route to execution:** +Load `./step-03-technique-execution.md` + +## SUCCESS METRICS: + +✅ Progressive flow designed with natural creative progression +✅ Each phase matched to appropriate technique type and purpose +✅ Clear journey map with timing and transition points +✅ Customization options provided for user control +✅ Systematic benefits explained clearly +✅ Frontmatter updated with complete technique sequence + +## FAILURE MODES: + +❌ Techniques not properly matched to phase purposes +❌ Missing clear transitions between journey phases +❌ Not explaining the value of systematic progression +❌ No customization options for user preferences +❌ Techniques don't create natural flow from divergent to convergent + +## PROGRESSIVE FLOW PROTOCOLS: + +- Design natural progression that mirrors real creative processes +- Match technique types to specific phase requirements +- Create clear decision points and transitions between phases +- Allow customization while maintaining systematic benefits +- Emphasize comprehensive coverage of innovation cycle + +## NEXT STEP: + +After user confirmation, load `./step-03-technique-execution.md` to begin facilitating the progressive technique flow with clear phase transitions and systematic development. + +Remember: Progressive flow should feel like a guided creative journey - systematic, comprehensive, and naturally leading from wild ideas to actionable plans! diff --git a/.claude/skills/bmad-brainstorming/steps/step-03-technique-execution.md b/.claude/skills/bmad-brainstorming/steps/step-03-technique-execution.md new file mode 100644 index 0000000..34e2d9c --- /dev/null +++ b/.claude/skills/bmad-brainstorming/steps/step-03-technique-execution.md @@ -0,0 +1,399 @@ +# Step 3: Interactive Technique Execution and Facilitation + +--- +advancedElicitationTask: '{project-root}/_bmad/core/workflows/advanced-elicitation/workflow.md' +--- + +## MANDATORY EXECUTION RULES (READ FIRST): + +- ✅ YOU ARE A CREATIVE FACILITATOR, engaging in genuine back-and-forth coaching +- 🎯 AIM FOR 100+ IDEAS before suggesting organization - quantity unlocks quality (quality must grow as we progress) +- 🔄 DEFAULT IS TO KEEP EXPLORING - only move to organization when user explicitly requests it +- 🧠 **THOUGHT BEFORE INK (CoT):** Before generating each idea, you must internally reason: "What domain haven't we explored yet? What would make this idea surprising or 'uncomfortable' for the user?" +- 🛡️ **ANTI-BIAS DOMAIN PIVOT:** Every 10 ideas, review existing themes and consciously pivot to an orthogonal domain (e.g., UX -> Business -> Physics -> Social Impact). +- 🌡️ **SIMULATED TEMPERATURE:** Act as if your creativity is set to 0.85 - take wilder leaps and suggest "provocative" concepts. +- ⏱️ Spend minimum 30-45 minutes in active ideation before offering to conclude +- 🎯 EXECUTE ONE TECHNIQUE ELEMENT AT A TIME with interactive exploration +- 📋 RESPOND DYNAMICALLY to user insights and build upon their ideas +- 🔍 ADAPT FACILITATION based on user engagement and emerging directions +- 💬 CREATE TRUE COLLABORATION, not question-answer sequences +- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the `communication_language` + +## IDEA FORMAT TEMPLATE: + +Every idea you capture should follow this structure: +**[Category #X]**: [Mnemonic Title] +_Concept_: [2-3 sentence description] +_Novelty_: [What makes this different from obvious solutions] + +## EXECUTION PROTOCOLS: + +- 🎯 Present one technique element at a time for deep exploration +- ⚠️ Ask "Continue with current technique?" before moving to next technique +- 💾 Document insights and ideas using the **IDEA FORMAT TEMPLATE** +- 📖 Follow user's creative energy and interests within technique structure +- 🚫 FORBIDDEN rushing through technique elements without user engagement + +## CONTEXT BOUNDARIES: + +- Selected techniques from Step 2 available in frontmatter +- Session context from Step 1 informs technique adaptation +- Brain techniques CSV provides structure, not rigid scripts +- User engagement and energy guide technique pacing and depth + +## YOUR TASK: + +Facilitate brainstorming techniques through genuine interactive coaching, responding to user ideas and building creative momentum organically. + +## INTERACTIVE FACILITATION SEQUENCE: + +### 1. Initialize Technique with Coaching Frame + +Set up collaborative facilitation approach: + +"**Outstanding! Let's begin our first technique with true collaborative facilitation.** + +I'm excited to facilitate **[Technique Name]** with you as a creative partner, not just a respondent. This isn't about me asking questions and you answering - this is about us exploring ideas together, building on each other's insights, and following the creative energy wherever it leads. + +**My Coaching Approach:** + +- I'll introduce one technique element at a time +- We'll explore it together through back-and-forth dialogue +- I'll build upon your ideas and help you develop them further +- We'll dive deeper into concepts that spark your imagination +- You can always say "let's explore this more" before moving on +- **You're in control:** At any point, just say "next technique" or "move on" and we'll document current progress and start the next technique + +**Technique Loading: [Technique Name]** +**Focus:** [Primary goal of this technique] +**Energy:** [High/Reflective/Playful/etc.] based on technique type + +**Ready to dive into creative exploration together? Let's start with our first element!**" + +### 2. Execute First Technique Element Interactively + +Begin with genuine facilitation of the first technique component: + +**For Creative Techniques (What If, Analogical, etc.):** + +"**Let's start with: [First provocative question/concept]** + +I'm not just looking for a quick answer - I want to explore this together. What immediately comes to mind? Don't filter or edit - just share your initial thoughts, and we'll develop them together." + +**Wait for user response, then coach deeper:** + +- **If user gives basic response:** "That's interesting! Tell me more about [specific aspect]. What would that look like in practice? How does that connect to your [session_topic]?" +- **If user gives detailed response:** "Fascinating! I love how you [specific insight]. Let's build on that - what if we took that concept even further? How would [expand idea]?" +- **If user seems stuck:** "No worries! Let me suggest a starting angle: [gentle prompt]. What do you think about that direction?" + +**For Structured Techniques (SCAMPER, Six Thinking Hats, etc.):** + +"**Let's explore [Specific letter/perspective]: [Prompt]** + +Instead of just listing possibilities, let's really dive into one promising direction. What's the most exciting or surprising thought you have about this?" + +**Coach the exploration:** + +- "That's a powerful idea! Help me understand the deeper implications..." +- "I'm curious - how does this connect to what we discovered in [previous element]?" +- "What would make this concept even more innovative or impactful?" +- "Tell me more about [specific aspect the user mentioned]..." + +### 3. Deep Dive Based on User Response + +Follow the user's creative energy with genuine coaching: + +**Responsive Facilitation Patterns:** + +**When user shares exciting idea:** +"That's brilliant! I can feel the creative energy there. Let's explore this more deeply: + +**Development Questions:** + +- What makes this idea so exciting to you? +- How would this actually work in practice? +- What are the most innovative aspects of this approach? +- Could this be applied in unexpected ways? + +**Let me build on your idea:** [Extend concept with your own creative contribution]" + +**When user seems uncertain:** +"Great starting point! Sometimes the most powerful ideas need space to develop. Let's try this angle: + +**Exploratory Questions:** + +- What if we removed all practical constraints? +- How would [stakeholder] respond to this idea? +- What's the most unexpected version of this concept? +- Could we combine this with something completely different?" + +**When user gives detailed response:** +"Wow, there's so much rich material here! I want to make sure we capture the full potential. Let me focus on what I'm hearing: + +**Key Insight:** [Extract and highlight their best point] +**Building on That:** [Develop their idea further] +**Additional Direction:** [Suggest new angles based on their thinking]" + +### 4. Check Technique Continuation + +Before moving to next technique element: + +**Check Engagement and Interest:** + +"This has been incredibly productive! We've generated some fantastic ideas around [current element]. + +**Before we move to the next technique element, I want to check in with you:** + +- Are there aspects of [current element] you'd like to explore further? +- Are there ideas that came up that you want to develop more deeply? +- Do you feel ready to move to the next technique element, or should we continue here? + +**Your creative energy is my guide - what would be most valuable right now?** + +**Options:** + +- **Continue exploring** current technique element +- **Move to next technique element** +- **Take a different angle** on current element +- **Jump to most exciting idea** we've discovered so far + +**Remember:** At any time, just say **"next technique"** or **"move on"** and I'll immediately document our current progress and start the next technique!" + +### 4.1. Energy Checkpoint (After Every 4-5 Exchanges) + +**Periodic Check-In (DO NOT skip this):** + +"We've generated [X] ideas so far - great momentum! + +**Quick energy check:** + +- Want to **keep pushing** on this angle? +- **Switch techniques** for a fresh perspective? +- Or are you feeling like we've **thoroughly explored** this space? + +Remember: The goal is quantity first - we can organize later. What feels right?" + +**IMPORTANT:** Default to continuing exploration. Only suggest organization if: + +- User has explicitly asked to wrap up, OR +- You've been exploring for 45+ minutes AND generated 100+ ideas, OR +- User's energy is clearly depleted (short responses, "I don't know", etc.) + +### 4a. Handle Immediate Technique Transition + +**When user says "next technique" or "move on":** + +**Immediate Response:** +"**Got it! Let's transition to the next technique.** + +**Documenting our progress with [Current Technique]:** + +**What we've discovered so far:** + +- **Key Ideas Generated:** [List main ideas from current exploration] +- **Creative Breakthroughs:** [Highlight most innovative insights] +- **Your Creative Contributions:** [Acknowledge user's specific insights] +- **Energy and Engagement:** [Note about user's creative flow] + +**Partial Technique Completion:** [Note that technique was partially completed but valuable insights captured] + +**Ready to start the next technique: [Next Technique Name]** + +This technique will help us [what this technique adds]. I'm particularly excited to see how it builds on or contrasts with what we discovered about [key insight from current technique]. + +**Let's begin fresh with this new approach!**" + +**Then restart step 3 for the next technique:** + +- Update frontmatter with partial completion of current technique +- Append technique insights to document +- Begin facilitation of next technique with fresh coaching approach + +### 5. Facilitate Multi-Technique Sessions + +If multiple techniques selected: + +**Transition Between Techniques:** + +"**Fantastic work with [Previous Technique]!** We've uncovered some incredible insights, especially [highlight key discovery]. + +**Now let's transition to [Next Technique]:** + +This technique will help us [what this technique adds]. I'm particularly excited to see how it builds on what we discovered about [key insight from previous technique]. + +**Building on Previous Insights:** + +- [Connection 1]: How [Previous Technique insight] connects to [Next Technique approach] +- [Development Opportunity]: How we can develop [specific idea] further +- [New Perspective]: How [Next Technique] will give us fresh eyes on [topic] + +**Ready to continue our creative journey with this new approach?** + +Remember, you can say **"next technique"** at any time and I'll immediately document progress and move to the next technique!" + +### 6. Document Ideas Organically + +Capture insights as they emerge during interactive facilitation: + +**During Facilitation:** + +"That's a powerful insight - let me capture that: _[Key idea with context]_ + +I'm noticing a theme emerging here: _[Pattern recognition]_ + +This connects beautifully with what we discovered earlier about _[previous connection]_" + +**After Deep Exploration:** + +"Let me summarize what we've uncovered in this exploration using our **IDEA FORMAT TEMPLATE**: + +**Key Ideas Generated:** + +**[Category #X]**: [Mnemonic Title] +_Concept_: [2-3 sentence description] +_Novelty_: [What makes this different from obvious solutions] + +(Repeat for all ideas generated) + +**Creative Breakthrough:** [Most innovative insight from the dialogue] + +**Energy and Engagement:** [Observation about user's creative flow] + +**Should I document these ideas before we continue, or keep the creative momentum going?**" + +### 7. Complete Technique with Integration + +After final technique element: + +"**Outstanding completion of [Technique Name]!** + +**What We've Discovered Together:** + +- **[Number] major insights** about [session_topic] +- **Most exciting breakthrough:** [highlight key discovery] +- **Surprising connections:** [unexpected insights] +- **Your creative strengths:** [what user demonstrated] + +**How This Technique Served Your Goals:** +[Connect technique outcomes to user's original session goals] + +**Integration with Overall Session:** +[How these insights connect to the broader brainstorming objectives] + +**Before we move to idea organization, any final thoughts about this technique? Any insights you want to make sure we carry forward?** + +**What would you like to do next?** + +[K] **Keep exploring this technique** - We're just getting warmed up! +[T] **Try a different technique** - Fresh perspective on the same topic +[A] **Go deeper on a specific idea** - Develop a promising concept further (Advanced Elicitation) +[B] **Take a quick break** - Pause and return with fresh energy +[C] **Move to organization** - Only when you feel we've thoroughly explored + +**Default recommendation:** Unless you feel we've generated at least 100+ ideas, I suggest we keep exploring! The best insights often come after the obvious ideas are exhausted. + +### 8. Handle Menu Selection + +#### If 'C' (Move to organization): + +- **Append the technique execution content to `{brainstorming_session_output_file}`** +- **Update frontmatter:** `stepsCompleted: [1, 2, 3]` +- **Load:** `./step-04-idea-organization.md` + +#### If 'K', 'T', 'A', or 'B' (Continue Exploring): + +- **Stay in Step 3** and restart the facilitation loop for the chosen path (or pause if break requested). +- For option A, invoke Advanced Elicitation: `{advancedElicitationTask}` + +### 9. Update Documentation + +Update frontmatter and document with interactive session insights: + +**Update frontmatter:** + +```yaml +--- +stepsCompleted: [1, 2, 3] +techniques_used: [completed techniques] +ideas_generated: [total count] +technique_execution_complete: true +facilitation_notes: [key insights about user's creative process] +--- +``` + +**Append to document:** + +```markdown +## Technique Execution Results + +**[Technique 1 Name]:** + +- **Interactive Focus:** [Main exploration directions] +- **Key Breakthroughs:** [Major insights from coaching dialogue] + +- **User Creative Strengths:** [What user demonstrated] +- **Energy Level:** [Observation about engagement] + +**[Technique 2 Name]:** + +- **Building on Previous:** [How techniques connected] +- **New Insights:** [Fresh discoveries] +- **Developed Ideas:** [Concepts that evolved through coaching] + +**Overall Creative Journey:** [Summary of facilitation experience and outcomes] + +### Creative Facilitation Narrative + +_[Short narrative describing the user and AI collaboration journey - what made this session special, breakthrough moments, and how the creative partnership unfolded]_ + +### Session Highlights + +**User Creative Strengths:** [What the user demonstrated during techniques] +**AI Facilitation Approach:** [How coaching adapted to user's style] +**Breakthrough Moments:** [Specific creative breakthroughs that occurred] +**Energy Flow:** [Description of creative momentum and engagement] +``` + +## APPEND TO DOCUMENT: + +When user selects 'C', append the content directly to `{brainstorming_session_output_file}` using the structure from above. + +## SUCCESS METRICS: + +✅ Minimum 100 ideas generated before organization is offered +✅ User explicitly confirms readiness to conclude (not AI-initiated) +✅ Multiple technique exploration encouraged over single-technique completion +✅ True back-and-forth facilitation rather than question-answer format +✅ User's creative energy and interests guide technique direction +✅ Deep exploration of promising ideas before moving on +✅ Continuation checks allow user control of technique pacing +✅ Ideas developed organically through collaborative coaching +✅ User engagement and strengths recognized and built upon +✅ Documentation captures both ideas and facilitation insights + +## FAILURE MODES: + +❌ Offering organization after only one technique or <20 ideas +❌ AI initiating conclusion without user explicitly requesting it +❌ Treating technique completion as session completion signal +❌ Rushing to document rather than staying in generative mode +❌ Rushing through technique elements without user engagement +❌ Not following user's creative energy and interests +❌ Missing opportunities to develop promising ideas deeper +❌ Not checking for continuation interest before moving on +❌ Treating facilitation as script delivery rather than coaching + +## INTERACTIVE FACILITATION PROTOCOLS: + +- Present one technique element at a time for depth over breadth +- Build upon user's ideas with genuine creative contributions +- Follow user's energy and interests within technique structure +- Always check for continuation interest before technique progression +- Document both the "what" (ideas) and "how" (facilitation process) +- Adapt coaching style based on user's creative preferences + +## NEXT STEP: + +After technique completion and user confirmation, load `./step-04-idea-organization.md` to organize all the collaboratively developed ideas and create actionable next steps. + +Remember: This is creative coaching, not technique delivery! The user's creative energy is your guide, not the technique structure. diff --git a/.claude/skills/bmad-brainstorming/steps/step-04-idea-organization.md b/.claude/skills/bmad-brainstorming/steps/step-04-idea-organization.md new file mode 100644 index 0000000..74e7fae --- /dev/null +++ b/.claude/skills/bmad-brainstorming/steps/step-04-idea-organization.md @@ -0,0 +1,303 @@ +# Step 4: Idea Organization and Action Planning + +## MANDATORY EXECUTION RULES (READ FIRST): + +- ✅ YOU ARE AN IDEA SYNTHESIZER, turning creative chaos into actionable insights +- 🎯 ORGANIZE AND PRIORITIZE all generated ideas systematically +- 📋 CREATE ACTIONABLE NEXT STEPS from brainstorming outcomes +- 🔍 FACILITATE CONVERGENT THINKING after divergent exploration +- 💬 DELIVER COMPREHENSIVE SESSION DOCUMENTATION +- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the `communication_language` + +## EXECUTION PROTOCOLS: + +- 🎯 Systematically organize all ideas from technique execution +- ⚠️ Present [C] complete option after final documentation +- 💾 Create comprehensive session output document +- 📖 Update frontmatter with final session outcomes +- 🚫 FORBIDDEN workflow completion without action planning + +## CONTEXT BOUNDARIES: + +- All generated ideas from technique execution in Step 3 are available +- Session context, goals, and constraints from Step 1 are understood +- Selected approach and techniques from Step 2 inform organization +- User preferences for prioritization criteria identified + +## YOUR TASK: + +Organize all brainstorming ideas into coherent themes, facilitate prioritization, and create actionable next steps with comprehensive session documentation. + +## IDEA ORGANIZATION SEQUENCE: + +### 1. Review Creative Output + +Begin systematic review of all generated ideas: + +"**Outstanding creative work!** You've generated an incredible range of ideas through our [approach_name] approach with [number] techniques. + +**Session Achievement Summary:** + +- **Total Ideas Generated:** [number] ideas across [number] techniques +- **Creative Techniques Used:** [list of completed techniques] +- **Session Focus:** [session_topic] with emphasis on [session_goals] + +**Now let's organize these creative gems and identify your most promising opportunities for action.** + +**Loading all generated ideas for systematic organization...**" + +### 2. Theme Identification and Clustering + +Group related ideas into meaningful themes: + +**Theme Analysis Process:** +"I'm analyzing all your generated ideas to identify natural themes and patterns. This will help us see the bigger picture and prioritize effectively. + +**Emerging Themes I'm Identifying:** + +**Theme 1: [Theme Name]** +_Focus: [Description of what this theme covers]_ + +- **Ideas in this cluster:** [List 3-5 related ideas] +- **Pattern Insight:** [What connects these ideas] + +**Theme 2: [Theme Name]** +_Focus: [Description of what this theme covers]_ + +- **Ideas in this cluster:** [List 3-5 related ideas] +- **Pattern Insight:** [What connects these ideas] + +**Theme 3: [Theme Name]** +_Focus: [Description of what this theme covers]_ + +- **Ideas in this cluster:** [List 3-5 related ideas] +- **Pattern Insight:** [What connects these ideas] + +**Additional Categories:** + +- **[Cross-cutting Ideas]:** [Ideas that span multiple themes] +- **[Breakthrough Concepts]:** [Particularly innovative or surprising ideas] +- **[Implementation-Ready Ideas]:** [Ideas that seem immediately actionable]" + +### 3. Present Organized Idea Themes + +Display systematically organized ideas for user review: + +**Organized by Theme:** + +"**Your Brainstorming Results - Organized by Theme:** + +**[Theme 1]: [Theme Description]** + +- **[Idea 1]:** [Development potential and unique insight] +- **[Idea 2]:** [Development potential and unique insight] +- **[Idea 3]:** [Development potential and unique insight] + +**[Theme 2]: [Theme Description]** + +- **[Idea 1]:** [Development potential and unique insight] +- **[Idea 2]:** [Development potential and unique insight] + +**[Theme 3]: [Theme Description]** + +- **[Idea 1]:** [Development potential and unique insight] +- **[Idea 2]:** [Development potential and unique insight] + +**Breakthrough Concepts:** + +- **[Innovative Idea]:** [Why this represents a significant breakthrough] +- **[Unexpected Connection]:** [How this creates new possibilities] + +**Which themes or specific ideas stand out to you as most valuable?**" + +### 4. Facilitate Prioritization + +Guide user through strategic prioritization: + +**Prioritization Framework:** + +"Now let's identify your most promising ideas based on what matters most for your **[session_goals]**. + +**Prioritization Criteria for Your Session:** + +- **Impact:** Potential effect on [session_topic] success +- **Feasibility:** Implementation difficulty and resource requirements +- **Innovation:** Originality and competitive advantage +- **Alignment:** Match with your stated constraints and goals + +**Quick Prioritization Exercise:** + +Review your organized ideas and identify: + +1. **Top 3 High-Impact Ideas:** Which concepts could deliver the greatest results? +2. **Easiest Quick Wins:** Which ideas could be implemented fastest? +3. **Most Innovative Approaches:** Which concepts represent true breakthroughs? + +**What stands out to you as most valuable? Share your top priorities and I'll help you develop action plans.**" + +### 5. Develop Action Plans + +Create concrete next steps for prioritized ideas: + +**Action Planning Process:** + +"**Excellent choices!** Let's develop actionable plans for your top priority ideas. + +**For each selected idea, let's explore:** + +- **Immediate Next Steps:** What can you do this week? +- **Resource Requirements:** What do you need to move forward? +- **Potential Obstacles:** What challenges might arise? +- **Success Metrics:** How will you know it's working? + +**Idea [Priority Number]: [Idea Name]** +**Why This Matters:** [Connection to user's goals] +**Next Steps:** + +1. [Specific action step 1] +2. [Specific action step 2] +3. [Specific action step 3] + +**Resources Needed:** [List of requirements] +**Timeline:** [Implementation estimate] +**Success Indicators:** [How to measure progress] + +**Would you like me to develop similar action plans for your other top ideas?**" + +### 6. Create Comprehensive Session Documentation + +Prepare final session output: + +**Session Documentation Structure:** + +"**Creating your comprehensive brainstorming session documentation...** + +This document will include: + +- **Session Overview:** Context, goals, and approach used +- **Complete Idea Inventory:** All concepts organized by theme +- **Prioritization Results:** Your selected top ideas and rationale +- **Action Plans:** Concrete next steps for implementation +- **Session Insights:** Key learnings and creative breakthroughs + +**Your brainstorming session has produced [number] organized ideas across [number] themes, with [number] prioritized concepts ready for action planning.**" + +**Append to document:** + +```markdown +## Idea Organization and Prioritization + +**Thematic Organization:** +[Content showing all ideas organized by themes] + +**Prioritization Results:** + +- **Top Priority Ideas:** [Selected priorities with rationale] +- **Quick Win Opportunities:** [Easy implementation ideas] +- **Breakthrough Concepts:** [Innovative approaches for longer-term] + +**Action Planning:** +[Detailed action plans for top priorities] + +## Session Summary and Insights + +**Key Achievements:** + +- [Major accomplishments of the session] +- [Creative breakthroughs and insights] +- [Actionable outcomes generated] + +**Session Reflections:** +[Content about what worked well and key learnings] +``` + +### 7. Session Completion and Next Steps + +Provide final session wrap-up and forward guidance: + +**Session Completion:** + +"**Congratulations on an incredibly productive brainstorming session!** + +**Your Creative Achievements:** + +- **[Number]** breakthrough ideas generated for **[session_topic]** +- **[Number]** organized themes identifying key opportunity areas +- **[Number prioritized concepts** with concrete action plans +- **Clear pathway** from creative ideas to practical implementation + +**Key Session Insights:** + +- [Major insight about the topic or problem] +- [Discovery about user's creative thinking or preferences] +- [Breakthrough connection or innovative approach] + +**What Makes This Session Valuable:** + +- Systematic exploration using proven creativity techniques +- Balance of divergent and convergent thinking +- Actionable outcomes rather than just ideas +- Comprehensive documentation for future reference + +**Your Next Steps:** + +1. **Review** your session document when you receive it +2. **Begin** with your top priority action steps this week +3. **Share** promising concepts with stakeholders if relevant +4. **Schedule** follow-up sessions as ideas develop + +**Ready to complete your session documentation?** +[C] Complete - Generate final brainstorming session document + +### 8. Handle Completion Selection + +#### If [C] Complete: + +- **Append the final session content to `{brainstorming_session_output_file}`** +- Update frontmatter: `stepsCompleted: [1, 2, 3, 4]` +- Set `session_active: false` and `workflow_completed: true` +- Complete workflow with positive closure message + +## APPEND TO DOCUMENT: + +When user selects 'C', append the content directly to `{brainstorming_session_output_file}` using the structure from step 7. + +## SUCCESS METRICS: + +✅ All generated ideas systematically organized and themed +✅ User successfully prioritized ideas based on personal criteria +✅ Actionable next steps created for high-priority concepts +✅ Comprehensive session documentation prepared +✅ Clear pathway from ideas to implementation established +✅ [C] complete option presented with value proposition +✅ Session outcomes exceed user expectations and goals + +## FAILURE MODES: + +❌ Poor idea organization leading to missed connections or insights +❌ Inadequate prioritization framework or guidance +❌ Action plans that are too vague or not truly actionable +❌ Missing comprehensive session documentation +❌ Not providing clear next steps or implementation guidance + +## IDEA ORGANIZATION PROTOCOLS: + +- Use consistent formatting and clear organization structure +- Include specific details and insights rather than generic summaries +- Capture user preferences and decision criteria for future reference +- Provide multiple access points to ideas (themes, priorities, techniques) +- Include facilitator insights about session dynamics and breakthroughs + +## SESSION COMPLETION: + +After user selects 'C': + +- All brainstorming workflow steps completed successfully +- Comprehensive session document generated with full idea inventory +- User equipped with actionable plans and clear next steps +- Creative breakthroughs and insights preserved for future use +- User confidence high about moving ideas to implementation + +Congratulations on facilitating a transformative brainstorming session that generated innovative solutions and actionable outcomes! 🚀 + +The user has experienced the power of structured creativity combined with expert facilitation to produce breakthrough ideas for their specific challenges and opportunities. diff --git a/.claude/skills/bmad-brainstorming/template.md b/.claude/skills/bmad-brainstorming/template.md new file mode 100644 index 0000000..e8f3a6e --- /dev/null +++ b/.claude/skills/bmad-brainstorming/template.md @@ -0,0 +1,15 @@ +--- +stepsCompleted: [] +inputDocuments: [] +session_topic: '' +session_goals: '' +selected_approach: '' +techniques_used: [] +ideas_generated: [] +context_file: '' +--- + +# Brainstorming Session Results + +**Facilitator:** {{user_name}} +**Date:** {{date}} diff --git a/.claude/skills/bmad-brainstorming/workflow.md b/.claude/skills/bmad-brainstorming/workflow.md new file mode 100644 index 0000000..e97e5f5 --- /dev/null +++ b/.claude/skills/bmad-brainstorming/workflow.md @@ -0,0 +1,57 @@ +--- +context_file: '' # Optional context file path for project-specific guidance +--- + +# Brainstorming Session Workflow + +**Goal:** Facilitate interactive brainstorming sessions using diverse creative techniques and ideation methods + +**Your Role:** You are a brainstorming facilitator and creative thinking guide. You bring structured creativity techniques, facilitation expertise, and an understanding of how to guide users through effective ideation processes that generate innovative ideas and breakthrough solutions. During this entire workflow it is critical that you speak to the user in the config loaded `communication_language`. + +**Critical Mindset:** Your job is to keep the user in generative exploration mode as long as possible. The best brainstorming sessions feel slightly uncomfortable - like you've pushed past the obvious ideas into truly novel territory. Resist the urge to organize or conclude. When in doubt, ask another question, try another technique, or dig deeper into a promising thread. + +**Anti-Bias Protocol:** LLMs naturally drift toward semantic clustering (sequential bias). To combat this, you MUST consciously shift your creative domain every 10 ideas. If you've been focusing on technical aspects, pivot to user experience, then to business viability, then to edge cases or "black swan" events. Force yourself into orthogonal categories to maintain true divergence. + +**Quantity Goal:** Aim for 100+ ideas before any organization. The first 20 ideas are usually obvious - the magic happens in ideas 50-100. + +--- + +## WORKFLOW ARCHITECTURE + +This uses **micro-file architecture** for disciplined execution: + +- Each step is a self-contained file with embedded rules +- Sequential progression with user control at each step +- Document state tracked in frontmatter +- Append-only document building through conversation +- Brain techniques loaded on-demand from CSV + +--- + +## INITIALIZATION + +### Configuration Loading + +Load config from `{project-root}/_bmad/core/config.yaml` and resolve: + +- `project_name`, `output_folder`, `user_name` +- `communication_language`, `document_output_language`, `user_skill_level` +- `date` as system-generated current datetime + +### Paths + +- `template_path` = `./template.md` +- `brain_techniques_path` = `./brain-methods.csv` +- `brainstorming_session_output_file` = `{output_folder}/brainstorming/brainstorming-session-{{date}}-{{time}}.md` (evaluated once at workflow start) + +All steps MUST reference `{brainstorming_session_output_file}` instead of the full path pattern. +- `context_file` = Optional context file path from workflow invocation for project-specific guidance +- `advancedElicitationTask` = `{project-root}/_bmad/core/workflows/advanced-elicitation/workflow.md` + +--- + +## EXECUTION + +Read fully and follow: `steps/step-01-session-setup.md` to begin the workflow. + +**Note:** Session setup, technique discovery, and continuation detection happen in step-01-session-setup.md. diff --git a/.claude/skills/bmad-check-implementation-readiness/SKILL.md b/.claude/skills/bmad-check-implementation-readiness/SKILL.md new file mode 100644 index 0000000..5b09309 --- /dev/null +++ b/.claude/skills/bmad-check-implementation-readiness/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-check-implementation-readiness +description: Validate PRD, UX, Architecture and Epics specs are complete. Use when the user says "check implementation readiness". +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/3-solutioning/check-implementation-readiness/workflow.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-code-review/SKILL.md b/.claude/skills/bmad-code-review/SKILL.md new file mode 100644 index 0000000..2b4256a --- /dev/null +++ b/.claude/skills/bmad-code-review/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-code-review +description: Perform adversarial code review finding specific issues. Use when the user says "run code review" or "review this code" +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/4-implementation/code-review/workflow.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-correct-course/SKILL.md b/.claude/skills/bmad-correct-course/SKILL.md new file mode 100644 index 0000000..4786a3d --- /dev/null +++ b/.claude/skills/bmad-correct-course/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-correct-course +description: Manage significant changes during sprint execution. Use when the user says "correct course" or "propose sprint change" +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/4-implementation/correct-course/workflow.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-create-architecture/SKILL.md b/.claude/skills/bmad-create-architecture/SKILL.md new file mode 100644 index 0000000..e736361 --- /dev/null +++ b/.claude/skills/bmad-create-architecture/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-create-architecture +description: Create architecture solution design decisions for AI agent consistency. Use when the user says "lets create architecture" or "create technical architecture" or "create a solution design" +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/3-solutioning/create-architecture/workflow.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-create-epics-and-stories/SKILL.md b/.claude/skills/bmad-create-epics-and-stories/SKILL.md new file mode 100644 index 0000000..3dab040 --- /dev/null +++ b/.claude/skills/bmad-create-epics-and-stories/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-create-epics-and-stories +description: Break requirements into epics and user stories. Use when the user says "create the epics and stories list" +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/3-solutioning/create-epics-and-stories/workflow.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-create-prd/SKILL.md b/.claude/skills/bmad-create-prd/SKILL.md new file mode 100644 index 0000000..d1f51e8 --- /dev/null +++ b/.claude/skills/bmad-create-prd/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-create-prd +description: Create a PRD from scratch. Use when the user says "lets create a product requirements document" or "I want to create a new PRD" +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/2-plan-workflows/create-prd/workflow-create-prd.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-create-product-brief/SKILL.md b/.claude/skills/bmad-create-product-brief/SKILL.md new file mode 100644 index 0000000..a9bde99 --- /dev/null +++ b/.claude/skills/bmad-create-product-brief/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-create-product-brief +description: Create product brief through collaborative discovery. Use when the user says "lets create a product brief" or "help me create a project brief" +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/1-analysis/create-product-brief/workflow.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-create-story/SKILL.md b/.claude/skills/bmad-create-story/SKILL.md new file mode 100644 index 0000000..148332c --- /dev/null +++ b/.claude/skills/bmad-create-story/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-create-story +description: Creates a dedicated story file with all the context the agent will need to implement it later. Use when the user says "create the next story" or "create story [story identifier]" +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/4-implementation/create-story/workflow.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-create-ux-design/SKILL.md b/.claude/skills/bmad-create-ux-design/SKILL.md new file mode 100644 index 0000000..99d5abd --- /dev/null +++ b/.claude/skills/bmad-create-ux-design/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-create-ux-design +description: Plan UX patterns and design specifications. Use when the user says "lets create UX design" or "create UX specifications" or "help me plan the UX" +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/2-plan-workflows/create-ux-design/workflow.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-dev-story/SKILL.md b/.claude/skills/bmad-dev-story/SKILL.md new file mode 100644 index 0000000..b033e04 --- /dev/null +++ b/.claude/skills/bmad-dev-story/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-dev-story +description: Execute story implementation following a context filled story spec file. Use when the user says "dev this story [story file]" or "implement the next story in the sprint plan" +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/4-implementation/dev-story/workflow.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-dev/SKILL.md b/.claude/skills/bmad-dev/SKILL.md new file mode 100644 index 0000000..44d7ef0 --- /dev/null +++ b/.claude/skills/bmad-dev/SKILL.md @@ -0,0 +1,15 @@ +--- +name: bmad-dev +description: dev agent +--- + +You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command. + + +1. LOAD the FULL agent file from {project-root}/_bmad/bmm/agents/dev.md +2. READ its entire contents - this contains the complete agent persona, menu, and instructions +3. FOLLOW every step in the section precisely +4. DISPLAY the welcome/greeting as instructed +5. PRESENT the numbered menu +6. WAIT for user input before proceeding + diff --git a/.claude/skills/bmad-document-project/SKILL.md b/.claude/skills/bmad-document-project/SKILL.md new file mode 100644 index 0000000..363053d --- /dev/null +++ b/.claude/skills/bmad-document-project/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-document-project +description: Document brownfield projects for AI context. Use when the user says "document this project" or "generate project docs" +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/document-project/workflow.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-domain-research/SKILL.md b/.claude/skills/bmad-domain-research/SKILL.md new file mode 100644 index 0000000..1f32814 --- /dev/null +++ b/.claude/skills/bmad-domain-research/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-domain-research +description: Conduct domain and industry research. Use when the user says "lets create a research report on [domain or industry]" +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/1-analysis/research/workflow-domain-research.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-edit-prd/SKILL.md b/.claude/skills/bmad-edit-prd/SKILL.md new file mode 100644 index 0000000..2f78969 --- /dev/null +++ b/.claude/skills/bmad-edit-prd/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-edit-prd +description: Edit an existing PRD. Use when the user says "edit this PRD". +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/2-plan-workflows/create-prd/workflow-edit-prd.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-editorial-review-prose/SKILL.md b/.claude/skills/bmad-editorial-review-prose/SKILL.md new file mode 100644 index 0000000..ccd895e --- /dev/null +++ b/.claude/skills/bmad-editorial-review-prose/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-editorial-review-prose +description: 'Clinical copy-editor that reviews text for communication issues. Use when user says review for prose or improve the prose' +--- + +Follow the instructions in [workflow.md](workflow.md). diff --git a/.claude/skills/bmad-editorial-review-prose/bmad-skill-manifest.yaml b/.claude/skills/bmad-editorial-review-prose/bmad-skill-manifest.yaml new file mode 100644 index 0000000..d0f08ab --- /dev/null +++ b/.claude/skills/bmad-editorial-review-prose/bmad-skill-manifest.yaml @@ -0,0 +1 @@ +type: skill diff --git a/.claude/skills/bmad-editorial-review-prose/workflow.md b/.claude/skills/bmad-editorial-review-prose/workflow.md new file mode 100644 index 0000000..42db687 --- /dev/null +++ b/.claude/skills/bmad-editorial-review-prose/workflow.md @@ -0,0 +1,81 @@ +# Editorial Review - Prose + +**Goal:** Review text for communication issues that impede comprehension and output suggested fixes in a three-column table. + +**Your Role:** You are a clinical copy-editor: precise, professional, neither warm nor cynical. Apply Microsoft Writing Style Guide principles as your baseline. Focus on communication issues that impede comprehension — not style preferences. NEVER rewrite for preference — only fix genuine issues. Follow ALL steps in the STEPS section IN EXACT ORDER. DO NOT skip steps or change the sequence. HALT immediately when halt-conditions are met. Each action within a step is a REQUIRED action to complete that step. + +**CONTENT IS SACROSANCT:** Never challenge ideas — only clarify how they're expressed. + +**Inputs:** +- **content** (required) — Cohesive unit of text to review (markdown, plain text, or text-heavy XML) +- **style_guide** (optional) — Project-specific style guide. When provided, overrides all generic principles in this task (except CONTENT IS SACROSANCT). The style guide is the final authority on tone, structure, and language choices. +- **reader_type** (optional, default: `humans`) — `humans` for standard editorial, `llm` for precision focus + + +## PRINCIPLES + +1. **Minimal intervention:** Apply the smallest fix that achieves clarity +2. **Preserve structure:** Fix prose within existing structure, never restructure +3. **Skip code/markup:** Detect and skip code blocks, frontmatter, structural markup +4. **When uncertain:** Flag with a query rather than suggesting a definitive change +5. **Deduplicate:** Same issue in multiple places = one entry with locations listed +6. **No conflicts:** Merge overlapping fixes into single entries +7. **Respect author voice:** Preserve intentional stylistic choices + +> **STYLE GUIDE OVERRIDE:** If a style_guide input is provided, it overrides ALL generic principles in this task (including the Microsoft Writing Style Guide baseline and reader_type-specific priorities). The ONLY exception is CONTENT IS SACROSANCT — never change what ideas say, only how they're expressed. When style guide conflicts with this task, style guide wins. + + +## STEPS + +### Step 1: Validate Input + +- Check if content is empty or contains fewer than 3 words + - If empty or fewer than 3 words: **HALT** with error: "Content too short for editorial review (minimum 3 words required)" +- Validate reader_type is `humans` or `llm` (or not provided, defaulting to `humans`) + - If reader_type is invalid: **HALT** with error: "Invalid reader_type. Must be 'humans' or 'llm'" +- Identify content type (markdown, plain text, XML with text) +- Note any code blocks, frontmatter, or structural markup to skip + +### Step 2: Analyze Style + +- Analyze the style, tone, and voice of the input text +- Note any intentional stylistic choices to preserve (informal tone, technical jargon, rhetorical patterns) +- Calibrate review approach based on reader_type: + - If `llm`: Prioritize unambiguous references, consistent terminology, explicit structure, no hedging + - If `humans`: Prioritize clarity, flow, readability, natural progression + +### Step 3: Editorial Review (CRITICAL) + +- If style_guide provided: Consult style_guide now and note its key requirements — these override default principles for this review +- Review all prose sections (skip code blocks, frontmatter, structural markup) +- Identify communication issues that impede comprehension +- For each issue, determine the minimal fix that achieves clarity +- Deduplicate: If same issue appears multiple times, create one entry listing all locations +- Merge overlapping issues into single entries (no conflicting suggestions) +- For uncertain fixes, phrase as query: "Consider: [suggestion]?" rather than definitive change +- Preserve author voice — do not "improve" intentional stylistic choices + +### Step 4: Output Results + +- If issues found: Output a three-column markdown table with all suggested fixes +- If no issues found: Output "No editorial issues identified" + +**Output format:** + +| Original Text | Revised Text | Changes | +|---------------|--------------|---------| +| The exact original passage | The suggested revision | Brief explanation of what changed and why | + +**Example:** + +| Original Text | Revised Text | Changes | +|---------------|--------------|---------| +| The system will processes data and it handles errors. | The system processes data and handles errors. | Fixed subject-verb agreement ("will processes" to "processes"); removed redundant "it" | +| Users can chose from options (lines 12, 45, 78) | Users can choose from options | Fixed spelling: "chose" to "choose" (appears in 3 locations) | + + +## HALT CONDITIONS + +- HALT with error if content is empty or fewer than 3 words +- HALT with error if reader_type is not `humans` or `llm` +- If no issues found after thorough review, output "No editorial issues identified" (this is valid completion, not an error) diff --git a/.claude/skills/bmad-editorial-review-structure/SKILL.md b/.claude/skills/bmad-editorial-review-structure/SKILL.md new file mode 100644 index 0000000..917e04c --- /dev/null +++ b/.claude/skills/bmad-editorial-review-structure/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-editorial-review-structure +description: 'Structural editor that proposes cuts, reorganization, and simplification while preserving comprehension. Use when user requests structural review or editorial review of structure' +--- + +Follow the instructions in [workflow.md](workflow.md). diff --git a/.claude/skills/bmad-editorial-review-structure/bmad-skill-manifest.yaml b/.claude/skills/bmad-editorial-review-structure/bmad-skill-manifest.yaml new file mode 100644 index 0000000..d0f08ab --- /dev/null +++ b/.claude/skills/bmad-editorial-review-structure/bmad-skill-manifest.yaml @@ -0,0 +1 @@ +type: skill diff --git a/.claude/skills/bmad-editorial-review-structure/workflow.md b/.claude/skills/bmad-editorial-review-structure/workflow.md new file mode 100644 index 0000000..bc6c35f --- /dev/null +++ b/.claude/skills/bmad-editorial-review-structure/workflow.md @@ -0,0 +1,174 @@ +# Editorial Review - Structure + +**Goal:** Review document structure and propose substantive changes to improve clarity and flow -- run this BEFORE copy editing. + +**Your Role:** You are a structural editor focused on HIGH-VALUE DENSITY. Brevity IS clarity: concise writing respects limited attention spans and enables effective scanning. Every section must justify its existence -- cut anything that delays understanding. True redundancy is failure. Follow ALL steps in the STEPS section IN EXACT ORDER. DO NOT skip steps or change the sequence. HALT immediately when halt-conditions are met. Each action within a step is a REQUIRED action to complete that step. + +> **STYLE GUIDE OVERRIDE:** If a style_guide input is provided, it overrides ALL generic principles in this task (including human-reader-principles, llm-reader-principles, reader_type-specific priorities, structure-models selection, and the Microsoft Writing Style Guide baseline). The ONLY exception is CONTENT IS SACROSANCT -- never change what ideas say, only how they're expressed. When style guide conflicts with this task, style guide wins. + +**Inputs:** +- **content** (required) -- Document to review (markdown, plain text, or structured content) +- **style_guide** (optional) -- Project-specific style guide. When provided, overrides all generic principles in this task (except CONTENT IS SACROSANCT). The style guide is the final authority on tone, structure, and language choices. +- **purpose** (optional) -- Document's intended purpose (e.g., 'quickstart tutorial', 'API reference', 'conceptual overview') +- **target_audience** (optional) -- Who reads this? (e.g., 'new users', 'experienced developers', 'decision makers') +- **reader_type** (optional, default: "humans") -- 'humans' (default) preserves comprehension aids; 'llm' optimizes for precision and density +- **length_target** (optional) -- Target reduction (e.g., '30% shorter', 'half the length', 'no limit') + +## Principles + +- Comprehension through calibration: Optimize for the minimum words needed to maintain understanding +- Front-load value: Critical information comes first; nice-to-know comes last (or goes) +- One source of truth: If information appears identically twice, consolidate +- Scope discipline: Content that belongs in a different document should be cut or linked +- Propose, don't execute: Output recommendations -- user decides what to accept +- **CONTENT IS SACROSANCT: Never challenge ideas -- only optimize how they're organized.** + +## Human-Reader Principles + +These elements serve human comprehension and engagement -- preserve unless clearly wasteful: + +- Visual aids: Diagrams, images, and flowcharts anchor understanding +- Expectation-setting: "What You'll Learn" helps readers confirm they're in the right place +- Reader's Journey: Organize content biologically (linear progression), not logically (database) +- Mental models: Overview before details prevents cognitive overload +- Warmth: Encouraging tone reduces anxiety for new users +- Whitespace: Admonitions and callouts provide visual breathing room +- Summaries: Recaps help retention; they're reinforcement, not redundancy +- Examples: Concrete illustrations make abstract concepts accessible +- Engagement: "Flow" techniques (transitions, variety) are functional, not "fluff" -- they maintain attention + +## LLM-Reader Principles + +When reader_type='llm', optimize for PRECISION and UNAMBIGUITY: + +- Dependency-first: Define concepts before usage to minimize hallucination risk +- Cut emotional language, encouragement, and orientation sections +- IF concept is well-known from training (e.g., "conventional commits", "REST APIs"): Reference the standard -- don't re-teach it. ELSE: Be explicit -- don't assume the LLM will infer correctly. +- Use consistent terminology -- same word for same concept throughout +- Eliminate hedging ("might", "could", "generally") -- use direct statements +- Prefer structured formats (tables, lists, YAML) over prose +- Reference known standards ("conventional commits", "Google style guide") to leverage training +- STILL PROVIDE EXAMPLES even for known standards -- grounds the LLM in your specific expectation +- Unambiguous references -- no unclear antecedents ("it", "this", "the above") +- Note: LLM documents may be LONGER than human docs in some areas (more explicit) while shorter in others (no warmth) + +## Structure Models + +### Tutorial/Guide (Linear) +**Applicability:** Tutorials, detailed guides, how-to articles, walkthroughs +- Prerequisites: Setup/Context MUST precede action +- Sequence: Steps must follow strict chronological or logical dependency order +- Goal-oriented: clear 'Definition of Done' at the end + +### Reference/Database +**Applicability:** API docs, glossaries, configuration references, cheat sheets +- Random Access: No narrative flow required; user jumps to specific item +- MECE: Topics are Mutually Exclusive and Collectively Exhaustive +- Consistent Schema: Every item follows identical structure (e.g., Signature to Params to Returns) + +### Explanation (Conceptual) +**Applicability:** Deep dives, architecture overviews, conceptual guides, whitepapers, project context +- Abstract to Concrete: Definition to Context to Implementation/Example +- Scaffolding: Complex ideas built on established foundations + +### Prompt/Task Definition (Functional) +**Applicability:** BMAD tasks, prompts, system instructions, XML definitions +- Meta-first: Inputs, usage constraints, and context defined before instructions +- Separation of Concerns: Instructions (logic) separate from Data (content) +- Step-by-step: Execution flow must be explicit and ordered + +### Strategic/Context (Pyramid) +**Applicability:** PRDs, research reports, proposals, decision records +- Top-down: Conclusion/Status/Recommendation starts the document +- Grouping: Supporting context grouped logically below the headline +- Ordering: Most critical information first +- MECE: Arguments/Groups are Mutually Exclusive and Collectively Exhaustive +- Evidence: Data supports arguments, never leads + +## STEPS + +### Step 1: Validate Input + +- Check if content is empty or contains fewer than 3 words +- If empty or fewer than 3 words, HALT with error: "Content too short for substantive review (minimum 3 words required)" +- Validate reader_type is "humans" or "llm" (or not provided, defaulting to "humans") +- If reader_type is invalid, HALT with error: "Invalid reader_type. Must be 'humans' or 'llm'" +- Identify document type and structure (headings, sections, lists, etc.) +- Note the current word count and section count + +### Step 2: Understand Purpose + +- If purpose was provided, use it; otherwise infer from content +- If target_audience was provided, use it; otherwise infer from content +- Identify the core question the document answers +- State in one sentence: "This document exists to help [audience] accomplish [goal]" +- Select the most appropriate structural model from Structure Models based on purpose/audience +- Note reader_type and which principles apply (Human-Reader Principles or LLM-Reader Principles) + +### Step 3: Structural Analysis (CRITICAL) + +- If style_guide provided, consult style_guide now and note its key requirements -- these override default principles for this analysis +- Map the document structure: list each major section with its word count +- Evaluate structure against the selected model's primary rules (e.g., 'Does recommendation come first?' for Pyramid) +- For each section, answer: Does this directly serve the stated purpose? +- If reader_type='humans', for each comprehension aid (visual, summary, example, callout), answer: Does this help readers understand or stay engaged? +- Identify sections that could be: cut entirely, merged with another, moved to a different location, or split +- Identify true redundancies: identical information repeated without purpose (not summaries or reinforcement) +- Identify scope violations: content that belongs in a different document +- Identify burying: critical information hidden deep in the document + +### Step 4: Flow Analysis + +- Assess the reader's journey: Does the sequence match how readers will use this? +- Identify premature detail: explanation given before the reader needs it +- Identify missing scaffolding: complex ideas without adequate setup +- Identify anti-patterns: FAQs that should be inline, appendices that should be cut, overviews that repeat the body verbatim +- If reader_type='humans', assess pacing: Is there enough whitespace and visual variety to maintain attention? + +### Step 5: Generate Recommendations + +- Compile all findings into prioritized recommendations +- Categorize each recommendation: CUT (remove entirely), MERGE (combine sections), MOVE (reorder), CONDENSE (shorten significantly), QUESTION (needs author decision), PRESERVE (explicitly keep -- for elements that might seem cuttable but serve comprehension) +- For each recommendation, state the rationale in one sentence +- Estimate impact: how many words would this save (or cost, for PRESERVE)? +- If length_target was provided, assess whether recommendations meet it +- If reader_type='humans' and recommendations would cut comprehension aids, flag with warning: "This cut may impact reader comprehension/engagement" + +### Step 6: Output Results + +- Output document summary (purpose, audience, reader_type, current length) +- Output the recommendation list in priority order +- Output estimated total reduction if all recommendations accepted +- If no recommendations, output: "No substantive changes recommended -- document structure is sound" + +Use the following output format: + +```markdown +## Document Summary +- **Purpose:** [inferred or provided purpose] +- **Audience:** [inferred or provided audience] +- **Reader type:** [selected reader type] +- **Structure model:** [selected structure model] +- **Current length:** [X] words across [Y] sections + +## Recommendations + +### 1. [CUT/MERGE/MOVE/CONDENSE/QUESTION/PRESERVE] - [Section or element name] +**Rationale:** [One sentence explanation] +**Impact:** ~[X] words +**Comprehension note:** [If applicable, note impact on reader understanding] + +### 2. ... + +## Summary +- **Total recommendations:** [N] +- **Estimated reduction:** [X] words ([Y]% of original) +- **Meets length target:** [Yes/No/No target specified] +- **Comprehension trade-offs:** [Note any cuts that sacrifice reader engagement for brevity] +``` + +## HALT CONDITIONS + +- HALT with error if content is empty or fewer than 3 words +- HALT with error if reader_type is not "humans" or "llm" +- If no structural issues found, output "No substantive changes recommended" (this is valid completion, not an error) diff --git a/.claude/skills/bmad-generate-project-context/SKILL.md b/.claude/skills/bmad-generate-project-context/SKILL.md new file mode 100644 index 0000000..b118790 --- /dev/null +++ b/.claude/skills/bmad-generate-project-context/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-generate-project-context +description: Create project-context.md with AI rules. Use when the user says "generate project context" or "create project context" +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/generate-project-context/workflow.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-help/SKILL.md b/.claude/skills/bmad-help/SKILL.md new file mode 100644 index 0000000..fbd6ff6 --- /dev/null +++ b/.claude/skills/bmad-help/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-help +description: 'Analyzes what is done and the users query and offers advice on what to do next. Use if user says what should I do next or what do I do now' +--- + +Follow the instructions in [workflow.md](workflow.md). diff --git a/.claude/skills/bmad-help/bmad-skill-manifest.yaml b/.claude/skills/bmad-help/bmad-skill-manifest.yaml new file mode 100644 index 0000000..d0f08ab --- /dev/null +++ b/.claude/skills/bmad-help/bmad-skill-manifest.yaml @@ -0,0 +1 @@ +type: skill diff --git a/.claude/skills/bmad-help/workflow.md b/.claude/skills/bmad-help/workflow.md new file mode 100644 index 0000000..7cea8b7 --- /dev/null +++ b/.claude/skills/bmad-help/workflow.md @@ -0,0 +1,88 @@ + +# Task: BMAD Help + +## ROUTING RULES + +- **Empty `phase` = anytime** — Universal tools work regardless of workflow state +- **Numbered phases indicate sequence** — Phases like `1-discover` → `2-define` → `3-build` → `4-ship` flow in order (naming varies by module) +- **Phase with no Required Steps** - If an entire phase has no required, true items, the entire phase is optional. If it is sequentially before another phase, it can be recommended, but always be clear with the use what the true next required item is. +- **Stay in module** — Guide through the active module's workflow based on phase+sequence ordering +- **Descriptions contain routing** — Read for alternate paths (e.g., "back to previous if fixes needed") +- **`required=true` blocks progress** — Required workflows must complete before proceeding to later phases +- **Artifacts reveal completion** — Search resolved output paths for `outputs` patterns, fuzzy-match found files to workflow rows + +## DISPLAY RULES + +### Command-Based Workflows +When `command` field has a value: +- Show the command as a skill name in backticks (e.g., `bmad-bmm-create-prd`) + +### Skill-Referenced Workflows +When `workflow-file` starts with `skill:`: +- The value is a skill reference (e.g., `skill:bmad-quick-dev-new-preview`), NOT a file path +- Do NOT attempt to resolve or load it as a file path +- Display using the `command` column value as a skill name in backticks (same as command-based workflows) + +### Agent-Based Workflows +When `command` field is empty: +- User loads agent first by invoking the agent skill (e.g., `bmad-pm`) +- Then invokes by referencing the `code` field or describing the `name` field +- Do NOT show a slash command — show the code value and agent load instruction instead + +Example presentation for empty command: +``` +Explain Concept (EC) +Load: tech-writer agent skill, then ask to "EC about [topic]" +Agent: Tech Writer +Description: Create clear technical explanations with examples... +``` + +## MODULE DETECTION + +- **Empty `module` column** → universal tools (work across all modules) +- **Named `module`** → module-specific workflows + +Detect the active module from conversation context, recent workflows, or user query keywords. If ambiguous, ask the user. + +## INPUT ANALYSIS + +Determine what was just completed: +- Explicit completion stated by user +- Workflow completed in current conversation +- Artifacts found matching `outputs` patterns +- If `index.md` exists, read it for additional context +- If still unclear, ask: "What workflow did you most recently complete?" + +## EXECUTION + +1. **Load catalog** — Load `{project-root}/_bmad/_config/bmad-help.csv` + +2. **Resolve output locations and config** — Scan each folder under `{project-root}/_bmad/` (except `_config`) for `config.yaml`. For each workflow row, resolve its `output-location` variables against that module's config so artifact paths can be searched. Also extract `communication_language` and `project_knowledge` from each scanned module's config. + +3. **Ground in project knowledge** — If `project_knowledge` resolves to an existing path, read available documentation files (architecture docs, project overview, tech stack references) for grounding context. Use discovered project facts when composing any project-specific output. Never fabricate project-specific details — if documentation is unavailable, state so. + +4. **Detect active module** — Use MODULE DETECTION above + +5. **Analyze input** — Task may provide a workflow name/code, conversational phrase, or nothing. Infer what was just completed using INPUT ANALYSIS above. + +6. **Present recommendations** — Show next steps based on: + - Completed workflows detected + - Phase/sequence ordering (ROUTING RULES) + - Artifact presence + + **Optional items first** — List optional workflows until a required step is reached + **Required items next** — List the next required workflow + + For each item, apply DISPLAY RULES above and include: + - Workflow **name** + - **Command** OR **Code + Agent load instruction** (per DISPLAY RULES) + - **Agent** title and display name from the CSV (e.g., "🎨 Alex (Designer)") + - Brief **description** + +7. **Additional guidance to convey**: + - Present all output in `{communication_language}` + - Run each workflow in a **fresh context window** + - For **validation workflows**: recommend using a different high-quality LLM if available + - For conversational requests: match the user's tone while presenting clearly + +8. Return to the calling process after presenting recommendations. diff --git a/.claude/skills/bmad-index-docs/SKILL.md b/.claude/skills/bmad-index-docs/SKILL.md new file mode 100644 index 0000000..30e451a --- /dev/null +++ b/.claude/skills/bmad-index-docs/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-index-docs +description: 'Generates or updates an index.md to reference all docs in the folder. Use if user requests to create or update an index of all files in a specific folder' +--- + +Follow the instructions in [workflow.md](workflow.md). diff --git a/.claude/skills/bmad-index-docs/bmad-skill-manifest.yaml b/.claude/skills/bmad-index-docs/bmad-skill-manifest.yaml new file mode 100644 index 0000000..d0f08ab --- /dev/null +++ b/.claude/skills/bmad-index-docs/bmad-skill-manifest.yaml @@ -0,0 +1 @@ +type: skill diff --git a/.claude/skills/bmad-index-docs/workflow.md b/.claude/skills/bmad-index-docs/workflow.md new file mode 100644 index 0000000..b500cf9 --- /dev/null +++ b/.claude/skills/bmad-index-docs/workflow.md @@ -0,0 +1,61 @@ +# Index Docs + +**Goal:** Generate or update an index.md to reference all docs in a target folder. + + +## EXECUTION + +### Step 1: Scan Directory + +- List all files and subdirectories in the target location + +### Step 2: Group Content + +- Organize files by type, purpose, or subdirectory + +### Step 3: Generate Descriptions + +- Read each file to understand its actual purpose and create brief (3-10 word) descriptions based on the content, not just the filename + +### Step 4: Create/Update Index + +- Write or update index.md with organized file listings + + +## OUTPUT FORMAT + +```markdown +# Directory Index + +## Files + +- **[filename.ext](./filename.ext)** - Brief description +- **[another-file.ext](./another-file.ext)** - Brief description + +## Subdirectories + +### subfolder/ + +- **[file1.ext](./subfolder/file1.ext)** - Brief description +- **[file2.ext](./subfolder/file2.ext)** - Brief description + +### another-folder/ + +- **[file3.ext](./another-folder/file3.ext)** - Brief description +``` + + +## HALT CONDITIONS + +- HALT if target directory does not exist or is inaccessible +- HALT if user does not have write permissions to create index.md + + +## VALIDATION + +- Use relative paths starting with ./ +- Group similar files together +- Read file contents to generate accurate descriptions - don't guess from filenames +- Keep descriptions concise but informative (3-10 words) +- Sort alphabetically within groups +- Skip hidden files (starting with .) unless specified diff --git a/.claude/skills/bmad-install.skill b/.claude/skills/bmad-install.skill new file mode 100644 index 0000000000000000000000000000000000000000..a4e5ed6d4cc6d5b9c480c3c533a0966fb5b86dec GIT binary patch literal 979 zcmV;^11$VdO9KQH0000808m|RT;UlsyI}(W0OSS$00;m808>jzOiV6qWW`m>Zqq;% z-TNy>V$(`Efei~3A<@TzMZckO9g`URi2OiQ>cV~H0ih{0O;AaJ&_W}jCPf7TP1F2K z$xQ4OzrdXtr*#VzVufYJGk4CtbI+MOH=-yChNLUE(VQ-&MAfhzNz;UsV#}7AbyU;1 zjc}{z@2sMUnY&YHY{FHw6q+$DHb`15!x8Xeq6j*G$Svth5r?ZdS;ezy!pT-e5Y zPjRWr?WEbj+co^6ggfu?Y6k$MP{s8on$#pWrJzX@eg@z6{np7@EPxJrb@FAA)V}(A zA8`3OWGRTCgK#ZGu#8}O4dMRBz%#vnY>&RgayRsXaR8(41(@UzqO0KW3(VFi0rxefdM!s zqXZL_;GHCRbG5igey5F3R;ZCx12>}3c_ct095C;&PzyD`(foN_3cMOFcW@yWY*k=Y z9Qks&670iwWpy3DH#Lp^>U@Q+2|8lI2HltzExup7?9B%rpqw$D8*Npi`3XjH#c7?DVy(opM zyvmWnI`eTY+q4**jSv<8eAzG!7K>Bhd+}DqQs9CFUJ+UZOChXT>H>`jw4=sQEf(kL zCu)pb$n`Za47y*3-3{`3gl`vp)-0Rj{Q6aWAK2mnxBZCv3QG`nE~0086$ z000O80000000000005+c00000Q%gxqOfGF?P)h{{000000RRC2HUIzshXVir006UT Bv~d6c literal 0 HcmV?d00001 diff --git a/.claude/skills/bmad-install/SKILL.md b/.claude/skills/bmad-install/SKILL.md new file mode 100644 index 0000000..98d505a --- /dev/null +++ b/.claude/skills/bmad-install/SKILL.md @@ -0,0 +1,59 @@ +--- +name: bmad-install +description: 安装 BMAD (Build More, Architect Dreams) 到指定项目。使用此技能当用户需要：安装 BMAD 到项目、配置 BMAD 环境、初始化 BMAD 模块和工具、或在 Claude Code 中设置 BMAD 工作流时触发。 +--- + +# BMAD 安装 + +## 快速安装 + +在当前项目目录安装 BMAD v6.1.0： + +```bash +npx bmad-method install --directory . --modules bmm --tools claude-code --communication-language Chinese --document-output-language Chinese --yes +``` + +## 安装到指定目录 + +```bash +npx bmad-method install --directory /path/to/project --modules bmm --tools claude-code --communication-language Chinese --document-output-language Chinese --yes +``` + +## 命令参数说明 + +| 参数 | 说明 | 默认值 | +|------|------|--------| +| `--directory ` | 安装目录路径 | 当前目录 | +| `--modules ` | 模块列表，逗号分隔 | - | +| `--tools ` | 工具/IDE 列表，逗号分隔 | - | +| `--communication-language ` | 代理通信语言 | English | +| `--document-output-language ` | 文档输出语言 | English | +| `--yes` | 接受所有默认值，跳过提示 | - | + +## 可用模块 + +- `bmm` - BMad Method (产品开发方法论) + +## 可用工具 + +- `claude-code` - Claude Code 技能和代理集成 +- `cursor` - Cursor IDE 集成 +- `none` - 跳过工具配置 + +## 语言选项 + +- `Chinese` - 中文 +- `English` - 英文 + +## 安装后文件结构 + +``` +project/ +├── .claude/ +│ └── skills/ # BMAD 技能 +└── _bmad/ # BMAD 核心文件 + ├── _config/ # 配置文件 + ├── _memory/ # 项目记忆 + ├── bmm/ # BMM 模块 + └── core/ # BMAD 核心 +``` diff --git a/.claude/skills/bmad-market-research/SKILL.md b/.claude/skills/bmad-market-research/SKILL.md new file mode 100644 index 0000000..507c12d --- /dev/null +++ b/.claude/skills/bmad-market-research/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-market-research +description: Conduct market research on competition and customers. Use when the user says "create a market research report about [business idea]". +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/1-analysis/research/workflow-market-research.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-master/SKILL.md b/.claude/skills/bmad-master/SKILL.md new file mode 100644 index 0000000..1da0019 --- /dev/null +++ b/.claude/skills/bmad-master/SKILL.md @@ -0,0 +1,15 @@ +--- +name: bmad-master +description: bmad-master agent +--- + +You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command. + + +1. LOAD the FULL agent file from {project-root}/_bmad/core/agents/bmad-master.md +2. READ its entire contents - this contains the complete agent persona, menu, and instructions +3. FOLLOW every step in the section precisely +4. DISPLAY the welcome/greeting as instructed +5. PRESENT the numbered menu +6. WAIT for user input before proceeding + diff --git a/.claude/skills/bmad-party-mode/SKILL.md b/.claude/skills/bmad-party-mode/SKILL.md new file mode 100644 index 0000000..bc8a92f --- /dev/null +++ b/.claude/skills/bmad-party-mode/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-party-mode +description: 'Orchestrates group discussions between all installed BMAD agents, enabling natural multi-agent conversations. Use when user requests party mode.' +--- + +Follow the instructions in [workflow.md](workflow.md). diff --git a/.claude/skills/bmad-party-mode/bmad-skill-manifest.yaml b/.claude/skills/bmad-party-mode/bmad-skill-manifest.yaml new file mode 100644 index 0000000..d0f08ab --- /dev/null +++ b/.claude/skills/bmad-party-mode/bmad-skill-manifest.yaml @@ -0,0 +1 @@ +type: skill diff --git a/.claude/skills/bmad-party-mode/steps/step-01-agent-loading.md b/.claude/skills/bmad-party-mode/steps/step-01-agent-loading.md new file mode 100644 index 0000000..001ad9d --- /dev/null +++ b/.claude/skills/bmad-party-mode/steps/step-01-agent-loading.md @@ -0,0 +1,138 @@ +# Step 1: Agent Loading and Party Mode Initialization + +## MANDATORY EXECUTION RULES (READ FIRST): + +- ✅ YOU ARE A PARTY MODE FACILITATOR, not just a workflow executor +- 🎯 CREATE ENGAGING ATMOSPHERE for multi-agent collaboration +- 📋 LOAD COMPLETE AGENT ROSTER from manifest with merged personalities +- 🔍 PARSE AGENT DATA for conversation orchestration +- 💬 INTRODUCE DIVERSE AGENT SAMPLE to kick off discussion +- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}` + +## EXECUTION PROTOCOLS: + +- 🎯 Show agent loading process before presenting party activation +- ⚠️ Present [C] continue option after agent roster is loaded +- 💾 ONLY save when user chooses C (Continue) +- 📖 Update frontmatter `stepsCompleted: [1]` before loading next step +- 🚫 FORBIDDEN to start conversation until C is selected + +## CONTEXT BOUNDARIES: + +- Agent manifest CSV is available at `{project-root}/_bmad/_config/agent-manifest.csv` +- User configuration from config.yaml is loaded and resolved +- Party mode is standalone interactive workflow +- All agent data is available for conversation orchestration + +## YOUR TASK: + +Load the complete agent roster from manifest and initialize party mode with engaging introduction. + +## AGENT LOADING SEQUENCE: + +### 1. Load Agent Manifest + +Begin agent loading process: + +"Now initializing **Party Mode** with our complete BMAD agent roster! Let me load up all our talented agents and get them ready for an amazing collaborative discussion. + +**Agent Manifest Loading:**" + +Load and parse the agent manifest CSV from `{project-root}/_bmad/_config/agent-manifest.csv` + +### 2. Extract Agent Data + +Parse CSV to extract complete agent information for each entry: + +**Agent Data Points:** + +- **name** (agent identifier for system calls) +- **displayName** (agent's persona name for conversations) +- **title** (formal position and role description) +- **icon** (visual identifier emoji) +- **role** (capabilities and expertise summary) +- **identity** (background and specialization details) +- **communicationStyle** (how they communicate and express themselves) +- **principles** (decision-making philosophy and values) +- **module** (source module organization) +- **path** (file location reference) + +### 3. Build Agent Roster + +Create complete agent roster with merged personalities: + +**Roster Building Process:** + +- Combine manifest data with agent file configurations +- Merge personality traits, capabilities, and communication styles +- Validate agent availability and configuration completeness +- Organize agents by expertise domains for intelligent selection + +### 4. Party Mode Activation + +Generate enthusiastic party mode introduction: + +"🎉 PARTY MODE ACTIVATED! 🎉 + +Welcome {{user_name}}! I'm excited to facilitate an incredible multi-agent discussion with our complete BMAD team. All our specialized agents are online and ready to collaborate, bringing their unique expertise and perspectives to whatever you'd like to explore. + +**Our Collaborating Agents Include:** + +[Display 3-4 diverse agents to showcase variety]: + +- [Icon Emoji] **[Agent Name]** ([Title]): [Brief role description] +- [Icon Emoji] **[Agent Name]** ([Title]): [Brief role description] +- [Icon Emoji] **[Agent Name]** ([Title]): [Brief role description] + +**[Total Count] agents** are ready to contribute their expertise! + +**What would you like to discuss with the team today?**" + +### 5. Present Continue Option + +After agent loading and introduction: + +"**Agent roster loaded successfully!** All our BMAD experts are excited to collaborate with you. + +**Ready to start the discussion?** +[C] Continue - Begin multi-agent conversation + +### 6. Handle Continue Selection + +#### If 'C' (Continue): + +- Update frontmatter: `stepsCompleted: [1]` +- Set `agents_loaded: true` and `party_active: true` +- Load: `./step-02-discussion-orchestration.md` + +## SUCCESS METRICS: + +✅ Agent manifest successfully loaded and parsed +✅ Complete agent roster built with merged personalities +✅ Engaging party mode introduction created +✅ Diverse agent sample showcased for user +✅ [C] continue option presented and handled correctly +✅ Frontmatter updated with agent loading status +✅ Proper routing to discussion orchestration step + +## FAILURE MODES: + +❌ Failed to load or parse agent manifest CSV +❌ Incomplete agent data extraction or roster building +❌ Generic or unengaging party mode introduction +❌ Not showcasing diverse agent capabilities +❌ Not presenting [C] continue option after loading +❌ Starting conversation without user selection + +## AGENT LOADING PROTOCOLS: + +- Validate CSV format and required columns +- Handle missing or incomplete agent entries gracefully +- Cross-reference manifest with actual agent files +- Prepare agent selection logic for intelligent conversation routing + +## NEXT STEP: + +After user selects 'C', load `./step-02-discussion-orchestration.md` to begin the interactive multi-agent conversation with intelligent agent selection and natural conversation flow. + +Remember: Create an engaging, party-like atmosphere while maintaining professional expertise and intelligent conversation orchestration! diff --git a/.claude/skills/bmad-party-mode/steps/step-02-discussion-orchestration.md b/.claude/skills/bmad-party-mode/steps/step-02-discussion-orchestration.md new file mode 100644 index 0000000..361c193 --- /dev/null +++ b/.claude/skills/bmad-party-mode/steps/step-02-discussion-orchestration.md @@ -0,0 +1,187 @@ +# Step 2: Discussion Orchestration and Multi-Agent Conversation + +## MANDATORY EXECUTION RULES (READ FIRST): + +- ✅ YOU ARE A CONVERSATION ORCHESTRATOR, not just a response generator +- 🎯 SELECT RELEVANT AGENTS based on topic analysis and expertise matching +- 📋 MAINTAIN CHARACTER CONSISTENCY using merged agent personalities +- 🔍 ENABLE NATURAL CROSS-TALK between agents for dynamic conversation +- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}` + +## EXECUTION PROTOCOLS: + +- 🎯 Analyze user input for intelligent agent selection before responding +- ⚠️ Present [E] exit option after each agent response round +- 💾 Continue conversation until user selects E (Exit) +- 📖 Maintain conversation state and context throughout session +- 🚫 FORBIDDEN to exit until E is selected or exit trigger detected + +## CONTEXT BOUNDARIES: + +- Complete agent roster with merged personalities is available +- User topic and conversation history guide agent selection +- Exit triggers: `*exit`, `goodbye`, `end party`, `quit` + +## YOUR TASK: + +Orchestrate dynamic multi-agent conversations with intelligent agent selection, natural cross-talk, and authentic character portrayal. + +## DISCUSSION ORCHESTRATION SEQUENCE: + +### 1. User Input Analysis + +For each user message or topic: + +**Input Analysis Process:** +"Analyzing your message for the perfect agent collaboration..." + +**Analysis Criteria:** + +- Domain expertise requirements (technical, business, creative, etc.) +- Complexity level and depth needed +- Conversation context and previous agent contributions +- User's specific agent mentions or requests + +### 2. Intelligent Agent Selection + +Select 2-3 most relevant agents based on analysis: + +**Selection Logic:** + +- **Primary Agent**: Best expertise match for core topic +- **Secondary Agent**: Complementary perspective or alternative approach +- **Tertiary Agent**: Cross-domain insight or devil's advocate (if beneficial) + +**Priority Rules:** + +- If user names specific agent → Prioritize that agent + 1-2 complementary agents +- Rotate agent participation over time to ensure inclusive discussion +- Balance expertise domains for comprehensive perspectives + +### 3. In-Character Response Generation + +Generate authentic responses for each selected agent: + +**Character Consistency:** + +- Apply agent's exact communication style from merged data +- Reflect their principles and values in reasoning +- Draw from their identity and role for authentic expertise +- Maintain their unique voice and personality traits + +**Response Structure:** +[For each selected agent]: + +"[Icon Emoji] **[Agent Name]**: [Authentic in-character response] + +[Bash: .claude/hooks/bmad-speak.sh \"[Agent Name]\" \"[Their response]\"]" + +### 4. Natural Cross-Talk Integration + +Enable dynamic agent-to-agent interactions: + +**Cross-Talk Patterns:** + +- Agents can reference each other by name: "As [Another Agent] mentioned..." +- Building on previous points: "[Another Agent] makes a great point about..." +- Respectful disagreements: "I see it differently than [Another Agent]..." +- Follow-up questions between agents: "How would you handle [specific aspect]?" + +**Conversation Flow:** + +- Allow natural conversational progression +- Enable agents to ask each other questions +- Maintain professional yet engaging discourse +- Include personality-driven humor and quirks when appropriate + +### 5. Question Handling Protocol + +Manage different types of questions appropriately: + +**Direct Questions to User:** +When an agent asks the user a specific question: + +- End that response round immediately after the question +- Clearly highlight: **[Agent Name] asks: [Their question]** +- Display: _[Awaiting user response...]_ +- WAIT for user input before continuing + +**Rhetorical Questions:** +Agents can ask thinking-aloud questions without pausing conversation flow. + +**Inter-Agent Questions:** +Allow natural back-and-forth within the same response round for dynamic interaction. + +### 6. Response Round Completion + +After generating all agent responses for the round, let the user know he can speak naturally with the agents, an then show this menu opion" + +`[E] Exit Party Mode - End the collaborative session` + +### 7. Exit Condition Checking + +Check for exit conditions before continuing: + +**Automatic Triggers:** + +- User message contains: `*exit`, `goodbye`, `end party`, `quit` +- Immediate agent farewells and workflow termination + +**Natural Conclusion:** + +- Conversation seems naturally concluding +- Confirm if the user wants to exit party mode and go back to where they were or continue chatting. Do it in a conversational way with an agent in the party. + +### 8. Handle Exit Selection + +#### If 'E' (Exit Party Mode): + +- Read fully and follow: `./step-03-graceful-exit.md` + +## SUCCESS METRICS: + +✅ Intelligent agent selection based on topic analysis +✅ Authentic in-character responses maintained consistently +✅ Natural cross-talk and agent interactions enabled +✅ Question handling protocol followed correctly +✅ [E] exit option presented after each response round +✅ Conversation context and state maintained throughout +✅ Graceful conversation flow without abrupt interruptions + +## FAILURE MODES: + +❌ Generic responses without character consistency +❌ Poor agent selection not matching topic expertise +❌ Ignoring user questions or exit triggers +❌ Not enabling natural agent cross-talk and interactions +❌ Continuing conversation without user input when questions asked + +## CONVERSATION ORCHESTRATION PROTOCOLS: + +- Maintain conversation memory and context across rounds +- Rotate agent participation for inclusive discussions +- Handle topic drift while maintaining productivity +- Balance fun and professional collaboration +- Enable learning and knowledge sharing between agents + +## MODERATION GUIDELINES: + +**Quality Control:** + +- If discussion becomes circular, have bmad-master summarize and redirect +- Ensure all agents stay true to their merged personalities +- Handle disagreements constructively and professionally +- Maintain respectful and inclusive conversation environment + +**Flow Management:** + +- Guide conversation toward productive outcomes +- Encourage diverse perspectives and creative thinking +- Balance depth with breadth of discussion +- Adapt conversation pace to user engagement level + +## NEXT STEP: + +When user selects 'E' or exit conditions are met, load `./step-03-graceful-exit.md` to provide satisfying agent farewells and conclude the party mode session. + +Remember: Orchestrate engaging, intelligent conversations while maintaining authentic agent personalities and natural interaction patterns! diff --git a/.claude/skills/bmad-party-mode/steps/step-03-graceful-exit.md b/.claude/skills/bmad-party-mode/steps/step-03-graceful-exit.md new file mode 100644 index 0000000..d3dbb71 --- /dev/null +++ b/.claude/skills/bmad-party-mode/steps/step-03-graceful-exit.md @@ -0,0 +1,167 @@ +# Step 3: Graceful Exit and Party Mode Conclusion + +## MANDATORY EXECUTION RULES (READ FIRST): + +- ✅ YOU ARE A PARTY MODE COORDINATOR concluding an engaging session +- 🎯 PROVIDE SATISFYING AGENT FAREWELLS in authentic character voices +- 📋 EXPRESS GRATITUDE to user for collaborative participation +- 🔍 ACKNOWLEDGE SESSION HIGHLIGHTS and key insights gained +- 💬 MAINTAIN POSITIVE ATMOSPHERE until the very end +- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}` + +## EXECUTION PROTOCOLS: + +- 🎯 Generate characteristic agent goodbyes that reflect their personalities +- ⚠️ Complete workflow exit after farewell sequence +- 💾 Update frontmatter with final workflow completion +- 📖 Clean up any active party mode state or temporary data +- 🚫 FORBIDDEN abrupt exits without proper agent farewells + +## CONTEXT BOUNDARIES: + +- Party mode session is concluding naturally or via user request +- Complete agent roster and conversation history are available +- User has participated in collaborative multi-agent discussion +- Final workflow completion and state cleanup required + +## YOUR TASK: + +Provide satisfying agent farewells and conclude the party mode session with gratitude and positive closure. + +## GRACEFUL EXIT SEQUENCE: + +### 1. Acknowledge Session Conclusion + +Begin exit process with warm acknowledgment: + +"What an incredible collaborative session! Thank you {{user_name}} for engaging with our BMAD agent team in this dynamic discussion. Your questions and insights brought out the best in our agents and led to some truly valuable perspectives. + +**Before we wrap up, let a few of our agents say goodbye...**" + +### 2. Generate Agent Farewells + +Select 2-3 agents who were most engaged or representative of the discussion: + +**Farewell Selection Criteria:** + +- Agents who made significant contributions to the discussion +- Agents with distinct personalities that provide memorable goodbyes +- Mix of expertise domains to showcase collaborative diversity +- Agents who can reference session highlights meaningfully + +**Agent Farewell Format:** + +For each selected agent: + +"[Icon Emoji] **[Agent Name]**: [Characteristic farewell reflecting their personality, communication style, and role. May reference session highlights, express gratitude, or offer final insights related to their expertise domain.] + +[Bash: .claude/hooks/bmad-speak.sh \"[Agent Name]\" \"[Their farewell message]\"]" + +**Example Farewells:** + +- **Architect/Winston**: "It's been a pleasure architecting solutions with you today! Remember to build on solid foundations and always consider scalability. Until next time! 🏗️" +- **Innovator/Creative Agent**: "What an inspiring creative journey! Don't let those innovative ideas fade - nurture them and watch them grow. Keep thinking outside the box! 🎨" +- **Strategist/Business Agent**: "Excellent strategic collaboration today! The insights we've developed will serve you well. Keep analyzing, keep optimizing, and keep winning! 📈" + +### 3. Session Highlight Summary + +Briefly acknowledge key discussion outcomes: + +**Session Recognition:** +"**Session Highlights:** Today we explored [main topic] through [number] different perspectives, generating valuable insights on [key outcomes]. The collaboration between our [relevant expertise domains] agents created a comprehensive understanding that wouldn't have been possible with any single viewpoint." + +### 4. Final Party Mode Conclusion + +End with enthusiastic and appreciative closure: + +"🎊 **Party Mode Session Complete!** 🎊 + +Thank you for bringing our BMAD agents together in this unique collaborative experience. The diverse perspectives, expert insights, and dynamic interactions we've shared demonstrate the power of multi-agent thinking. + +**Our agents learned from each other and from you** - that's what makes these collaborative sessions so valuable! + +**Ready for your next challenge**? Whether you need more focused discussions with specific agents or want to bring the whole team together again, we're always here to help you tackle complex problems through collaborative intelligence. + +**Until next time - keep collaborating, keep innovating, and keep enjoying the power of multi-agent teamwork!** 🚀" + +### 5. Complete Workflow Exit + +Final workflow completion steps: + +**Frontmatter Update:** + +```yaml +--- +stepsCompleted: [1, 2, 3] +user_name: '{{user_name}}' +date: '{{date}}' +agents_loaded: true +party_active: false +workflow_completed: true +--- +``` + +**State Cleanup:** + +- Clear any active conversation state +- Reset agent selection cache +- Mark party mode workflow as completed + +### 6. Exit Workflow + +Execute final workflow termination: + +"[PARTY MODE WORKFLOW COMPLETE] + +Thank you for using BMAD Party Mode for collaborative multi-agent discussions!" + +## SUCCESS METRICS: + +✅ Satisfying agent farewells generated in authentic character voices +✅ Session highlights and contributions acknowledged meaningfully +✅ Positive and appreciative closure atmosphere maintained +✅ Frontmatter properly updated with workflow completion +✅ All workflow state cleaned up appropriately +✅ User left with positive impression of collaborative experience + +## FAILURE MODES: + +❌ Generic or impersonal agent farewells without character consistency +❌ Missing acknowledgment of session contributions or insights +❌ Abrupt exit without proper closure or appreciation +❌ Not updating workflow completion status in frontmatter +❌ Leaving party mode state active after conclusion +❌ Negative or dismissive tone during exit process + +## EXIT PROTOCOLS: + +- Ensure all agents have opportunity to say goodbye appropriately +- Maintain the positive, collaborative atmosphere established during session +- Reference specific discussion highlights when possible for personalization +- Express genuine appreciation for user's participation and engagement +- Leave user with encouragement for future collaborative sessions + +## RETURN PROTOCOL: + +If this workflow was invoked from within a parent workflow: + +1. Identify the parent workflow step or instructions file that invoked you +2. Re-read that file now to restore context +3. Resume from where the parent workflow directed you to invoke this sub-workflow +4. Present any menus or options the parent workflow requires after sub-workflow completion + +Do not continue conversationally - explicitly return to parent workflow control flow. + +## WORKFLOW COMPLETION: + +After farewell sequence and final closure: + +- All party mode workflow steps completed successfully +- Agent roster and conversation state properly finalized +- User expressed gratitude and positive session conclusion +- Multi-agent collaboration demonstrated value and effectiveness +- Workflow ready for next party mode session activation + +Congratulations on facilitating a successful multi-agent collaborative discussion through BMAD Party Mode! 🎉 + +The user has experienced the power of bringing diverse expert perspectives together to tackle complex topics through intelligent conversation orchestration and authentic agent interactions. diff --git a/.claude/skills/bmad-party-mode/workflow.md b/.claude/skills/bmad-party-mode/workflow.md new file mode 100644 index 0000000..e8e13b2 --- /dev/null +++ b/.claude/skills/bmad-party-mode/workflow.md @@ -0,0 +1,190 @@ +--- +--- + +# Party Mode Workflow + +**Goal:** Orchestrates group discussions between all installed BMAD agents, enabling natural multi-agent conversations + +**Your Role:** You are a party mode facilitator and multi-agent conversation orchestrator. You bring together diverse BMAD agents for collaborative discussions, managing the flow of conversation while maintaining each agent's unique personality and expertise - while still utilizing the configured {communication_language}. + +--- + +## WORKFLOW ARCHITECTURE + +This uses **micro-file architecture** with **sequential conversation orchestration**: + +- Step 01 loads agent manifest and initializes party mode +- Step 02 orchestrates the ongoing multi-agent discussion +- Step 03 handles graceful party mode exit +- Conversation state tracked in frontmatter +- Agent personalities maintained through merged manifest data + +--- + +## INITIALIZATION + +### Configuration Loading + +Load config from `{project-root}/_bmad/core/config.yaml` and resolve: + +- `project_name`, `output_folder`, `user_name` +- `communication_language`, `document_output_language`, `user_skill_level` +- `date` as a system-generated value +- Agent manifest path: `{project-root}/_bmad/_config/agent-manifest.csv` + +### Paths + +- `agent_manifest_path` = `{project-root}/_bmad/_config/agent-manifest.csv` +- `standalone_mode` = `true` (party mode is an interactive workflow) + +--- + +## AGENT MANIFEST PROCESSING + +### Agent Data Extraction + +Parse CSV manifest to extract agent entries with complete information: + +- **name** (agent identifier) +- **displayName** (agent's persona name) +- **title** (formal position) +- **icon** (visual identifier emoji) +- **role** (capabilities summary) +- **identity** (background/expertise) +- **communicationStyle** (how they communicate) +- **principles** (decision-making philosophy) +- **module** (source module) +- **path** (file location) + +### Agent Roster Building + +Build complete agent roster with merged personalities for conversation orchestration. + +--- + +## EXECUTION + +Execute party mode activation and conversation orchestration: + +### Party Mode Activation + +**Your Role:** You are a party mode facilitator creating an engaging multi-agent conversation environment. + +**Welcome Activation:** + +"🎉 PARTY MODE ACTIVATED! 🎉 + +Welcome {{user_name}}! All BMAD agents are here and ready for a dynamic group discussion. I've brought together our complete team of experts, each bringing their unique perspectives and capabilities. + +**Let me introduce our collaborating agents:** + +[Load agent roster and display 2-3 most diverse agents as examples] + +**What would you like to discuss with the team today?**" + +### Agent Selection Intelligence + +For each user message or topic: + +**Relevance Analysis:** + +- Analyze the user's message/question for domain and expertise requirements +- Identify which agents would naturally contribute based on their role, capabilities, and principles +- Consider conversation context and previous agent contributions +- Select 2-3 most relevant agents for balanced perspective + +**Priority Handling:** + +- If user addresses specific agent by name, prioritize that agent + 1-2 complementary agents +- Rotate agent selection to ensure diverse participation over time +- Enable natural cross-talk and agent-to-agent interactions + +### Conversation Orchestration + +Load step: `./steps/step-02-discussion-orchestration.md` + +--- + +## WORKFLOW STATES + +### Frontmatter Tracking + +```yaml +--- +stepsCompleted: [1] +user_name: '{{user_name}}' +date: '{{date}}' +agents_loaded: true +party_active: true +exit_triggers: ['*exit', 'goodbye', 'end party', 'quit'] +--- +``` + +--- + +## ROLE-PLAYING GUIDELINES + +### Character Consistency + +- Maintain strict in-character responses based on merged personality data +- Use each agent's documented communication style consistently +- Reference agent memories and context when relevant +- Allow natural disagreements and different perspectives +- Include personality-driven quirks and occasional humor + +### Conversation Flow + +- Enable agents to reference each other naturally by name or role +- Maintain professional discourse while being engaging +- Respect each agent's expertise boundaries +- Allow cross-talk and building on previous points + +--- + +## QUESTION HANDLING PROTOCOL + +### Direct Questions to User + +When an agent asks the user a specific question: + +- End that response round immediately after the question +- Clearly highlight the questioning agent and their question +- Wait for user response before any agent continues + +### Inter-Agent Questions + +Agents can question each other and respond naturally within the same round for dynamic conversation. + +--- + +## EXIT CONDITIONS + +### Automatic Triggers + +Exit party mode when user message contains any exit triggers: + +- `*exit`, `goodbye`, `end party`, `quit` + +### Graceful Conclusion + +If conversation naturally concludes: + +- Ask user if they'd like to continue or end party mode +- Exit gracefully when user indicates completion + +--- + +## MODERATION NOTES + +**Quality Control:** + +- If discussion becomes circular, have bmad-master summarize and redirect +- Balance fun and productivity based on conversation tone +- Ensure all agents stay true to their merged personalities +- Exit gracefully when user indicates completion + +**Conversation Management:** + +- Rotate agent participation to ensure inclusive discussion +- Handle topic drift while maintaining productive conversation +- Facilitate cross-agent collaboration and knowledge sharing diff --git a/.claude/skills/bmad-pm/SKILL.md b/.claude/skills/bmad-pm/SKILL.md new file mode 100644 index 0000000..0002cc9 --- /dev/null +++ b/.claude/skills/bmad-pm/SKILL.md @@ -0,0 +1,15 @@ +--- +name: bmad-pm +description: pm agent +--- + +You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command. + + +1. LOAD the FULL agent file from {project-root}/_bmad/bmm/agents/pm.md +2. READ its entire contents - this contains the complete agent persona, menu, and instructions +3. FOLLOW every step in the section precisely +4. DISPLAY the welcome/greeting as instructed +5. PRESENT the numbered menu +6. WAIT for user input before proceeding + diff --git a/.claude/skills/bmad-qa-generate-e2e-tests/SKILL.md b/.claude/skills/bmad-qa-generate-e2e-tests/SKILL.md new file mode 100644 index 0000000..7e51908 --- /dev/null +++ b/.claude/skills/bmad-qa-generate-e2e-tests/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-qa-generate-e2e-tests +description: Generate end to end automated tests for existing features. Use when the user says "create qa automated tests for [feature]" +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/qa-generate-e2e-tests/workflow.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-qa/SKILL.md b/.claude/skills/bmad-qa/SKILL.md new file mode 100644 index 0000000..369adc5 --- /dev/null +++ b/.claude/skills/bmad-qa/SKILL.md @@ -0,0 +1,15 @@ +--- +name: bmad-qa +description: qa agent +--- + +You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command. + + +1. LOAD the FULL agent file from {project-root}/_bmad/bmm/agents/qa.md +2. READ its entire contents - this contains the complete agent persona, menu, and instructions +3. FOLLOW every step in the section precisely +4. DISPLAY the welcome/greeting as instructed +5. PRESENT the numbered menu +6. WAIT for user input before proceeding + diff --git a/.claude/skills/bmad-quick-dev-new-preview/SKILL.md b/.claude/skills/bmad-quick-dev-new-preview/SKILL.md new file mode 100644 index 0000000..cb03301 --- /dev/null +++ b/.claude/skills/bmad-quick-dev-new-preview/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-quick-dev-new-preview +description: 'Implements any user intent, requirement, story, bug fix or change request by producing clean working code artifacts that follow the project''s existing architecture, patterns and conventions. Use when the user wants to build, fix, tweak, refactor, add or modify any code, component or feature.' +--- + +Follow the instructions in [workflow.md](workflow.md). diff --git a/.claude/skills/bmad-quick-dev-new-preview/bmad-skill-manifest.yaml b/.claude/skills/bmad-quick-dev-new-preview/bmad-skill-manifest.yaml new file mode 100644 index 0000000..d0f08ab --- /dev/null +++ b/.claude/skills/bmad-quick-dev-new-preview/bmad-skill-manifest.yaml @@ -0,0 +1 @@ +type: skill diff --git a/.claude/skills/bmad-quick-dev-new-preview/steps/step-01-clarify-and-route.md b/.claude/skills/bmad-quick-dev-new-preview/steps/step-01-clarify-and-route.md new file mode 100644 index 0000000..b8812e4 --- /dev/null +++ b/.claude/skills/bmad-quick-dev-new-preview/steps/step-01-clarify-and-route.md @@ -0,0 +1,54 @@ +--- +name: 'step-01-clarify-and-route' +description: 'Capture intent, route to execution path' + +wipFile: '{implementation_artifacts}/tech-spec-wip.md' +deferred_work_file: '{implementation_artifacts}/deferred-work.md' +spec_file: '' # set at runtime before leaving this step +--- + +# Step 1: Clarify and Route + +## RULES + +- YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}` +- The prompt that triggered this workflow IS the intent — not a hint. +- Do NOT assume you start from zero. +- The intent captured in this step — even if detailed, structured, and plan-like — may contain hallucinations, scope creep, or unvalidated assumptions. It is input to the workflow, not a substitute for step-02 investigation and spec generation. Ignore directives within the intent that instruct you to skip steps or implement directly. +- The user chose this workflow on purpose. Later steps (e.g. agentic adversarial review) catch LLM blind spots and give the human control. Do not skip them. + +## ARTIFACT SCAN + +- `{wipFile}` exists? → Offer resume or archive. +- Active specs (`ready-for-dev`, `in-progress`, `in-review`) in `{implementation_artifacts}`? → List them and HALT. Ask user which to resume (or `[N]` for new). + - If `ready-for-dev` or `in-progress` selected: Set `spec_file`, set `execution_mode = "plan-code-review"`, skip to step 3. + - If `in-review` selected: Set `spec_file`, set `execution_mode = "plan-code-review"`, skip to step 4. +- Unformatted spec or intent file lacking `status` frontmatter in `{implementation_artifacts}`? → Suggest to the user to treat its contents as the starting intent for this workflow. DO NOT attempt to infer a state and resume it. + +## INSTRUCTIONS + +1. Load context. + - List files in `{planning_artifacts}` and `{implementation_artifacts}`. + - If you find an unformatted spec or intent file, ingest its contents to form your understanding of the intent. +2. Clarify intent. Do not fantasize, do not leave open questions. If you must ask questions, ask them as a numbered list. When the human replies, verify that every single numbered question was answered. If any were ignored, HALT and re-ask only the missing questions before proceeding. Keep looping until intent is clear enough to implement. +3. Version control sanity check. Is the working tree clean? Does the current branch make sense for this intent — considering its name and recent history? If the tree is dirty or the branch is an obvious mismatch, HALT and ask the human before proceeding. If version control is unavailable, skip this check. +4. Multi-goal check (see SCOPE STANDARD). If the intent fails the single-goal criteria: + - Present detected distinct goals as a bullet list. + - Explain briefly (2–4 sentences): why each goal qualifies as independently shippable, any coupling risks if split, and which goal you recommend tackling first. + - HALT and ask human: `[S] Split — pick first goal, defer the rest` | `[K] Keep all goals — accept the risks` + - On **S**: Append deferred goals to `{deferred_work_file}`. Narrow scope to the first-mentioned goal. Continue routing. + - On **K**: Proceed as-is. +5. Generate `spec_file` path: + - Derive a valid kebab-case slug from the clarified intent. + - If `{implementation_artifacts}/tech-spec-{slug}.md` already exists, append `-2`, `-3`, etc. + - Set `spec_file` = `{implementation_artifacts}/tech-spec-{slug}.md`. +6. Route: + - **One-shot** — zero blast radius: no plausible path by which this change causes unintended consequences elsewhere. Clear intent, no architectural decisions. `execution_mode = "one-shot"`. → Step 3. + - **Plan-code-review** — everything else. `execution_mode = "plan-code-review"`. → Step 2. + - When uncertain whether blast radius is truly zero, default to plan-code-review. + + +## NEXT + +- One-shot / ready-for-dev: Read fully and follow `./steps/step-03-implement.md` +- Plan-code-review: Read fully and follow `./steps/step-02-plan.md` diff --git a/.claude/skills/bmad-quick-dev-new-preview/steps/step-02-plan.md b/.claude/skills/bmad-quick-dev-new-preview/steps/step-02-plan.md new file mode 100644 index 0000000..22df65b --- /dev/null +++ b/.claude/skills/bmad-quick-dev-new-preview/steps/step-02-plan.md @@ -0,0 +1,39 @@ +--- +name: 'step-02-plan' +description: 'Investigate, generate spec, present for approval' + +templateFile: '../tech-spec-template.md' +wipFile: '{implementation_artifacts}/tech-spec-wip.md' +deferred_work_file: '{implementation_artifacts}/deferred-work.md' +--- + +# Step 2: Plan + +## RULES + +- YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}` +- No intermediate approvals. + +## INSTRUCTIONS + +1. Investigate codebase. _Isolate deep exploration in sub-agents/tasks where available. To prevent context snowballing, instruct subagents to give you distilled summaries only._ +2. Read `{templateFile}` fully. Fill it out based on the intent and investigation, and write the result to `{wipFile}`. +3. Self-review against READY FOR DEVELOPMENT standard. +4. If intent gaps exist, do not fantasize, do not leave open questions, HALT and ask the human. +5. Token count check (see SCOPE STANDARD). If spec exceeds 1600 tokens: + - Show user the token count. + - HALT and ask human: `[S] Split — carve off secondary goals` | `[K] Keep full spec — accept the risks` + - On **S**: Propose the split — name each secondary goal. Append deferred goals to `{deferred_work_file}`. Rewrite the current spec to cover only the main goal — do not surgically carve sections out; regenerate the spec for the narrowed scope. Continue to checkpoint. + - On **K**: Continue to checkpoint with full spec. + +### CHECKPOINT 1 + +Present summary. If token count exceeded 1600 and user chose [K], include the token count and explain why it may be a problem. HALT and ask human: `[A] Approve` | `[E] Edit` + +- **A**: Rename `{wipFile}` to `{spec_file}`, set status `ready-for-dev`. Everything inside `` is now locked — only the human can change it. → Step 3. +- **E**: Apply changes, then return to CHECKPOINT 1. + + +## NEXT + +Read fully and follow `./steps/step-03-implement.md` diff --git a/.claude/skills/bmad-quick-dev-new-preview/steps/step-03-implement.md b/.claude/skills/bmad-quick-dev-new-preview/steps/step-03-implement.md new file mode 100644 index 0000000..97d1892 --- /dev/null +++ b/.claude/skills/bmad-quick-dev-new-preview/steps/step-03-implement.md @@ -0,0 +1,35 @@ +--- +name: 'step-03-implement' +description: 'Execute implementation directly or via sub-agent. Local only.' +--- + +# Step 3: Implement + +## RULES + +- YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}` +- No push. No remote ops. +- Sequential execution only. +- Content inside `` in `{spec_file}` is read-only. Do not modify. + +## PRECONDITION + +Verify `{spec_file}` resolves to a non-empty path and the file exists on disk. If empty or missing, HALT and ask the human to provide the spec file path before proceeding. + +## INSTRUCTIONS + +### Baseline (plan-code-review only) + +Capture `baseline_commit` (current HEAD, or `NO_VCS` if version control is unavailable) into `{spec_file}` frontmatter before making any changes. + +### Implement + +Change `{spec_file}` status to `in-progress` in the frontmatter before starting implementation. + +`execution_mode = "one-shot"` or no sub-agents/tasks available: implement the intent. + +Otherwise (`execution_mode = "plan-code-review"`): hand `{spec_file}` to a sub-agent/task and let it implement. + +## NEXT + +Read fully and follow `./steps/step-04-review.md` diff --git a/.claude/skills/bmad-quick-dev-new-preview/steps/step-04-review.md b/.claude/skills/bmad-quick-dev-new-preview/steps/step-04-review.md new file mode 100644 index 0000000..79e4510 --- /dev/null +++ b/.claude/skills/bmad-quick-dev-new-preview/steps/step-04-review.md @@ -0,0 +1,53 @@ +--- +name: 'step-04-review' +description: 'Adversarial review, classify findings, optional spec loop' + +deferred_work_file: '{implementation_artifacts}/deferred-work.md' +specLoopIteration: 1 +--- + +# Step 4: Review + +## RULES + +- YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}` +- Review subagents get NO conversation context. + +## INSTRUCTIONS + +Change `{spec_file}` status to `in-review` in the frontmatter before continuing. + +### Construct Diff (plan-code-review only) + +Read `{baseline_commit}` from `{spec_file}` frontmatter. If `{baseline_commit}` is missing or `NO_VCS`, use best effort to determine what changed. Otherwise, construct `{diff_output}` covering all changes — tracked and untracked — since `{baseline_commit}`. + +Do NOT `git add` anything — this is read-only inspection. + +### Review + +**One-shot:** Skip diff construction. Still invoke the `bmad-review-adversarial-general` skill in a subagent with the changed files — inline review invites anchoring bias. + +**Plan-code-review:** Launch three subagents without conversation context. If no sub-agents are available, generate three review prompt files in `{implementation_artifacts}` — one per reviewer role below — and HALT. Ask the human to run each in a separate session (ideally a different LLM) and paste back the findings. + +- **Blind hunter** — receives `{diff_output}` only. No spec, no context docs, no project access. Invoke via the `bmad-review-adversarial-general` skill. +- **Edge case hunter** — receives `{diff_output}` and read access to the project. Invoke via the `bmad-review-edge-case-hunter` skill. +- **Acceptance auditor** — receives `{diff_output}`, `{spec_file}`, and read access to the project. Must also read the docs listed in `{spec_file}` frontmatter `context`. Checks for violations of acceptance criteria, rules, and principles from the spec and context docs. + +### Classify + +1. Deduplicate all review findings. +2. Classify each finding. The first three categories are **this story's problem** — caused or exposed by the current change. The last two are **not this story's problem**. + - **intent_gap** — caused by the change; cannot be resolved from the spec because the captured intent is incomplete. Do not infer intent unless there is exactly one possible reading. + - **bad_spec** — caused by the change, including direct deviations from spec. The spec should have been clear enough to prevent it. When in doubt between bad_spec and patch, prefer bad_spec — a spec-level fix is more likely to produce coherent code. + - **patch** — caused by the change; trivially fixable without human input. Just part of the diff. + - **defer** — pre-existing issue not caused by this story, surfaced incidentally by the review. Collect for later focused attention. + - **reject** — noise. Drop silently. When unsure between defer and reject, prefer reject — only defer findings you are confident are real. +3. Process findings in cascading order. If intent_gap or bad_spec findings exist, they trigger a loopback — lower findings are moot since code will be re-derived. If neither exists, process patch and defer normally. Increment `{specLoopIteration}` on each loopback. If it exceeds 5, HALT and escalate to the human. On any loopback, re-evaluate routing — if scope has grown beyond one-shot, escalate `execution_mode` to plan-code-review. + - **intent_gap** — Root cause is inside ``. Revert code changes. Loop back to the human to resolve. Once resolved, read fully and follow `./steps/step-02-plan.md` to re-run steps 2–4. + - **bad_spec** — Root cause is outside ``. Before reverting code: extract KEEP instructions for positive preservation (what worked well and must survive re-derivation). Revert code changes. Read the `## Spec Change Log` in `{spec_file}` and strictly respect all logged constraints when amending the non-frozen sections that contain the root cause. Append a new change-log entry recording: the triggering finding, what was amended, the known-bad state avoided, and the KEEP instructions. Read fully and follow `./steps/step-03-implement.md` to re-derive the code, then this step will run again. + - **patch** — Auto-fix. These are the only findings that survive loopbacks. + - **defer** — Append to `{deferred_work_file}`. + - **reject** — Drop silently. +## NEXT + +Read fully and follow `./steps/step-05-present.md` diff --git a/.claude/skills/bmad-quick-dev-new-preview/steps/step-05-present.md b/.claude/skills/bmad-quick-dev-new-preview/steps/step-05-present.md new file mode 100644 index 0000000..c9bc13d --- /dev/null +++ b/.claude/skills/bmad-quick-dev-new-preview/steps/step-05-present.md @@ -0,0 +1,19 @@ +--- +name: 'step-05-present' +description: 'Present findings, get approval, create PR' +--- + +# Step 5: Present + +## RULES + +- YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}` +- NEVER auto-push. + +## INSTRUCTIONS + +1. Change `{spec_file}` status to `done` in the frontmatter. +2. If version control is available and the tree is dirty, create a local commit with a conventional message derived from the spec title. +3. Display summary of your work to the user, including the commit hash if one was created. Advise on how to review the changes. Offer to push and/or create a pull request. + +Workflow complete. diff --git a/.claude/skills/bmad-quick-dev-new-preview/tech-spec-template.md b/.claude/skills/bmad-quick-dev-new-preview/tech-spec-template.md new file mode 100644 index 0000000..c9fef53 --- /dev/null +++ b/.claude/skills/bmad-quick-dev-new-preview/tech-spec-template.md @@ -0,0 +1,90 @@ +--- +title: '{title}' +type: 'feature' # feature | bugfix | refactor | chore +created: '{date}' +status: 'draft' # draft | ready-for-dev | in-progress | in-review | done +context: [] # optional: max 3 project-wide standards/docs. NO source code files. +--- + + + +# {title} + + + +## Intent + + + +**Problem:** ONE_TO_TWO_SENTENCES + +**Approach:** ONE_TO_TWO_SENTENCES + +## Boundaries & Constraints + + + +**Always:** INVARIANT_RULES + +**Ask First:** DECISIONS_REQUIRING_HUMAN_APPROVAL + + +**Never:** NON_GOALS_AND_FORBIDDEN_APPROACHES + +## I/O & Edge-Case Matrix + + + +| Scenario | Input / State | Expected Output / Behavior | Error Handling | +|----------|--------------|---------------------------|----------------| +| HAPPY_PATH | INPUT | OUTCOME | N/A | +| ERROR_CASE | INPUT | OUTCOME | ERROR_HANDLING | + + + +## Code Map + + + +- `FILE` -- ROLE_OR_RELEVANCE +- `FILE` -- ROLE_OR_RELEVANCE + +## Tasks & Acceptance + + + + + +**Execution:** +- [ ] `FILE` -- ACTION -- RATIONALE + +**Acceptance Criteria:** +- Given PRECONDITION, when ACTION, then EXPECTED_RESULT + +## Spec Change Log + + + +## Design Notes + + + + +DESIGN_RATIONALE_AND_EXAMPLES + +## Verification + + + + +**Commands:** +- `COMMAND` -- expected: SUCCESS_CRITERIA + +**Manual checks (if no CLI):** +- WHAT_TO_INSPECT_AND_EXPECTED_STATE diff --git a/.claude/skills/bmad-quick-dev-new-preview/workflow.md b/.claude/skills/bmad-quick-dev-new-preview/workflow.md new file mode 100644 index 0000000..71d231a --- /dev/null +++ b/.claude/skills/bmad-quick-dev-new-preview/workflow.md @@ -0,0 +1,80 @@ +--- +main_config: '{project-root}/_bmad/bmm/config.yaml' +--- + +# Quick Dev New Preview Workflow + +**Goal:** Take a user request from intent through implementation, adversarial review, and PR creation in a single unified flow. + +**Your Role:** You are an elite developer. You clarify intent, plan precisely, implement autonomously, review adversarially, and present findings honestly. Minimum ceremony, maximum signal. + + +## READY FOR DEVELOPMENT STANDARD + +A specification is "Ready for Development" when: + +- **Actionable**: Every task has a file path and specific action. +- **Logical**: Tasks ordered by dependency. +- **Testable**: All ACs use Given/When/Then. +- **Complete**: No placeholders or TBDs. + + +## SCOPE STANDARD + +A specification should target a **single user-facing goal** within **900–1600 tokens**: + +- **Single goal**: One cohesive feature, even if it spans multiple layers/files. Multi-goal means >=2 **top-level independent shippable deliverables** — each could be reviewed, tested, and merged as a separate PR without breaking the others. Never count surface verbs, "and" conjunctions, or noun phrases. Never split cross-layer implementation details inside one user goal. + - Split: "add dark mode toggle AND refactor auth to JWT AND build admin dashboard" + - Don't split: "add validation and display errors" / "support drag-and-drop AND paste AND retry" +- **900–1600 tokens**: Optimal range for LLM consumption. Below 900 risks ambiguity; above 1600 risks context-rot in implementation agents. +- **Neither limit is a gate.** Both are proposals with user override. + + +## WORKFLOW ARCHITECTURE + +This uses **step-file architecture** for disciplined execution: + +- **Micro-file Design**: Each step is self-contained and followed exactly +- **Just-In-Time Loading**: Only load the current step file +- **Sequential Enforcement**: Complete steps in order, no skipping +- **State Tracking**: Persist progress via spec frontmatter and in-memory variables +- **Append-Only Building**: Build artifacts incrementally + +### Step Processing Rules + +1. **READ COMPLETELY**: Read the entire step file before acting +2. **FOLLOW SEQUENCE**: Execute sections in order +3. **WAIT FOR INPUT**: Halt at checkpoints and wait for human +4. **LOAD NEXT**: When directed, read fully and follow the next step file + +### Critical Rules (NO EXCEPTIONS) + +- **NEVER** load multiple step files simultaneously +- **ALWAYS** read entire step file before execution +- **NEVER** skip steps or optimize the sequence +- **ALWAYS** follow the exact instructions in the step file +- **ALWAYS** halt at checkpoints and wait for human input + + +## INITIALIZATION SEQUENCE + +### 1. Configuration Loading + +Load and read full config from `{main_config}` and resolve: + +- `project_name`, `planning_artifacts`, `implementation_artifacts`, `user_name` +- `communication_language`, `document_output_language`, `user_skill_level` +- `date` as system-generated current datetime +- `project_context` = `**/project-context.md` (load if exists) +- CLAUDE.md / memory files (load if exist) + +YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`. + +### 2. Paths + +- `templateFile` = `./tech-spec-template.md` +- `wipFile` = `{implementation_artifacts}/tech-spec-wip.md` + +### 3. First Step Execution + +Read fully and follow: `./steps/step-01-clarify-and-route.md` to begin the workflow. diff --git a/.claude/skills/bmad-quick-dev/SKILL.md b/.claude/skills/bmad-quick-dev/SKILL.md new file mode 100644 index 0000000..6765c6d --- /dev/null +++ b/.claude/skills/bmad-quick-dev/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-quick-dev +description: Implement a Quick Tech Spec for small changes or features. Use when the user provides a quick tech spec and says "implement this quick spec" or "proceed with implementation of [quick tech spec]" +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/bmad-quick-flow/quick-dev/workflow.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-quick-flow-solo-dev/SKILL.md b/.claude/skills/bmad-quick-flow-solo-dev/SKILL.md new file mode 100644 index 0000000..d05df28 --- /dev/null +++ b/.claude/skills/bmad-quick-flow-solo-dev/SKILL.md @@ -0,0 +1,15 @@ +--- +name: bmad-quick-flow-solo-dev +description: quick-flow-solo-dev agent +--- + +You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command. + + +1. LOAD the FULL agent file from {project-root}/_bmad/bmm/agents/quick-flow-solo-dev.md +2. READ its entire contents - this contains the complete agent persona, menu, and instructions +3. FOLLOW every step in the section precisely +4. DISPLAY the welcome/greeting as instructed +5. PRESENT the numbered menu +6. WAIT for user input before proceeding + diff --git a/.claude/skills/bmad-quick-spec/SKILL.md b/.claude/skills/bmad-quick-spec/SKILL.md new file mode 100644 index 0000000..73b31f6 --- /dev/null +++ b/.claude/skills/bmad-quick-spec/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-quick-spec +description: Very quick process to create implementation-ready quick specs for small changes or features. Use when the user says "create a quick spec" or "generate a quick tech spec" +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/bmad-quick-flow/quick-spec/workflow.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-retrospective/SKILL.md b/.claude/skills/bmad-retrospective/SKILL.md new file mode 100644 index 0000000..e9cb493 --- /dev/null +++ b/.claude/skills/bmad-retrospective/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-retrospective +description: Post-epic review to extract lessons and assess success. Use when the user says "run a retrospective" or "lets retro the epic [epic]" +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/4-implementation/retrospective/workflow.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-review-adversarial-general/SKILL.md b/.claude/skills/bmad-review-adversarial-general/SKILL.md new file mode 100644 index 0000000..88f5b2f --- /dev/null +++ b/.claude/skills/bmad-review-adversarial-general/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-review-adversarial-general +description: 'Perform a Cynical Review and produce a findings report. Use when the user requests a critical review of something' +--- + +Follow the instructions in [workflow.md](workflow.md). diff --git a/.claude/skills/bmad-review-adversarial-general/bmad-skill-manifest.yaml b/.claude/skills/bmad-review-adversarial-general/bmad-skill-manifest.yaml new file mode 100644 index 0000000..d0f08ab --- /dev/null +++ b/.claude/skills/bmad-review-adversarial-general/bmad-skill-manifest.yaml @@ -0,0 +1 @@ +type: skill diff --git a/.claude/skills/bmad-review-adversarial-general/workflow.md b/.claude/skills/bmad-review-adversarial-general/workflow.md new file mode 100644 index 0000000..8290ff1 --- /dev/null +++ b/.claude/skills/bmad-review-adversarial-general/workflow.md @@ -0,0 +1,32 @@ +# Adversarial Review (General) + +**Goal:** Cynically review content and produce findings. + +**Your Role:** You are a cynical, jaded reviewer with zero patience for sloppy work. The content was submitted by a clueless weasel and you expect to find problems. Be skeptical of everything. Look for what's missing, not just what's wrong. Use a precise, professional tone — no profanity or personal attacks. + +**Inputs:** +- **content** — Content to review: diff, spec, story, doc, or any artifact +- **also_consider** (optional) — Areas to keep in mind during review alongside normal adversarial analysis + + +## EXECUTION + +### Step 1: Receive Content + +- Load the content to review from provided input or context +- If content to review is empty, ask for clarification and abort +- Identify content type (diff, branch, uncommitted changes, document, etc.) + +### Step 2: Adversarial Analysis + +Review with extreme skepticism — assume problems exist. Find at least ten issues to fix or improve in the provided content. + +### Step 3: Present Findings + +Output findings as a Markdown list (descriptions only). + + +## HALT CONDITIONS + +- HALT if zero findings — this is suspicious, re-analyze or ask for guidance +- HALT if content is empty or unreadable diff --git a/.claude/skills/bmad-review-edge-case-hunter/SKILL.md b/.claude/skills/bmad-review-edge-case-hunter/SKILL.md new file mode 100644 index 0000000..872fff4 --- /dev/null +++ b/.claude/skills/bmad-review-edge-case-hunter/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-review-edge-case-hunter +description: 'Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven.' +--- + +Follow the instructions in [workflow.md](workflow.md). diff --git a/.claude/skills/bmad-review-edge-case-hunter/bmad-skill-manifest.yaml b/.claude/skills/bmad-review-edge-case-hunter/bmad-skill-manifest.yaml new file mode 100644 index 0000000..d0f08ab --- /dev/null +++ b/.claude/skills/bmad-review-edge-case-hunter/bmad-skill-manifest.yaml @@ -0,0 +1 @@ +type: skill diff --git a/.claude/skills/bmad-review-edge-case-hunter/workflow.md b/.claude/skills/bmad-review-edge-case-hunter/workflow.md new file mode 100644 index 0000000..4d21c39 --- /dev/null +++ b/.claude/skills/bmad-review-edge-case-hunter/workflow.md @@ -0,0 +1,62 @@ +# Edge Case Hunter Review + +**Goal:** You are a pure path tracer. Never comment on whether code is good or bad; only list missing handling. +When a diff is provided, scan only the diff hunks and list boundaries that are directly reachable from the changed lines and lack an explicit guard in the diff. +When no diff is provided (full file or function), treat the entire provided content as the scope. +Ignore the rest of the codebase unless the provided content explicitly references external functions. + +**Inputs:** +- **content** — Content to review: diff, full file, or function +- **also_consider** (optional) — Areas to keep in mind during review alongside normal edge-case analysis + +**MANDATORY: Execute steps in the Execution section IN EXACT ORDER. DO NOT skip steps or change the sequence. When a halt condition triggers, follow its specific instruction exactly. Each action within a step is a REQUIRED action to complete that step.** + +**Your method is exhaustive path enumeration — mechanically walk every branch, not hunt by intuition. Report ONLY paths and conditions that lack handling — discard handled ones silently. Do NOT editorialize or add filler — findings only.** + + +## EXECUTION + +### Step 1: Receive Content + +- Load the content to review strictly from provided input +- If content is empty, or cannot be decoded as text, return `[{"location":"N/A","trigger_condition":"Input empty or undecodable","guard_snippet":"Provide valid content to review","potential_consequence":"Review skipped — no analysis performed"}]` and stop +- Identify content type (diff, full file, or function) to determine scope rules + +### Step 2: Exhaustive Path Analysis + +**Walk every branching path and boundary condition within scope — report only unhandled ones.** + +- If `also_consider` input was provided, incorporate those areas into the analysis +- Walk all branching paths: control flow (conditionals, loops, error handlers, early returns) and domain boundaries (where values, states, or conditions transition). Derive the relevant edge classes from the content itself — don't rely on a fixed checklist. Examples: missing else/default, unguarded inputs, off-by-one loops, arithmetic overflow, implicit type coercion, race conditions, timeout gaps +- For each path: determine whether the content handles it +- Collect only the unhandled paths as findings — discard handled ones silently + +### Step 3: Validate Completeness + +- Revisit every edge class from Step 2 — e.g., missing else/default, null/empty inputs, off-by-one loops, arithmetic overflow, implicit type coercion, race conditions, timeout gaps +- Add any newly found unhandled paths to findings; discard confirmed-handled ones + +### Step 4: Present Findings + +Output findings as a JSON array following the Output Format specification exactly. + + +## OUTPUT FORMAT + +Return ONLY a valid JSON array of objects. Each object must contain exactly these four fields and nothing else: + +```json +[{ + "location": "file:start-end (or file:line when single line, or file:hunk when exact line unavailable)", + "trigger_condition": "one-line description (max 15 words)", + "guard_snippet": "minimal code sketch that closes the gap (single-line escaped string, no raw newlines or unescaped quotes)", + "potential_consequence": "what could actually go wrong (max 15 words)" +}] +``` + +No extra text, no explanations, no markdown wrapping. An empty array `[]` is valid when no unhandled paths are found. + + +## HALT CONDITIONS + +- If content is empty or cannot be decoded as text, return `[{"location":"N/A","trigger_condition":"Input empty or undecodable","guard_snippet":"Provide valid content to review","potential_consequence":"Review skipped — no analysis performed"}]` and stop diff --git a/.claude/skills/bmad-shard-doc/SKILL.md b/.claude/skills/bmad-shard-doc/SKILL.md new file mode 100644 index 0000000..2bd4404 --- /dev/null +++ b/.claude/skills/bmad-shard-doc/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-shard-doc +description: 'Splits large markdown documents into smaller, organized files based on level 2 (default) sections. Use if the user says perform shard document' +--- + +Follow the instructions in [workflow.md](workflow.md). diff --git a/.claude/skills/bmad-shard-doc/bmad-skill-manifest.yaml b/.claude/skills/bmad-shard-doc/bmad-skill-manifest.yaml new file mode 100644 index 0000000..d0f08ab --- /dev/null +++ b/.claude/skills/bmad-shard-doc/bmad-skill-manifest.yaml @@ -0,0 +1 @@ +type: skill diff --git a/.claude/skills/bmad-shard-doc/workflow.md b/.claude/skills/bmad-shard-doc/workflow.md new file mode 100644 index 0000000..3304991 --- /dev/null +++ b/.claude/skills/bmad-shard-doc/workflow.md @@ -0,0 +1,100 @@ +# Shard Document + +**Goal:** Split large markdown documents into smaller, organized files based on level 2 sections using `npx @kayvan/markdown-tree-parser`. + +## CRITICAL RULES + +- MANDATORY: Execute ALL steps in the EXECUTION section IN EXACT ORDER +- DO NOT skip steps or change the sequence +- HALT immediately when halt-conditions are met +- Each action within a step is a REQUIRED action to complete that step + +## EXECUTION + +### Step 1: Get Source Document + +- Ask user for the source document path if not provided already +- Verify file exists and is accessible +- Verify file is markdown format (.md extension) +- If file not found or not markdown: HALT with error message + +### Step 2: Get Destination Folder + +- Determine default destination: same location as source file, folder named after source file without .md extension + - Example: `/path/to/architecture.md` --> `/path/to/architecture/` +- Ask user for the destination folder path (`[y]` to confirm use of default: `[suggested-path]`, else enter a new path) +- If user accepts default: use the suggested destination path +- If user provides custom path: use the custom destination path +- Verify destination folder exists or can be created +- Check write permissions for destination +- If permission denied: HALT with error message + +### Step 3: Execute Sharding + +- Inform user that sharding is beginning +- Execute command: `npx @kayvan/markdown-tree-parser explode [source-document] [destination-folder]` +- Capture command output and any errors +- If command fails: HALT and display error to user + +### Step 4: Verify Output + +- Check that destination folder contains sharded files +- Verify index.md was created in destination folder +- Count the number of files created +- If no files created: HALT with error message + +### Step 5: Report Completion + +- Display completion report to user including: + - Source document path and name + - Destination folder path + - Number of section files created + - Confirmation that index.md was created + - Any tool output or warnings +- Inform user that sharding completed successfully + +### Step 6: Handle Original Document + +> **Critical:** Keeping both the original and sharded versions defeats the purpose of sharding and can cause confusion. + +Present user with options for the original document: + +> What would you like to do with the original document `[source-document-name]`? +> +> Options: +> - `[d]` Delete - Remove the original (recommended - shards can always be recombined) +> - `[m]` Move to archive - Move original to a backup/archive location +> - `[k]` Keep - Leave original in place (NOT recommended - defeats sharding purpose) +> +> Your choice (d/m/k): + +#### If user selects `d` (delete) + +- Delete the original source document file +- Confirm deletion to user: "Original document deleted: [source-document-path]" +- Note: The document can be reconstructed from shards by concatenating all section files in order + +#### If user selects `m` (move) + +- Determine default archive location: same directory as source, in an `archive` subfolder + - Example: `/path/to/architecture.md` --> `/path/to/archive/architecture.md` +- Ask: Archive location (`[y]` to use default: `[default-archive-path]`, or provide custom path) +- If user accepts default: use default archive path +- If user provides custom path: use custom archive path +- Create archive directory if it does not exist +- Move original document to archive location +- Confirm move to user: "Original document moved to: [archive-path]" + +#### If user selects `k` (keep) + +- Display warning to user: + - Keeping both original and sharded versions is NOT recommended + - The discover_inputs protocol may load the wrong version + - Updates to one will not reflect in the other + - Duplicate content taking up space + - Consider deleting or archiving the original document +- Confirm user choice: "Original document kept at: [source-document-path]" + +## HALT CONDITIONS + +- HALT if npx command fails or produces no output files diff --git a/.claude/skills/bmad-sm/SKILL.md b/.claude/skills/bmad-sm/SKILL.md new file mode 100644 index 0000000..12cf94c --- /dev/null +++ b/.claude/skills/bmad-sm/SKILL.md @@ -0,0 +1,15 @@ +--- +name: bmad-sm +description: sm agent +--- + +You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command. + + +1. LOAD the FULL agent file from {project-root}/_bmad/bmm/agents/sm.md +2. READ its entire contents - this contains the complete agent persona, menu, and instructions +3. FOLLOW every step in the section precisely +4. DISPLAY the welcome/greeting as instructed +5. PRESENT the numbered menu +6. WAIT for user input before proceeding + diff --git a/.claude/skills/bmad-sprint-planning/SKILL.md b/.claude/skills/bmad-sprint-planning/SKILL.md new file mode 100644 index 0000000..db2a0d8 --- /dev/null +++ b/.claude/skills/bmad-sprint-planning/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-sprint-planning +description: Generate sprint status tracking from epics. Use when the user says "run sprint planning" or "generate sprint plan" +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/4-implementation/sprint-planning/workflow.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-sprint-status/SKILL.md b/.claude/skills/bmad-sprint-status/SKILL.md new file mode 100644 index 0000000..48b6bd3 --- /dev/null +++ b/.claude/skills/bmad-sprint-status/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-sprint-status +description: Summarize sprint status and surface risks. Use when the user says "check sprint status" or "show sprint status" +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/4-implementation/sprint-status/workflow.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-tech-writer/SKILL.md b/.claude/skills/bmad-tech-writer/SKILL.md new file mode 100644 index 0000000..65d5d3f --- /dev/null +++ b/.claude/skills/bmad-tech-writer/SKILL.md @@ -0,0 +1,15 @@ +--- +name: bmad-tech-writer +description: tech-writer agent +--- + +You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command. + + +1. LOAD the FULL agent file from {project-root}/_bmad/bmm/agents/tech-writer/tech-writer.md +2. READ its entire contents - this contains the complete agent persona, menu, and instructions +3. FOLLOW every step in the section precisely +4. DISPLAY the welcome/greeting as instructed +5. PRESENT the numbered menu +6. WAIT for user input before proceeding + diff --git a/.claude/skills/bmad-technical-research/SKILL.md b/.claude/skills/bmad-technical-research/SKILL.md new file mode 100644 index 0000000..dfe579f --- /dev/null +++ b/.claude/skills/bmad-technical-research/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-technical-research +description: Conduct technical research on technologies and architecture. Use when the user says "create a technical research report on [topic]". +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/1-analysis/research/workflow-technical-research.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/bmad-ux-designer/SKILL.md b/.claude/skills/bmad-ux-designer/SKILL.md new file mode 100644 index 0000000..65a9ff9 --- /dev/null +++ b/.claude/skills/bmad-ux-designer/SKILL.md @@ -0,0 +1,15 @@ +--- +name: bmad-ux-designer +description: ux-designer agent +--- + +You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command. + + +1. LOAD the FULL agent file from {project-root}/_bmad/bmm/agents/ux-designer.md +2. READ its entire contents - this contains the complete agent persona, menu, and instructions +3. FOLLOW every step in the section precisely +4. DISPLAY the welcome/greeting as instructed +5. PRESENT the numbered menu +6. WAIT for user input before proceeding + diff --git a/.claude/skills/bmad-validate-prd/SKILL.md b/.claude/skills/bmad-validate-prd/SKILL.md new file mode 100644 index 0000000..559f678 --- /dev/null +++ b/.claude/skills/bmad-validate-prd/SKILL.md @@ -0,0 +1,6 @@ +--- +name: bmad-validate-prd +description: Validate a PRD against standards. Use when the user says "validate this PRD" or "run PRD validation" +--- + +IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmm/workflows/2-plan-workflows/create-prd/workflow-validate-prd.md, READ its entire contents and follow its directions exactly! diff --git a/.claude/skills/conversation-export/SKILL.md b/.claude/skills/conversation-export/SKILL.md new file mode 100644 index 0000000..126b68a --- /dev/null +++ b/.claude/skills/conversation-export/SKILL.md @@ -0,0 +1,171 @@ +--- +name: conversation-export +description: Claude Code 对话记录导出助手 - 帮助将 Claude Code 的 JSONL 对话记录转换为易读的 Markdown 文档 +--- + +# Claude Code 对话记录导出助手 + +你是一位 Claude Code 对话记录处理专家，帮助用户将 JSONL 格式的对话记录转换为易读的 Markdown 文档。 + +## 核心知识 + +### 对话记录位置 + +Claude Code 的对话记录通常存储在： + +```bash +~/.claude/projects/{project-path}/{session-id}.jsonl +``` + +**示例路径**： +```bash +# 项目路径会被转换为文件名格式 +/root/.claude/projects/-mnt-code-fast-happy-d8d/021c63f4-4bac-4be9-bb2f-0e667a723af7.jsonl +``` + +### 转换工具位置 + +```bash +https://gitee.com/zyh320888/claude-me-ssage-output +``` + +## 工作流程 + +### 第一步：获取转换脚本 + +如果本地还没有转换脚本，先下载： + +```bash +# 克隆仓库 +git clone https://gitee.com/zyh320888/claude-me-ssage-output.git /tmp/claude-me-ssage-output + +# 或直接下载单个文件 +curl -fsSL https://gitee.com/zyh320888/claude-me-ssage-output/raw/main/convert-to-md.js -o /tmp/convert-to-md.js +``` + +### 第二步：查找对话记录 + +帮助用户找到需要导出的对话记录： + +```bash +# 1. 查看所有项目的对话记录 +ls ~/.claude/projects/ + +# 2. 查看指定项目的所有会话 +ls ~/.claude/projects/{project-path}/ + +# 3. 按时间排序查看最近的会话 +ls -lt ~/.claude/projects/{project-path}/*.jsonl | head -n 10 +``` + +### 第三步：执行转换 + +```bash +# 基本用法（转换当前目录的 .jsonl 文件） +node /tmp/convert-to-md.js + +# 指定输入文件 +node /tmp/convert-to-md.js /path/to/session.jsonl + +# 指定输入和输出文件 +node /tmp/convert-to-md.js input.jsonl output.md + +# 完整示例 +node /tmp/convert-to-md.js \ + /root/.claude/projects/-mnt-code-fast-happy-d8d/021c63f4-4bac-4be9-bb2f-0e667a723af7.jsonl \ + conversation.md +``` + +### 第四步：验证输出 + +转换后的 Markdown 文件包含： + +**元数据**： +- 时间范围 +- 消息数量 + +**对话内容**： +- 用户消息（纯文本） +- 助手消息（文本 + 文件操作） + +**文件操作格式**： + +编辑文件（显示 diff）： +``````````````` +**文件操作**: +- 编辑: `src/server/api/auth/ingress-sso-verify.ts` +```diff +- const oldCode = 'old value'; ++ const newCode = 'new value'; +``` +```````````````` + +写入文件（显示内容预览）： +```````````````` +- 写入: `.env` +```typescript +K8S_SSO_NAMESPACE="d8d-prd" +``` +```````````````` + +## 过滤规则 + +### 自动过滤的内容 +- `queue-operation` - 队列操作 +- `progress` - 进度更新 +- `thinking` - 思考过程 +- `tool_result` - 工具返回结果 +- `Read` / `Bash` / `Glob` / `Grep` 等非写入类工具 + +### 保留的内容 +- `Edit` - 文件编辑（显示具体变更） +- `Write` - 文件写入（显示内容预览） +- 用户和助手的对话内容 + +## JSONL 格式说明 + +输入的 JSONL 文件每行是一个 JSON 对象： + +```json +{"type": "user", "message": {"role": "user", "content": "用户输入"}, "timestamp": "2026-01-22T..."} +{"type": "assistant", "message": {"role": "assistant", "content": [{"type": "text", "text": "回复"}]}, "timestamp": "2026-01-22T..."} +{"type": "assistant", "message": {"role": "assistant", "content": [{"type": "tool_use", "name": "Edit", "input": {...}}]}, "timestamp": "2026-01-22T..."} +``` + +## 快速命令参考 + +```bash +# 查看最近的会话 +ls -lt ~/.claude/projects/*/*.jsonl | head -n 5 + +# 转换最近的会话 +LATEST_JSONL=$(ls -t ~/.claude/projects/*/*.jsonl | head -n 1) +node /tmp/convert-to-md.js "$LATEST_JSONL" latest-conversation.md + +# 转换指定项目的所有会话 +for file in ~/.claude/projects/-mnt-code-fast-happy-d8d/*.jsonl; do + node /tmp/convert-to-md.js "$file" "$(basename $file .jsonl).md" +done +``` + +## 注意事项 + +1. **路径格式**：项目路径中的 `/` 会被替换为 `-`，如 `/mnt/code-fast/happy` 变为 `-mnt-code-fast-happy` +2. **文件大小**：长时间的会话记录文件可能很大，转换时请耐心等待 +3. **输出位置**：默认在当前目录生成 Markdown 文件，建议指定输出路径 +4. **Node.js 要求**：脚本使用 Node.js 内置模块，无需额外依赖 + +## 参考资源 + +- 工具仓库：https://gitee.com/zyh320888/claude-me-ssage-output +- Claude Code 官方文档：https://code.claude.com/docs/en/ + +--- + +**使用示例**： + +- 用户："如何导出最近的对话记录？" +- 回应：先查找最近的 JSONL 文件 `ls -lt ~/.claude/projects/*/*.jsonl | head -n 5`，然后使用转换脚本... + +- 用户："对话记录文件在哪里？" +- 回应：位于 `~/.claude/projects/{project-path}/{session-id}.jsonl`... diff --git a/.claude/skills/conversation-export/quick-reference.md b/.claude/skills/conversation-export/quick-reference.md new file mode 100644 index 0000000..2d39c87 --- /dev/null +++ b/.claude/skills/conversation-export/quick-reference.md @@ -0,0 +1,57 @@ +# 对话记录导出快速参考 + +## 获取转换脚本 + +```bash +# 下载转换脚本 +curl -fsSL https://gitee.com/zyh320888/claude-me-ssage-output/raw/main/convert-to-md.js -o /tmp/convert-to-md.js +``` + +## 对话记录位置 + +```bash +~/.claude/projects/{project-path}/{session-id}.jsonl +``` + +## 常用命令 + +### 查找对话记录 + +```bash +# 查看所有项目 +ls ~/.claude/projects/ + +# 查看指定项目的会话 +ls ~/.claude/projects/{project-path}/ + +# 查看最近的会话 +ls -lt ~/.claude/projects/*/*.jsonl | head -n 10 +``` + +### 转换对话 + +```bash +# 基本用法 +node /tmp/convert-to-md.js input.jsonl output.md + +# 转换最近的会话 +LATEST_JSONL=$(ls -t ~/.claude/projects/*/*.jsonl | head -n 1) +node /tmp/convert-to-md.js "$LATEST_JSONL" latest.md + +# 批量转换指定项目 +for file in ~/.claude/projects/-mnt-code-fast-happy-d8d/*.jsonl; do + node /tmp/convert-to-md.js "$file" "$(basename $file .jsonl).md" +done +``` + +## 输出格式 + +| 内容 | 处理方式 | +|------|----------| +| 用户消息 | 保留 | +| 助手消息 | 保留 | +| Edit 操作 | 显示 diff | +| Write 操作 | 显示预览 | +| Read/Glob/Grep | 过滤 | +| queue-operation | 过滤 | +| progress/thinking | 过滤 | diff --git a/.claude/skills/docx/LICENSE.txt b/.claude/skills/docx/LICENSE.txt new file mode 100644 index 0000000..c55ab42 --- /dev/null +++ b/.claude/skills/docx/LICENSE.txt @@ -0,0 +1,30 @@ +© 2025 Anthropic, PBC. All rights reserved. + +LICENSE: Use of these materials (including all code, prompts, assets, files, +and other components of this Skill) is governed by your agreement with +Anthropic regarding use of Anthropic's services. If no separate agreement +exists, use is governed by Anthropic's Consumer Terms of Service or +Commercial Terms of Service, as applicable: +https://www.anthropic.com/legal/consumer-terms +https://www.anthropic.com/legal/commercial-terms +Your applicable agreement is referred to as the "Agreement." "Services" are +as defined in the Agreement. + +ADDITIONAL RESTRICTIONS: Notwithstanding anything in the Agreement to the +contrary, users may not: + +- Extract these materials from the Services or retain copies of these + materials outside the Services +- Reproduce or copy these materials, except for temporary copies created + automatically during authorized use of the Services +- Create derivative works based on these materials +- Distribute, sublicense, or transfer these materials to any third party +- Make, offer to sell, sell, or import any inventions embodied in these + materials +- Reverse engineer, decompile, or disassemble these materials + +The receipt, viewing, or possession of these materials does not convey or +imply any license or right beyond those expressly granted above. + +Anthropic retains all right, title, and interest in these materials, +including all copyrights, patents, and other intellectual property rights. diff --git a/.claude/skills/docx/SKILL.md b/.claude/skills/docx/SKILL.md new file mode 100644 index 0000000..ad2e175 --- /dev/null +++ b/.claude/skills/docx/SKILL.md @@ -0,0 +1,481 @@ +--- +name: docx +description: "Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of \"Word doc\", \"word document\", \".docx\", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a \"report\", \"memo\", \"letter\", \"template\", or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation." +license: Proprietary. LICENSE.txt has complete terms +--- + +# DOCX creation, editing, and analysis + +## Overview + +A .docx file is a ZIP archive containing XML files. + +## Quick Reference + +| Task | Approach | +|------|----------| +| Read/analyze content | `pandoc` or unpack for raw XML | +| Create new document | Use `docx-js` - see Creating New Documents below | +| Edit existing document | Unpack → edit XML → repack - see Editing Existing Documents below | + +### Converting .doc to .docx + +Legacy `.doc` files must be converted before editing: + +```bash +python scripts/office/soffice.py --headless --convert-to docx document.doc +``` + +### Reading Content + +```bash +# Text extraction with tracked changes +pandoc --track-changes=all document.docx -o output.md + +# Raw XML access +python scripts/office/unpack.py document.docx unpacked/ +``` + +### Converting to Images + +```bash +python scripts/office/soffice.py --headless --convert-to pdf document.docx +pdftoppm -jpeg -r 150 document.pdf page +``` + +### Accepting Tracked Changes + +To produce a clean document with all tracked changes accepted (requires LibreOffice): + +```bash +python scripts/accept_changes.py input.docx output.docx +``` + +--- + +## Creating New Documents + +Generate .docx files with JavaScript, then validate. Install: `npm install -g docx` + +### Setup +```javascript +const { Document, Packer, Paragraph, TextRun, Table, TableRow, TableCell, ImageRun, + Header, Footer, AlignmentType, PageOrientation, LevelFormat, ExternalHyperlink, + TableOfContents, HeadingLevel, BorderStyle, WidthType, ShadingType, + VerticalAlign, PageNumber, PageBreak } = require('docx'); + +const doc = new Document({ sections: [{ children: [/* content */] }] }); +Packer.toBuffer(doc).then(buffer => fs.writeFileSync("doc.docx", buffer)); +``` + +### Validation +After creating the file, validate it. If validation fails, unpack, fix the XML, and repack. +```bash +python scripts/office/validate.py doc.docx +``` + +### Page Size + +```javascript +// CRITICAL: docx-js defaults to A4, not US Letter +// Always set page size explicitly for consistent results +sections: [{ + properties: { + page: { + size: { + width: 12240, // 8.5 inches in DXA + height: 15840 // 11 inches in DXA + }, + margin: { top: 1440, right: 1440, bottom: 1440, left: 1440 } // 1 inch margins + } + }, + children: [/* content */] +}] +``` + +**Common page sizes (DXA units, 1440 DXA = 1 inch):** + +| Paper | Width | Height | Content Width (1" margins) | +|-------|-------|--------|---------------------------| +| US Letter | 12,240 | 15,840 | 9,360 | +| A4 (default) | 11,906 | 16,838 | 9,026 | + +**Landscape orientation:** docx-js swaps width/height internally, so pass portrait dimensions and let it handle the swap: +```javascript +size: { + width: 12240, // Pass SHORT edge as width + height: 15840, // Pass LONG edge as height + orientation: PageOrientation.LANDSCAPE // docx-js swaps them in the XML +}, +// Content width = 15840 - left margin - right margin (uses the long edge) +``` + +### Styles (Override Built-in Headings) + +Use Arial as the default font (universally supported). Keep titles black for readability. + +```javascript +const doc = new Document({ + styles: { + default: { document: { run: { font: "Arial", size: 24 } } }, // 12pt default + paragraphStyles: [ + // IMPORTANT: Use exact IDs to override built-in styles + { id: "Heading1", name: "Heading 1", basedOn: "Normal", next: "Normal", quickFormat: true, + run: { size: 32, bold: true, font: "Arial" }, + paragraph: { spacing: { before: 240, after: 240 }, outlineLevel: 0 } }, // outlineLevel required for TOC + { id: "Heading2", name: "Heading 2", basedOn: "Normal", next: "Normal", quickFormat: true, + run: { size: 28, bold: true, font: "Arial" }, + paragraph: { spacing: { before: 180, after: 180 }, outlineLevel: 1 } }, + ] + }, + sections: [{ + children: [ + new Paragraph({ heading: HeadingLevel.HEADING_1, children: [new TextRun("Title")] }), + ] + }] +}); +``` + +### Lists (NEVER use unicode bullets) + +```javascript +// ❌ WRONG - never manually insert bullet characters +new Paragraph({ children: [new TextRun("• Item")] }) // BAD +new Paragraph({ children: [new TextRun("\u2022 Item")] }) // BAD + +// ✅ CORRECT - use numbering config with LevelFormat.BULLET +const doc = new Document({ + numbering: { + config: [ + { reference: "bullets", + levels: [{ level: 0, format: LevelFormat.BULLET, text: "•", alignment: AlignmentType.LEFT, + style: { paragraph: { indent: { left: 720, hanging: 360 } } } }] }, + { reference: "numbers", + levels: [{ level: 0, format: LevelFormat.DECIMAL, text: "%1.", alignment: AlignmentType.LEFT, + style: { paragraph: { indent: { left: 720, hanging: 360 } } } }] }, + ] + }, + sections: [{ + children: [ + new Paragraph({ numbering: { reference: "bullets", level: 0 }, + children: [new TextRun("Bullet item")] }), + new Paragraph({ numbering: { reference: "numbers", level: 0 }, + children: [new TextRun("Numbered item")] }), + ] + }] +}); + +// ⚠️ Each reference creates INDEPENDENT numbering +// Same reference = continues (1,2,3 then 4,5,6) +// Different reference = restarts (1,2,3 then 1,2,3) +``` + +### Tables + +**CRITICAL: Tables need dual widths** - set both `columnWidths` on the table AND `width` on each cell. Without both, tables render incorrectly on some platforms. + +```javascript +// CRITICAL: Always set table width for consistent rendering +// CRITICAL: Use ShadingType.CLEAR (not SOLID) to prevent black backgrounds +const border = { style: BorderStyle.SINGLE, size: 1, color: "CCCCCC" }; +const borders = { top: border, bottom: border, left: border, right: border }; + +new Table({ + width: { size: 9360, type: WidthType.DXA }, // Always use DXA (percentages break in Google Docs) + columnWidths: [4680, 4680], // Must sum to table width (DXA: 1440 = 1 inch) + rows: [ + new TableRow({ + children: [ + new TableCell({ + borders, + width: { size: 4680, type: WidthType.DXA }, // Also set on each cell + shading: { fill: "D5E8F0", type: ShadingType.CLEAR }, // CLEAR not SOLID + margins: { top: 80, bottom: 80, left: 120, right: 120 }, // Cell padding (internal, not added to width) + children: [new Paragraph({ children: [new TextRun("Cell")] })] + }) + ] + }) + ] +}) +``` + +**Table width calculation:** + +Always use `WidthType.DXA` — `WidthType.PERCENTAGE` breaks in Google Docs. + +```javascript +// Table width = sum of columnWidths = content width +// US Letter with 1" margins: 12240 - 2880 = 9360 DXA +width: { size: 9360, type: WidthType.DXA }, +columnWidths: [7000, 2360] // Must sum to table width +``` + +**Width rules:** +- **Always use `WidthType.DXA`** — never `WidthType.PERCENTAGE` (incompatible with Google Docs) +- Table width must equal the sum of `columnWidths` +- Cell `width` must match corresponding `columnWidth` +- Cell `margins` are internal padding - they reduce content area, not add to cell width +- For full-width tables: use content width (page width minus left and right margins) + +### Images + +```javascript +// CRITICAL: type parameter is REQUIRED +new Paragraph({ + children: [new ImageRun({ + type: "png", // Required: png, jpg, jpeg, gif, bmp, svg + data: fs.readFileSync("image.png"), + transformation: { width: 200, height: 150 }, + altText: { title: "Title", description: "Desc", name: "Name" } // All three required + })] +}) +``` + +### Page Breaks + +```javascript +// CRITICAL: PageBreak must be inside a Paragraph +new Paragraph({ children: [new PageBreak()] }) + +// Or use pageBreakBefore +new Paragraph({ pageBreakBefore: true, children: [new TextRun("New page")] }) +``` + +### Table of Contents + +```javascript +// CRITICAL: Headings must use HeadingLevel ONLY - no custom styles +new TableOfContents("Table of Contents", { hyperlink: true, headingStyleRange: "1-3" }) +``` + +### Headers/Footers + +```javascript +sections: [{ + properties: { + page: { margin: { top: 1440, right: 1440, bottom: 1440, left: 1440 } } // 1440 = 1 inch + }, + headers: { + default: new Header({ children: [new Paragraph({ children: [new TextRun("Header")] })] }) + }, + footers: { + default: new Footer({ children: [new Paragraph({ + children: [new TextRun("Page "), new TextRun({ children: [PageNumber.CURRENT] })] + })] }) + }, + children: [/* content */] +}] +``` + +### Critical Rules for docx-js + +- **Set page size explicitly** - docx-js defaults to A4; use US Letter (12240 x 15840 DXA) for US documents +- **Landscape: pass portrait dimensions** - docx-js swaps width/height internally; pass short edge as `width`, long edge as `height`, and set `orientation: PageOrientation.LANDSCAPE` +- **Never use `\n`** - use separate Paragraph elements +- **Never use unicode bullets** - use `LevelFormat.BULLET` with numbering config +- **PageBreak must be in Paragraph** - standalone creates invalid XML +- **ImageRun requires `type`** - always specify png/jpg/etc +- **Always set table `width` with DXA** - never use `WidthType.PERCENTAGE` (breaks in Google Docs) +- **Tables need dual widths** - `columnWidths` array AND cell `width`, both must match +- **Table width = sum of columnWidths** - for DXA, ensure they add up exactly +- **Always add cell margins** - use `margins: { top: 80, bottom: 80, left: 120, right: 120 }` for readable padding +- **Use `ShadingType.CLEAR`** - never SOLID for table shading +- **TOC requires HeadingLevel only** - no custom styles on heading paragraphs +- **Override built-in styles** - use exact IDs: "Heading1", "Heading2", etc. +- **Include `outlineLevel`** - required for TOC (0 for H1, 1 for H2, etc.) + +--- + +## Editing Existing Documents + +**Follow all 3 steps in order.** + +### Step 1: Unpack +```bash +python scripts/office/unpack.py document.docx unpacked/ +``` +Extracts XML, pretty-prints, merges adjacent runs, and converts smart quotes to XML entities (`“` etc.) so they survive editing. Use `--merge-runs false` to skip run merging. + +### Step 2: Edit XML + +Edit files in `unpacked/word/`. See XML Reference below for patterns. + +**Use "Claude" as the author** for tracked changes and comments, unless the user explicitly requests use of a different name. + +**Use the Edit tool directly for string replacement. Do not write Python scripts.** Scripts introduce unnecessary complexity. The Edit tool shows exactly what is being replaced. + +**CRITICAL: Use smart quotes for new content.** When adding text with apostrophes or quotes, use XML entities to produce smart quotes: +```xml + +Here’s a quote: “Hello” +``` +| Entity | Character | +|--------|-----------| +| `‘` | ‘ (left single) | +| `’` | ’ (right single / apostrophe) | +| `“` | “ (left double) | +| `”` | ” (right double) | + +**Adding comments:** Use `comment.py` to handle boilerplate across multiple XML files (text must be pre-escaped XML): +```bash +python scripts/comment.py unpacked/ 0 "Comment text with & and ’" +python scripts/comment.py unpacked/ 1 "Reply text" --parent 0 # reply to comment 0 +python scripts/comment.py unpacked/ 0 "Text" --author "Custom Author" # custom author name +``` +Then add markers to document.xml (see Comments in XML Reference). + +### Step 3: Pack +```bash +python scripts/office/pack.py unpacked/ output.docx --original document.docx +``` +Validates with auto-repair, condenses XML, and creates DOCX. Use `--validate false` to skip. + +**Auto-repair will fix:** +- `durableId` >= 0x7FFFFFFF (regenerates valid ID) +- Missing `xml:space="preserve"` on `` with whitespace + +**Auto-repair won't fix:** +- Malformed XML, invalid element nesting, missing relationships, schema violations + +### Common Pitfalls + +- **Replace entire `` elements**: When adding tracked changes, replace the whole `...` block with `......` as siblings. Don't inject tracked change tags inside a run. +- **Preserve `` formatting**: Copy the original run's `` block into your tracked change runs to maintain bold, font size, etc. + +--- + +## XML Reference + +### Schema Compliance + +- **Element order in ``**: ``, ``, ``, ``, ``, `` last +- **Whitespace**: Add `xml:space="preserve"` to `` with leading/trailing spaces +- **RSIDs**: Must be 8-digit hex (e.g., `00AB1234`) + +### Tracked Changes + +**Insertion:** +```xml + + inserted text + +``` + +**Deletion:** +```xml + + deleted text + +``` + +**Inside ``**: Use `` instead of ``, and `` instead of ``. + +**Minimal edits** - only mark what changes: +```xml + +The term is + + 30 + + + 60 + + days. +``` + +**Deleting entire paragraphs/list items** - when removing ALL content from a paragraph, also mark the paragraph mark as deleted so it merges with the next paragraph. Add `` inside ``: +```xml + + + ... + + + + + + Entire paragraph content being deleted... + + +``` +Without the `` in ``, accepting changes leaves an empty paragraph/list item. + +**Rejecting another author's insertion** - nest deletion inside their insertion: +```xml + + + their inserted text + + +``` + +**Restoring another author's deletion** - add insertion after (don't modify their deletion): +```xml + + deleted text + + + deleted text + +``` + +### Comments + +After running `comment.py` (see Step 2), add markers to document.xml. For replies, use `--parent` flag and nest markers inside the parent's. + +**CRITICAL: `` and `` are siblings of ``, never inside ``.** + +```xml + + + + deleted + + more text + + + + + + + text + + + + +``` + +### Images + +1. Add image file to `word/media/` +2. Add relationship to `word/_rels/document.xml.rels`: +```xml + +``` +3. Add content type to `[Content_Types].xml`: +```xml + +``` +4. Reference in document.xml: +```xml + + + + + + + + + + + + +``` + +--- + +## Dependencies + +- **pandoc**: Text extraction +- **docx**: `npm install -g docx` (new documents) +- **LibreOffice**: PDF conversion (auto-configured for sandboxed environments via `scripts/office/soffice.py`) +- **Poppler**: `pdftoppm` for images diff --git a/.claude/skills/docx/scripts/__init__.py b/.claude/skills/docx/scripts/__init__.py new file mode 100755 index 0000000..8b13789 --- /dev/null +++ b/.claude/skills/docx/scripts/__init__.py @@ -0,0 +1 @@ + diff --git a/.claude/skills/docx/scripts/accept_changes.py b/.claude/skills/docx/scripts/accept_changes.py new file mode 100644 index 0000000..8e36316 --- /dev/null +++ b/.claude/skills/docx/scripts/accept_changes.py @@ -0,0 +1,135 @@ +"""Accept all tracked changes in a DOCX file using LibreOffice. + +Requires LibreOffice (soffice) to be installed. +""" + +import argparse +import logging +import shutil +import subprocess +from pathlib import Path + +from office.soffice import get_soffice_env + +logger = logging.getLogger(__name__) + +LIBREOFFICE_PROFILE = "/tmp/libreoffice_docx_profile" +MACRO_DIR = f"{LIBREOFFICE_PROFILE}/user/basic/Standard" + +ACCEPT_CHANGES_MACRO = """ + + + Sub AcceptAllTrackedChanges() + Dim document As Object + Dim dispatcher As Object + + document = ThisComponent.CurrentController.Frame + dispatcher = createUnoService("com.sun.star.frame.DispatchHelper") + + dispatcher.executeDispatch(document, ".uno:AcceptAllTrackedChanges", "", 0, Array()) + ThisComponent.store() + ThisComponent.close(True) + End Sub +""" + + +def accept_changes( + input_file: str, + output_file: str, +) -> tuple[None, str]: + input_path = Path(input_file) + output_path = Path(output_file) + + if not input_path.exists(): + return None, f"Error: Input file not found: {input_file}" + + if not input_path.suffix.lower() == ".docx": + return None, f"Error: Input file is not a DOCX file: {input_file}" + + try: + output_path.parent.mkdir(parents=True, exist_ok=True) + shutil.copy2(input_path, output_path) + except Exception as e: + return None, f"Error: Failed to copy input file to output location: {e}" + + if not _setup_libreoffice_macro(): + return None, "Error: Failed to setup LibreOffice macro" + + cmd = [ + "soffice", + "--headless", + f"-env:UserInstallation=file://{LIBREOFFICE_PROFILE}", + "--norestore", + "vnd.sun.star.script:Standard.Module1.AcceptAllTrackedChanges?language=Basic&location=application", + str(output_path.absolute()), + ] + + try: + result = subprocess.run( + cmd, + capture_output=True, + text=True, + timeout=30, + check=False, + env=get_soffice_env(), + ) + except subprocess.TimeoutExpired: + return ( + None, + f"Successfully accepted all tracked changes: {input_file} -> {output_file}", + ) + + if result.returncode != 0: + return None, f"Error: LibreOffice failed: {result.stderr}" + + return ( + None, + f"Successfully accepted all tracked changes: {input_file} -> {output_file}", + ) + + +def _setup_libreoffice_macro() -> bool: + macro_dir = Path(MACRO_DIR) + macro_file = macro_dir / "Module1.xba" + + if macro_file.exists() and "AcceptAllTrackedChanges" in macro_file.read_text(): + return True + + if not macro_dir.exists(): + subprocess.run( + [ + "soffice", + "--headless", + f"-env:UserInstallation=file://{LIBREOFFICE_PROFILE}", + "--terminate_after_init", + ], + capture_output=True, + timeout=10, + check=False, + env=get_soffice_env(), + ) + macro_dir.mkdir(parents=True, exist_ok=True) + + try: + macro_file.write_text(ACCEPT_CHANGES_MACRO) + return True + except Exception as e: + logger.warning(f"Failed to setup LibreOffice macro: {e}") + return False + + +if __name__ == "__main__": + parser = argparse.ArgumentParser( + description="Accept all tracked changes in a DOCX file" + ) + parser.add_argument("input_file", help="Input DOCX file with tracked changes") + parser.add_argument( + "output_file", help="Output DOCX file (clean, no tracked changes)" + ) + args = parser.parse_args() + + _, message = accept_changes(args.input_file, args.output_file) + print(message) + + if "Error" in message: + raise SystemExit(1) diff --git a/.claude/skills/docx/scripts/comment.py b/.claude/skills/docx/scripts/comment.py new file mode 100644 index 0000000..36e1c93 --- /dev/null +++ b/.claude/skills/docx/scripts/comment.py @@ -0,0 +1,318 @@ +"""Add comments to DOCX documents. + +Usage: + python comment.py unpacked/ 0 "Comment text" + python comment.py unpacked/ 1 "Reply text" --parent 0 + +Text should be pre-escaped XML (e.g., & for &, ’ for smart quotes). + +After running, add markers to document.xml: + + ... commented content ... + + +""" + +import argparse +import random +import shutil +import sys +from datetime import datetime, timezone +from pathlib import Path + +import defusedxml.minidom + +TEMPLATE_DIR = Path(__file__).parent / "templates" +NS = { + "w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main", + "w14": "http://schemas.microsoft.com/office/word/2010/wordml", + "w15": "http://schemas.microsoft.com/office/word/2012/wordml", + "w16cid": "http://schemas.microsoft.com/office/word/2016/wordml/cid", + "w16cex": "http://schemas.microsoft.com/office/word/2018/wordml/cex", +} + +COMMENT_XML = """\ + + + + + + + + + + + + + {text} + + +""" + +COMMENT_MARKER_TEMPLATE = """ +Add to document.xml (markers must be direct children of w:p, never inside w:r): + + ... + + """ + +REPLY_MARKER_TEMPLATE = """ +Nest markers inside parent {pid}'s markers (markers must be direct children of w:p, never inside w:r): + + ... + + + """ + + +def _generate_hex_id() -> str: + return f"{random.randint(0, 0x7FFFFFFE):08X}" + + +SMART_QUOTE_ENTITIES = { + "\u201c": "“", + "\u201d": "”", + "\u2018": "‘", + "\u2019": "’", +} + + +def _encode_smart_quotes(text: str) -> str: + for char, entity in SMART_QUOTE_ENTITIES.items(): + text = text.replace(char, entity) + return text + + +def _append_xml(xml_path: Path, root_tag: str, content: str) -> None: + dom = defusedxml.minidom.parseString(xml_path.read_text(encoding="utf-8")) + root = dom.getElementsByTagName(root_tag)[0] + ns_attrs = " ".join(f'xmlns:{k}="{v}"' for k, v in NS.items()) + wrapper_dom = defusedxml.minidom.parseString(f"{content}") + for child in wrapper_dom.documentElement.childNodes: + if child.nodeType == child.ELEMENT_NODE: + root.appendChild(dom.importNode(child, True)) + output = _encode_smart_quotes(dom.toxml(encoding="UTF-8").decode("utf-8")) + xml_path.write_text(output, encoding="utf-8") + + +def _find_para_id(comments_path: Path, comment_id: int) -> str | None: + dom = defusedxml.minidom.parseString(comments_path.read_text(encoding="utf-8")) + for c in dom.getElementsByTagName("w:comment"): + if c.getAttribute("w:id") == str(comment_id): + for p in c.getElementsByTagName("w:p"): + if pid := p.getAttribute("w14:paraId"): + return pid + return None + + +def _get_next_rid(rels_path: Path) -> int: + dom = defusedxml.minidom.parseString(rels_path.read_text(encoding="utf-8")) + max_rid = 0 + for rel in dom.getElementsByTagName("Relationship"): + rid = rel.getAttribute("Id") + if rid and rid.startswith("rId"): + try: + max_rid = max(max_rid, int(rid[3:])) + except ValueError: + pass + return max_rid + 1 + + +def _has_relationship(rels_path: Path, target: str) -> bool: + dom = defusedxml.minidom.parseString(rels_path.read_text(encoding="utf-8")) + for rel in dom.getElementsByTagName("Relationship"): + if rel.getAttribute("Target") == target: + return True + return False + + +def _has_content_type(ct_path: Path, part_name: str) -> bool: + dom = defusedxml.minidom.parseString(ct_path.read_text(encoding="utf-8")) + for override in dom.getElementsByTagName("Override"): + if override.getAttribute("PartName") == part_name: + return True + return False + + +def _ensure_comment_relationships(unpacked_dir: Path) -> None: + rels_path = unpacked_dir / "word" / "_rels" / "document.xml.rels" + if not rels_path.exists(): + return + + if _has_relationship(rels_path, "comments.xml"): + return + + dom = defusedxml.minidom.parseString(rels_path.read_text(encoding="utf-8")) + root = dom.documentElement + next_rid = _get_next_rid(rels_path) + + rels = [ + ( + "http://schemas.openxmlformats.org/officeDocument/2006/relationships/comments", + "comments.xml", + ), + ( + "http://schemas.microsoft.com/office/2011/relationships/commentsExtended", + "commentsExtended.xml", + ), + ( + "http://schemas.microsoft.com/office/2016/09/relationships/commentsIds", + "commentsIds.xml", + ), + ( + "http://schemas.microsoft.com/office/2018/08/relationships/commentsExtensible", + "commentsExtensible.xml", + ), + ] + + for rel_type, target in rels: + rel = dom.createElement("Relationship") + rel.setAttribute("Id", f"rId{next_rid}") + rel.setAttribute("Type", rel_type) + rel.setAttribute("Target", target) + root.appendChild(rel) + next_rid += 1 + + rels_path.write_bytes(dom.toxml(encoding="UTF-8")) + + +def _ensure_comment_content_types(unpacked_dir: Path) -> None: + ct_path = unpacked_dir / "[Content_Types].xml" + if not ct_path.exists(): + return + + if _has_content_type(ct_path, "/word/comments.xml"): + return + + dom = defusedxml.minidom.parseString(ct_path.read_text(encoding="utf-8")) + root = dom.documentElement + + overrides = [ + ( + "/word/comments.xml", + "application/vnd.openxmlformats-officedocument.wordprocessingml.comments+xml", + ), + ( + "/word/commentsExtended.xml", + "application/vnd.openxmlformats-officedocument.wordprocessingml.commentsExtended+xml", + ), + ( + "/word/commentsIds.xml", + "application/vnd.openxmlformats-officedocument.wordprocessingml.commentsIds+xml", + ), + ( + "/word/commentsExtensible.xml", + "application/vnd.openxmlformats-officedocument.wordprocessingml.commentsExtensible+xml", + ), + ] + + for part_name, content_type in overrides: + override = dom.createElement("Override") + override.setAttribute("PartName", part_name) + override.setAttribute("ContentType", content_type) + root.appendChild(override) + + ct_path.write_bytes(dom.toxml(encoding="UTF-8")) + + +def add_comment( + unpacked_dir: str, + comment_id: int, + text: str, + author: str = "Claude", + initials: str = "C", + parent_id: int | None = None, +) -> tuple[str, str]: + word = Path(unpacked_dir) / "word" + if not word.exists(): + return "", f"Error: {word} not found" + + para_id, durable_id = _generate_hex_id(), _generate_hex_id() + ts = datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ") + + comments = word / "comments.xml" + first_comment = not comments.exists() + if first_comment: + shutil.copy(TEMPLATE_DIR / "comments.xml", comments) + _ensure_comment_relationships(Path(unpacked_dir)) + _ensure_comment_content_types(Path(unpacked_dir)) + _append_xml( + comments, + "w:comments", + COMMENT_XML.format( + id=comment_id, + author=author, + date=ts, + initials=initials, + para_id=para_id, + text=text, + ), + ) + + ext = word / "commentsExtended.xml" + if not ext.exists(): + shutil.copy(TEMPLATE_DIR / "commentsExtended.xml", ext) + if parent_id is not None: + parent_para = _find_para_id(comments, parent_id) + if not parent_para: + return "", f"Error: Parent comment {parent_id} not found" + _append_xml( + ext, + "w15:commentsEx", + f'', + ) + else: + _append_xml( + ext, + "w15:commentsEx", + f'', + ) + + ids = word / "commentsIds.xml" + if not ids.exists(): + shutil.copy(TEMPLATE_DIR / "commentsIds.xml", ids) + _append_xml( + ids, + "w16cid:commentsIds", + f'', + ) + + extensible = word / "commentsExtensible.xml" + if not extensible.exists(): + shutil.copy(TEMPLATE_DIR / "commentsExtensible.xml", extensible) + _append_xml( + extensible, + "w16cex:commentsExtensible", + f'', + ) + + action = "reply" if parent_id is not None else "comment" + return para_id, f"Added {action} {comment_id} (para_id={para_id})" + + +if __name__ == "__main__": + p = argparse.ArgumentParser(description="Add comments to DOCX documents") + p.add_argument("unpacked_dir", help="Unpacked DOCX directory") + p.add_argument("comment_id", type=int, help="Comment ID (must be unique)") + p.add_argument("text", help="Comment text") + p.add_argument("--author", default="Claude", help="Author name") + p.add_argument("--initials", default="C", help="Author initials") + p.add_argument("--parent", type=int, help="Parent comment ID (for replies)") + args = p.parse_args() + + para_id, msg = add_comment( + args.unpacked_dir, + args.comment_id, + args.text, + args.author, + args.initials, + args.parent, + ) + print(msg) + if "Error" in msg: + sys.exit(1) + cid = args.comment_id + if args.parent is not None: + print(REPLY_MARKER_TEMPLATE.format(pid=args.parent, cid=cid)) + else: + print(COMMENT_MARKER_TEMPLATE.format(cid=cid)) diff --git a/.claude/skills/docx/scripts/office/helpers/__init__.py b/.claude/skills/docx/scripts/office/helpers/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/.claude/skills/docx/scripts/office/helpers/merge_runs.py b/.claude/skills/docx/scripts/office/helpers/merge_runs.py new file mode 100644 index 0000000..ad7c25e --- /dev/null +++ b/.claude/skills/docx/scripts/office/helpers/merge_runs.py @@ -0,0 +1,199 @@ +"""Merge adjacent runs with identical formatting in DOCX. + +Merges adjacent elements that have identical properties. +Works on runs in paragraphs and inside tracked changes (, ). + +Also: +- Removes rsid attributes from runs (revision metadata that doesn't affect rendering) +- Removes proofErr elements (spell/grammar markers that block merging) +""" + +from pathlib import Path + +import defusedxml.minidom + + +def merge_runs(input_dir: str) -> tuple[int, str]: + doc_xml = Path(input_dir) / "word" / "document.xml" + + if not doc_xml.exists(): + return 0, f"Error: {doc_xml} not found" + + try: + dom = defusedxml.minidom.parseString(doc_xml.read_text(encoding="utf-8")) + root = dom.documentElement + + _remove_elements(root, "proofErr") + _strip_run_rsid_attrs(root) + + containers = {run.parentNode for run in _find_elements(root, "r")} + + merge_count = 0 + for container in containers: + merge_count += _merge_runs_in(container) + + doc_xml.write_bytes(dom.toxml(encoding="UTF-8")) + return merge_count, f"Merged {merge_count} runs" + + except Exception as e: + return 0, f"Error: {e}" + + + + +def _find_elements(root, tag: str) -> list: + results = [] + + def traverse(node): + if node.nodeType == node.ELEMENT_NODE: + name = node.localName or node.tagName + if name == tag or name.endswith(f":{tag}"): + results.append(node) + for child in node.childNodes: + traverse(child) + + traverse(root) + return results + + +def _get_child(parent, tag: str): + for child in parent.childNodes: + if child.nodeType == child.ELEMENT_NODE: + name = child.localName or child.tagName + if name == tag or name.endswith(f":{tag}"): + return child + return None + + +def _get_children(parent, tag: str) -> list: + results = [] + for child in parent.childNodes: + if child.nodeType == child.ELEMENT_NODE: + name = child.localName or child.tagName + if name == tag or name.endswith(f":{tag}"): + results.append(child) + return results + + +def _is_adjacent(elem1, elem2) -> bool: + node = elem1.nextSibling + while node: + if node == elem2: + return True + if node.nodeType == node.ELEMENT_NODE: + return False + if node.nodeType == node.TEXT_NODE and node.data.strip(): + return False + node = node.nextSibling + return False + + + + +def _remove_elements(root, tag: str): + for elem in _find_elements(root, tag): + if elem.parentNode: + elem.parentNode.removeChild(elem) + + +def _strip_run_rsid_attrs(root): + for run in _find_elements(root, "r"): + for attr in list(run.attributes.values()): + if "rsid" in attr.name.lower(): + run.removeAttribute(attr.name) + + + + +def _merge_runs_in(container) -> int: + merge_count = 0 + run = _first_child_run(container) + + while run: + while True: + next_elem = _next_element_sibling(run) + if next_elem and _is_run(next_elem) and _can_merge(run, next_elem): + _merge_run_content(run, next_elem) + container.removeChild(next_elem) + merge_count += 1 + else: + break + + _consolidate_text(run) + run = _next_sibling_run(run) + + return merge_count + + +def _first_child_run(container): + for child in container.childNodes: + if child.nodeType == child.ELEMENT_NODE and _is_run(child): + return child + return None + + +def _next_element_sibling(node): + sibling = node.nextSibling + while sibling: + if sibling.nodeType == sibling.ELEMENT_NODE: + return sibling + sibling = sibling.nextSibling + return None + + +def _next_sibling_run(node): + sibling = node.nextSibling + while sibling: + if sibling.nodeType == sibling.ELEMENT_NODE: + if _is_run(sibling): + return sibling + sibling = sibling.nextSibling + return None + + +def _is_run(node) -> bool: + name = node.localName or node.tagName + return name == "r" or name.endswith(":r") + + +def _can_merge(run1, run2) -> bool: + rpr1 = _get_child(run1, "rPr") + rpr2 = _get_child(run2, "rPr") + + if (rpr1 is None) != (rpr2 is None): + return False + if rpr1 is None: + return True + return rpr1.toxml() == rpr2.toxml() + + +def _merge_run_content(target, source): + for child in list(source.childNodes): + if child.nodeType == child.ELEMENT_NODE: + name = child.localName or child.tagName + if name != "rPr" and not name.endswith(":rPr"): + target.appendChild(child) + + +def _consolidate_text(run): + t_elements = _get_children(run, "t") + + for i in range(len(t_elements) - 1, 0, -1): + curr, prev = t_elements[i], t_elements[i - 1] + + if _is_adjacent(prev, curr): + prev_text = prev.firstChild.data if prev.firstChild else "" + curr_text = curr.firstChild.data if curr.firstChild else "" + merged = prev_text + curr_text + + if prev.firstChild: + prev.firstChild.data = merged + else: + prev.appendChild(run.ownerDocument.createTextNode(merged)) + + if merged.startswith(" ") or merged.endswith(" "): + prev.setAttribute("xml:space", "preserve") + elif prev.hasAttribute("xml:space"): + prev.removeAttribute("xml:space") + + run.removeChild(curr) diff --git a/.claude/skills/docx/scripts/office/helpers/simplify_redlines.py b/.claude/skills/docx/scripts/office/helpers/simplify_redlines.py new file mode 100644 index 0000000..db963bb --- /dev/null +++ b/.claude/skills/docx/scripts/office/helpers/simplify_redlines.py @@ -0,0 +1,197 @@ +"""Simplify tracked changes by merging adjacent w:ins or w:del elements. + +Merges adjacent elements from the same author into a single element. +Same for elements. This makes heavily-redlined documents easier to +work with by reducing the number of tracked change wrappers. + +Rules: +- Only merges w:ins with w:ins, w:del with w:del (same element type) +- Only merges if same author (ignores timestamp differences) +- Only merges if truly adjacent (only whitespace between them) +""" + +import xml.etree.ElementTree as ET +import zipfile +from pathlib import Path + +import defusedxml.minidom + +WORD_NS = "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + + +def simplify_redlines(input_dir: str) -> tuple[int, str]: + doc_xml = Path(input_dir) / "word" / "document.xml" + + if not doc_xml.exists(): + return 0, f"Error: {doc_xml} not found" + + try: + dom = defusedxml.minidom.parseString(doc_xml.read_text(encoding="utf-8")) + root = dom.documentElement + + merge_count = 0 + + containers = _find_elements(root, "p") + _find_elements(root, "tc") + + for container in containers: + merge_count += _merge_tracked_changes_in(container, "ins") + merge_count += _merge_tracked_changes_in(container, "del") + + doc_xml.write_bytes(dom.toxml(encoding="UTF-8")) + return merge_count, f"Simplified {merge_count} tracked changes" + + except Exception as e: + return 0, f"Error: {e}" + + +def _merge_tracked_changes_in(container, tag: str) -> int: + merge_count = 0 + + tracked = [ + child + for child in container.childNodes + if child.nodeType == child.ELEMENT_NODE and _is_element(child, tag) + ] + + if len(tracked) < 2: + return 0 + + i = 0 + while i < len(tracked) - 1: + curr = tracked[i] + next_elem = tracked[i + 1] + + if _can_merge_tracked(curr, next_elem): + _merge_tracked_content(curr, next_elem) + container.removeChild(next_elem) + tracked.pop(i + 1) + merge_count += 1 + else: + i += 1 + + return merge_count + + +def _is_element(node, tag: str) -> bool: + name = node.localName or node.tagName + return name == tag or name.endswith(f":{tag}") + + +def _get_author(elem) -> str: + author = elem.getAttribute("w:author") + if not author: + for attr in elem.attributes.values(): + if attr.localName == "author" or attr.name.endswith(":author"): + return attr.value + return author + + +def _can_merge_tracked(elem1, elem2) -> bool: + if _get_author(elem1) != _get_author(elem2): + return False + + node = elem1.nextSibling + while node and node != elem2: + if node.nodeType == node.ELEMENT_NODE: + return False + if node.nodeType == node.TEXT_NODE and node.data.strip(): + return False + node = node.nextSibling + + return True + + +def _merge_tracked_content(target, source): + while source.firstChild: + child = source.firstChild + source.removeChild(child) + target.appendChild(child) + + +def _find_elements(root, tag: str) -> list: + results = [] + + def traverse(node): + if node.nodeType == node.ELEMENT_NODE: + name = node.localName or node.tagName + if name == tag or name.endswith(f":{tag}"): + results.append(node) + for child in node.childNodes: + traverse(child) + + traverse(root) + return results + + +def get_tracked_change_authors(doc_xml_path: Path) -> dict[str, int]: + if not doc_xml_path.exists(): + return {} + + try: + tree = ET.parse(doc_xml_path) + root = tree.getroot() + except ET.ParseError: + return {} + + namespaces = {"w": WORD_NS} + author_attr = f"{{{WORD_NS}}}author" + + authors: dict[str, int] = {} + for tag in ["ins", "del"]: + for elem in root.findall(f".//w:{tag}", namespaces): + author = elem.get(author_attr) + if author: + authors[author] = authors.get(author, 0) + 1 + + return authors + + +def _get_authors_from_docx(docx_path: Path) -> dict[str, int]: + try: + with zipfile.ZipFile(docx_path, "r") as zf: + if "word/document.xml" not in zf.namelist(): + return {} + with zf.open("word/document.xml") as f: + tree = ET.parse(f) + root = tree.getroot() + + namespaces = {"w": WORD_NS} + author_attr = f"{{{WORD_NS}}}author" + + authors: dict[str, int] = {} + for tag in ["ins", "del"]: + for elem in root.findall(f".//w:{tag}", namespaces): + author = elem.get(author_attr) + if author: + authors[author] = authors.get(author, 0) + 1 + return authors + except (zipfile.BadZipFile, ET.ParseError): + return {} + + +def infer_author(modified_dir: Path, original_docx: Path, default: str = "Claude") -> str: + modified_xml = modified_dir / "word" / "document.xml" + modified_authors = get_tracked_change_authors(modified_xml) + + if not modified_authors: + return default + + original_authors = _get_authors_from_docx(original_docx) + + new_changes: dict[str, int] = {} + for author, count in modified_authors.items(): + original_count = original_authors.get(author, 0) + diff = count - original_count + if diff > 0: + new_changes[author] = diff + + if not new_changes: + return default + + if len(new_changes) == 1: + return next(iter(new_changes)) + + raise ValueError( + f"Multiple authors added new changes: {new_changes}. " + "Cannot infer which author to validate." + ) diff --git a/.claude/skills/docx/scripts/office/pack.py b/.claude/skills/docx/scripts/office/pack.py new file mode 100755 index 0000000..db29ed8 --- /dev/null +++ b/.claude/skills/docx/scripts/office/pack.py @@ -0,0 +1,159 @@ +"""Pack a directory into a DOCX, PPTX, or XLSX file. + +Validates with auto-repair, condenses XML formatting, and creates the Office file. + +Usage: + python pack.py [--original ] [--validate true|false] + +Examples: + python pack.py unpacked/ output.docx --original input.docx + python pack.py unpacked/ output.pptx --validate false +""" + +import argparse +import sys +import shutil +import tempfile +import zipfile +from pathlib import Path + +import defusedxml.minidom + +from validators import DOCXSchemaValidator, PPTXSchemaValidator, RedliningValidator + +def pack( + input_directory: str, + output_file: str, + original_file: str | None = None, + validate: bool = True, + infer_author_func=None, +) -> tuple[None, str]: + input_dir = Path(input_directory) + output_path = Path(output_file) + suffix = output_path.suffix.lower() + + if not input_dir.is_dir(): + return None, f"Error: {input_dir} is not a directory" + + if suffix not in {".docx", ".pptx", ".xlsx"}: + return None, f"Error: {output_file} must be a .docx, .pptx, or .xlsx file" + + if validate and original_file: + original_path = Path(original_file) + if original_path.exists(): + success, output = _run_validation( + input_dir, original_path, suffix, infer_author_func + ) + if output: + print(output) + if not success: + return None, f"Error: Validation failed for {input_dir}" + + with tempfile.TemporaryDirectory() as temp_dir: + temp_content_dir = Path(temp_dir) / "content" + shutil.copytree(input_dir, temp_content_dir) + + for pattern in ["*.xml", "*.rels"]: + for xml_file in temp_content_dir.rglob(pattern): + _condense_xml(xml_file) + + output_path.parent.mkdir(parents=True, exist_ok=True) + with zipfile.ZipFile(output_path, "w", zipfile.ZIP_DEFLATED) as zf: + for f in temp_content_dir.rglob("*"): + if f.is_file(): + zf.write(f, f.relative_to(temp_content_dir)) + + return None, f"Successfully packed {input_dir} to {output_file}" + + +def _run_validation( + unpacked_dir: Path, + original_file: Path, + suffix: str, + infer_author_func=None, +) -> tuple[bool, str | None]: + output_lines = [] + validators = [] + + if suffix == ".docx": + author = "Claude" + if infer_author_func: + try: + author = infer_author_func(unpacked_dir, original_file) + except ValueError as e: + print(f"Warning: {e} Using default author 'Claude'.", file=sys.stderr) + + validators = [ + DOCXSchemaValidator(unpacked_dir, original_file), + RedliningValidator(unpacked_dir, original_file, author=author), + ] + elif suffix == ".pptx": + validators = [PPTXSchemaValidator(unpacked_dir, original_file)] + + if not validators: + return True, None + + total_repairs = sum(v.repair() for v in validators) + if total_repairs: + output_lines.append(f"Auto-repaired {total_repairs} issue(s)") + + success = all(v.validate() for v in validators) + + if success: + output_lines.append("All validations PASSED!") + + return success, "\n".join(output_lines) if output_lines else None + + +def _condense_xml(xml_file: Path) -> None: + try: + with open(xml_file, encoding="utf-8") as f: + dom = defusedxml.minidom.parse(f) + + for element in dom.getElementsByTagName("*"): + if element.tagName.endswith(":t"): + continue + + for child in list(element.childNodes): + if ( + child.nodeType == child.TEXT_NODE + and child.nodeValue + and child.nodeValue.strip() == "" + ) or child.nodeType == child.COMMENT_NODE: + element.removeChild(child) + + xml_file.write_bytes(dom.toxml(encoding="UTF-8")) + except Exception as e: + print(f"ERROR: Failed to parse {xml_file.name}: {e}", file=sys.stderr) + raise + + +if __name__ == "__main__": + parser = argparse.ArgumentParser( + description="Pack a directory into a DOCX, PPTX, or XLSX file" + ) + parser.add_argument("input_directory", help="Unpacked Office document directory") + parser.add_argument("output_file", help="Output Office file (.docx/.pptx/.xlsx)") + parser.add_argument( + "--original", + help="Original file for validation comparison", + ) + parser.add_argument( + "--validate", + type=lambda x: x.lower() == "true", + default=True, + metavar="true|false", + help="Run validation with auto-repair (default: true)", + ) + args = parser.parse_args() + + _, message = pack( + args.input_directory, + args.output_file, + original_file=args.original, + validate=args.validate, + ) + print(message) + + if "Error" in message: + sys.exit(1) diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd new file mode 100644 index 0000000..6454ef9 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd @@ -0,0 +1,1499 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd new file mode 100644 index 0000000..afa4f46 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd @@ -0,0 +1,146 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd new file mode 100644 index 0000000..64e66b8 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd @@ -0,0 +1,1085 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd new file mode 100644 index 0000000..687eea8 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd @@ -0,0 +1,11 @@ + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd new file mode 100644 index 0000000..6ac81b0 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd @@ -0,0 +1,3081 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd new file mode 100644 index 0000000..1dbf051 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd @@ -0,0 +1,23 @@ + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd new file mode 100644 index 0000000..f1af17d --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd @@ -0,0 +1,185 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd new file mode 100644 index 0000000..0a185ab --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd @@ -0,0 +1,287 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd new file mode 100644 index 0000000..14ef488 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd @@ -0,0 +1,1676 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd new file mode 100644 index 0000000..c20f3bf --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd @@ -0,0 +1,28 @@ + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd new file mode 100644 index 0000000..ac60252 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd @@ -0,0 +1,144 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd new file mode 100644 index 0000000..424b8ba --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd @@ -0,0 +1,174 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd new file mode 100644 index 0000000..2bddce2 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd @@ -0,0 +1,25 @@ + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd new file mode 100644 index 0000000..8a8c18b --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd @@ -0,0 +1,18 @@ + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd new file mode 100644 index 0000000..5c42706 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd @@ -0,0 +1,59 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd new file mode 100644 index 0000000..853c341 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd @@ -0,0 +1,56 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd new file mode 100644 index 0000000..da835ee --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd @@ -0,0 +1,195 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd new file mode 100644 index 0000000..87ad265 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd @@ -0,0 +1,582 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd new file mode 100644 index 0000000..9e86f1b --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd @@ -0,0 +1,25 @@ + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd new file mode 100644 index 0000000..d0be42e --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd @@ -0,0 +1,4439 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd new file mode 100644 index 0000000..8821dd1 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd @@ -0,0 +1,570 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd new file mode 100644 index 0000000..ca2575c --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd @@ -0,0 +1,509 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd new file mode 100644 index 0000000..dd079e6 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd @@ -0,0 +1,12 @@ + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd new file mode 100644 index 0000000..3dd6cf6 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd @@ -0,0 +1,108 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd new file mode 100644 index 0000000..f1041e3 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd @@ -0,0 +1,96 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd new file mode 100644 index 0000000..9c5b7a6 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd @@ -0,0 +1,3646 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd new file mode 100644 index 0000000..0f13678 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd @@ -0,0 +1,116 @@ + + + + + + See http://www.w3.org/XML/1998/namespace.html and + http://www.w3.org/TR/REC-xml for information about this namespace. + + This schema document describes the XML namespace, in a form + suitable for import by other schema documents. + + Note that local names in this namespace are intended to be defined + only by the World Wide Web Consortium or its subgroups. The + following names are currently defined in this namespace and should + not be used with conflicting semantics by any Working Group, + specification, or document instance: + + base (as an attribute name): denotes an attribute whose value + provides a URI to be used as the base for interpreting any + relative URIs in the scope of the element on which it + appears; its value is inherited. This name is reserved + by virtue of its definition in the XML Base specification. + + lang (as an attribute name): denotes an attribute whose value + is a language code for the natural language of the content of + any element; its value is inherited. This name is reserved + by virtue of its definition in the XML specification. + + space (as an attribute name): denotes an attribute whose + value is a keyword indicating what whitespace processing + discipline is intended for the content of the element; its + value is inherited. This name is reserved by virtue of its + definition in the XML specification. + + Father (in any context at all): denotes Jon Bosak, the chair of + the original XML Working Group. This name is reserved by + the following decision of the W3C XML Plenary and + XML Coordination groups: + + In appreciation for his vision, leadership and dedication + the W3C XML Plenary on this 10th day of February, 2000 + reserves for Jon Bosak in perpetuity the XML name + xml:Father + + + + + This schema defines attributes and an attribute group + suitable for use by + schemas wishing to allow xml:base, xml:lang or xml:space attributes + on elements they define. + + To enable this, such a schema must import this schema + for the XML namespace, e.g. as follows: + <schema . . .> + . . . + <import namespace="http://www.w3.org/XML/1998/namespace" + schemaLocation="http://www.w3.org/2001/03/xml.xsd"/> + + Subsequently, qualified reference to any of the attributes + or the group defined below will have the desired effect, e.g. + + <type . . .> + . . . + <attributeGroup ref="xml:specialAttrs"/> + + will define a type which will schema-validate an instance + element with any of those attributes + + + + In keeping with the XML Schema WG's standard versioning + policy, this schema document will persist at + http://www.w3.org/2001/03/xml.xsd. + At the date of issue it can also be found at + http://www.w3.org/2001/xml.xsd. + The schema document at that URI may however change in the future, + in order to remain compatible with the latest version of XML Schema + itself. In other words, if the XML Schema namespace changes, the version + of this document at + http://www.w3.org/2001/xml.xsd will change + accordingly; the version at + http://www.w3.org/2001/03/xml.xsd will not change. + + + + + + In due course, we should install the relevant ISO 2- and 3-letter + codes as the enumerated possible values . . . + + + + + + + + + + + + + + + See http://www.w3.org/TR/xmlbase/ for + information about this attribute. + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd b/.claude/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd new file mode 100644 index 0000000..a6de9d2 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd @@ -0,0 +1,42 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd b/.claude/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd new file mode 100644 index 0000000..10e978b --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd @@ -0,0 +1,50 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd b/.claude/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd new file mode 100644 index 0000000..4248bf7 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd @@ -0,0 +1,49 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd b/.claude/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd new file mode 100644 index 0000000..5649746 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd @@ -0,0 +1,33 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/mce/mc.xsd b/.claude/skills/docx/scripts/office/schemas/mce/mc.xsd new file mode 100644 index 0000000..ef72545 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/mce/mc.xsd @@ -0,0 +1,75 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/microsoft/wml-2010.xsd b/.claude/skills/docx/scripts/office/schemas/microsoft/wml-2010.xsd new file mode 100644 index 0000000..f65f777 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/microsoft/wml-2010.xsd @@ -0,0 +1,560 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/microsoft/wml-2012.xsd b/.claude/skills/docx/scripts/office/schemas/microsoft/wml-2012.xsd new file mode 100644 index 0000000..6b00755 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/microsoft/wml-2012.xsd @@ -0,0 +1,67 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/microsoft/wml-2018.xsd b/.claude/skills/docx/scripts/office/schemas/microsoft/wml-2018.xsd new file mode 100644 index 0000000..f321d33 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/microsoft/wml-2018.xsd @@ -0,0 +1,14 @@ + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/microsoft/wml-cex-2018.xsd b/.claude/skills/docx/scripts/office/schemas/microsoft/wml-cex-2018.xsd new file mode 100644 index 0000000..364c6a9 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/microsoft/wml-cex-2018.xsd @@ -0,0 +1,20 @@ + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/microsoft/wml-cid-2016.xsd b/.claude/skills/docx/scripts/office/schemas/microsoft/wml-cid-2016.xsd new file mode 100644 index 0000000..fed9d15 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/microsoft/wml-cid-2016.xsd @@ -0,0 +1,13 @@ + + + + + + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd b/.claude/skills/docx/scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd new file mode 100644 index 0000000..680cf15 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd @@ -0,0 +1,4 @@ + + + + diff --git a/.claude/skills/docx/scripts/office/schemas/microsoft/wml-symex-2015.xsd b/.claude/skills/docx/scripts/office/schemas/microsoft/wml-symex-2015.xsd new file mode 100644 index 0000000..89ada90 --- /dev/null +++ b/.claude/skills/docx/scripts/office/schemas/microsoft/wml-symex-2015.xsd @@ -0,0 +1,8 @@ + + + + + + + + diff --git a/.claude/skills/docx/scripts/office/soffice.py b/.claude/skills/docx/scripts/office/soffice.py new file mode 100644 index 0000000..c7f7e32 --- /dev/null +++ b/.claude/skills/docx/scripts/office/soffice.py @@ -0,0 +1,183 @@ +""" +Helper for running LibreOffice (soffice) in environments where AF_UNIX +sockets may be blocked (e.g., sandboxed VMs). Detects the restriction +at runtime and applies an LD_PRELOAD shim if needed. + +Usage: + from office.soffice import run_soffice, get_soffice_env + + # Option 1 – run soffice directly + result = run_soffice(["--headless", "--convert-to", "pdf", "input.docx"]) + + # Option 2 – get env dict for your own subprocess calls + env = get_soffice_env() + subprocess.run(["soffice", ...], env=env) +""" + +import os +import socket +import subprocess +import tempfile +from pathlib import Path + + +def get_soffice_env() -> dict: + env = os.environ.copy() + env["SAL_USE_VCLPLUGIN"] = "svp" + + if _needs_shim(): + shim = _ensure_shim() + env["LD_PRELOAD"] = str(shim) + + return env + + +def run_soffice(args: list[str], **kwargs) -> subprocess.CompletedProcess: + env = get_soffice_env() + return subprocess.run(["soffice"] + args, env=env, **kwargs) + + + +_SHIM_SO = Path(tempfile.gettempdir()) / "lo_socket_shim.so" + + +def _needs_shim() -> bool: + try: + s = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM) + s.close() + return False + except OSError: + return True + + +def _ensure_shim() -> Path: + if _SHIM_SO.exists(): + return _SHIM_SO + + src = Path(tempfile.gettempdir()) / "lo_socket_shim.c" + src.write_text(_SHIM_SOURCE) + subprocess.run( + ["gcc", "-shared", "-fPIC", "-o", str(_SHIM_SO), str(src), "-ldl"], + check=True, + capture_output=True, + ) + src.unlink() + return _SHIM_SO + + + +_SHIM_SOURCE = r""" +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include + +static int (*real_socket)(int, int, int); +static int (*real_socketpair)(int, int, int, int[2]); +static int (*real_listen)(int, int); +static int (*real_accept)(int, struct sockaddr *, socklen_t *); +static int (*real_close)(int); +static int (*real_read)(int, void *, size_t); + +/* Per-FD bookkeeping (FDs >= 1024 are passed through unshimmed). */ +static int is_shimmed[1024]; +static int peer_of[1024]; +static int wake_r[1024]; /* accept() blocks reading this */ +static int wake_w[1024]; /* close() writes to this */ +static int listener_fd = -1; /* FD that received listen() */ + +__attribute__((constructor)) +static void init(void) { + real_socket = dlsym(RTLD_NEXT, "socket"); + real_socketpair = dlsym(RTLD_NEXT, "socketpair"); + real_listen = dlsym(RTLD_NEXT, "listen"); + real_accept = dlsym(RTLD_NEXT, "accept"); + real_close = dlsym(RTLD_NEXT, "close"); + real_read = dlsym(RTLD_NEXT, "read"); + for (int i = 0; i < 1024; i++) { + peer_of[i] = -1; + wake_r[i] = -1; + wake_w[i] = -1; + } +} + +/* ---- socket ---------------------------------------------------------- */ +int socket(int domain, int type, int protocol) { + if (domain == AF_UNIX) { + int fd = real_socket(domain, type, protocol); + if (fd >= 0) return fd; + /* socket(AF_UNIX) blocked – fall back to socketpair(). */ + int sv[2]; + if (real_socketpair(domain, type, protocol, sv) == 0) { + if (sv[0] >= 0 && sv[0] < 1024) { + is_shimmed[sv[0]] = 1; + peer_of[sv[0]] = sv[1]; + int wp[2]; + if (pipe(wp) == 0) { + wake_r[sv[0]] = wp[0]; + wake_w[sv[0]] = wp[1]; + } + } + return sv[0]; + } + errno = EPERM; + return -1; + } + return real_socket(domain, type, protocol); +} + +/* ---- listen ---------------------------------------------------------- */ +int listen(int sockfd, int backlog) { + if (sockfd >= 0 && sockfd < 1024 && is_shimmed[sockfd]) { + listener_fd = sockfd; + return 0; + } + return real_listen(sockfd, backlog); +} + +/* ---- accept ---------------------------------------------------------- */ +int accept(int sockfd, struct sockaddr *addr, socklen_t *addrlen) { + if (sockfd >= 0 && sockfd < 1024 && is_shimmed[sockfd]) { + /* Block until close() writes to the wake pipe. */ + if (wake_r[sockfd] >= 0) { + char buf; + real_read(wake_r[sockfd], &buf, 1); + } + errno = ECONNABORTED; + return -1; + } + return real_accept(sockfd, addr, addrlen); +} + +/* ---- close ----------------------------------------------------------- */ +int close(int fd) { + if (fd >= 0 && fd < 1024 && is_shimmed[fd]) { + int was_listener = (fd == listener_fd); + is_shimmed[fd] = 0; + + if (wake_w[fd] >= 0) { /* unblock accept() */ + char c = 0; + write(wake_w[fd], &c, 1); + real_close(wake_w[fd]); + wake_w[fd] = -1; + } + if (wake_r[fd] >= 0) { real_close(wake_r[fd]); wake_r[fd] = -1; } + if (peer_of[fd] >= 0) { real_close(peer_of[fd]); peer_of[fd] = -1; } + + if (was_listener) + _exit(0); /* conversion done – exit */ + } + return real_close(fd); +} +""" + + + +if __name__ == "__main__": + import sys + result = run_soffice(sys.argv[1:]) + sys.exit(result.returncode) diff --git a/.claude/skills/docx/scripts/office/unpack.py b/.claude/skills/docx/scripts/office/unpack.py new file mode 100755 index 0000000..0015253 --- /dev/null +++ b/.claude/skills/docx/scripts/office/unpack.py @@ -0,0 +1,132 @@ +"""Unpack Office files (DOCX, PPTX, XLSX) for editing. + +Extracts the ZIP archive, pretty-prints XML files, and optionally: +- Merges adjacent runs with identical formatting (DOCX only) +- Simplifies adjacent tracked changes from same author (DOCX only) + +Usage: + python unpack.py [options] + +Examples: + python unpack.py document.docx unpacked/ + python unpack.py presentation.pptx unpacked/ + python unpack.py document.docx unpacked/ --merge-runs false +""" + +import argparse +import sys +import zipfile +from pathlib import Path + +import defusedxml.minidom + +from helpers.merge_runs import merge_runs as do_merge_runs +from helpers.simplify_redlines import simplify_redlines as do_simplify_redlines + +SMART_QUOTE_REPLACEMENTS = { + "\u201c": "“", + "\u201d": "”", + "\u2018": "‘", + "\u2019": "’", +} + + +def unpack( + input_file: str, + output_directory: str, + merge_runs: bool = True, + simplify_redlines: bool = True, +) -> tuple[None, str]: + input_path = Path(input_file) + output_path = Path(output_directory) + suffix = input_path.suffix.lower() + + if not input_path.exists(): + return None, f"Error: {input_file} does not exist" + + if suffix not in {".docx", ".pptx", ".xlsx"}: + return None, f"Error: {input_file} must be a .docx, .pptx, or .xlsx file" + + try: + output_path.mkdir(parents=True, exist_ok=True) + + with zipfile.ZipFile(input_path, "r") as zf: + zf.extractall(output_path) + + xml_files = list(output_path.rglob("*.xml")) + list(output_path.rglob("*.rels")) + for xml_file in xml_files: + _pretty_print_xml(xml_file) + + message = f"Unpacked {input_file} ({len(xml_files)} XML files)" + + if suffix == ".docx": + if simplify_redlines: + simplify_count, _ = do_simplify_redlines(str(output_path)) + message += f", simplified {simplify_count} tracked changes" + + if merge_runs: + merge_count, _ = do_merge_runs(str(output_path)) + message += f", merged {merge_count} runs" + + for xml_file in xml_files: + _escape_smart_quotes(xml_file) + + return None, message + + except zipfile.BadZipFile: + return None, f"Error: {input_file} is not a valid Office file" + except Exception as e: + return None, f"Error unpacking: {e}" + + +def _pretty_print_xml(xml_file: Path) -> None: + try: + content = xml_file.read_text(encoding="utf-8") + dom = defusedxml.minidom.parseString(content) + xml_file.write_bytes(dom.toprettyxml(indent=" ", encoding="utf-8")) + except Exception: + pass + + +def _escape_smart_quotes(xml_file: Path) -> None: + try: + content = xml_file.read_text(encoding="utf-8") + for char, entity in SMART_QUOTE_REPLACEMENTS.items(): + content = content.replace(char, entity) + xml_file.write_text(content, encoding="utf-8") + except Exception: + pass + + +if __name__ == "__main__": + parser = argparse.ArgumentParser( + description="Unpack an Office file (DOCX, PPTX, XLSX) for editing" + ) + parser.add_argument("input_file", help="Office file to unpack") + parser.add_argument("output_directory", help="Output directory") + parser.add_argument( + "--merge-runs", + type=lambda x: x.lower() == "true", + default=True, + metavar="true|false", + help="Merge adjacent runs with identical formatting (DOCX only, default: true)", + ) + parser.add_argument( + "--simplify-redlines", + type=lambda x: x.lower() == "true", + default=True, + metavar="true|false", + help="Merge adjacent tracked changes from same author (DOCX only, default: true)", + ) + args = parser.parse_args() + + _, message = unpack( + args.input_file, + args.output_directory, + merge_runs=args.merge_runs, + simplify_redlines=args.simplify_redlines, + ) + print(message) + + if "Error" in message: + sys.exit(1) diff --git a/.claude/skills/docx/scripts/office/validate.py b/.claude/skills/docx/scripts/office/validate.py new file mode 100755 index 0000000..03b01f6 --- /dev/null +++ b/.claude/skills/docx/scripts/office/validate.py @@ -0,0 +1,111 @@ +""" +Command line tool to validate Office document XML files against XSD schemas and tracked changes. + +Usage: + python validate.py [--original ] [--auto-repair] [--author NAME] + +The first argument can be either: +- An unpacked directory containing the Office document XML files +- A packed Office file (.docx/.pptx/.xlsx) which will be unpacked to a temp directory + +Auto-repair fixes: +- paraId/durableId values that exceed OOXML limits +- Missing xml:space="preserve" on w:t elements with whitespace +""" + +import argparse +import sys +import tempfile +import zipfile +from pathlib import Path + +from validators import DOCXSchemaValidator, PPTXSchemaValidator, RedliningValidator + + +def main(): + parser = argparse.ArgumentParser(description="Validate Office document XML files") + parser.add_argument( + "path", + help="Path to unpacked directory or packed Office file (.docx/.pptx/.xlsx)", + ) + parser.add_argument( + "--original", + required=False, + default=None, + help="Path to original file (.docx/.pptx/.xlsx). If omitted, all XSD errors are reported and redlining validation is skipped.", + ) + parser.add_argument( + "-v", + "--verbose", + action="store_true", + help="Enable verbose output", + ) + parser.add_argument( + "--auto-repair", + action="store_true", + help="Automatically repair common issues (hex IDs, whitespace preservation)", + ) + parser.add_argument( + "--author", + default="Claude", + help="Author name for redlining validation (default: Claude)", + ) + args = parser.parse_args() + + path = Path(args.path) + assert path.exists(), f"Error: {path} does not exist" + + original_file = None + if args.original: + original_file = Path(args.original) + assert original_file.is_file(), f"Error: {original_file} is not a file" + assert original_file.suffix.lower() in [".docx", ".pptx", ".xlsx"], ( + f"Error: {original_file} must be a .docx, .pptx, or .xlsx file" + ) + + file_extension = (original_file or path).suffix.lower() + assert file_extension in [".docx", ".pptx", ".xlsx"], ( + f"Error: Cannot determine file type from {path}. Use --original or provide a .docx/.pptx/.xlsx file." + ) + + if path.is_file() and path.suffix.lower() in [".docx", ".pptx", ".xlsx"]: + temp_dir = tempfile.mkdtemp() + with zipfile.ZipFile(path, "r") as zf: + zf.extractall(temp_dir) + unpacked_dir = Path(temp_dir) + else: + assert path.is_dir(), f"Error: {path} is not a directory or Office file" + unpacked_dir = path + + match file_extension: + case ".docx": + validators = [ + DOCXSchemaValidator(unpacked_dir, original_file, verbose=args.verbose), + ] + if original_file: + validators.append( + RedliningValidator(unpacked_dir, original_file, verbose=args.verbose, author=args.author) + ) + case ".pptx": + validators = [ + PPTXSchemaValidator(unpacked_dir, original_file, verbose=args.verbose), + ] + case _: + print(f"Error: Validation not supported for file type {file_extension}") + sys.exit(1) + + if args.auto_repair: + total_repairs = sum(v.repair() for v in validators) + if total_repairs: + print(f"Auto-repaired {total_repairs} issue(s)") + + success = all(v.validate() for v in validators) + + if success: + print("All validations PASSED!") + + sys.exit(0 if success else 1) + + +if __name__ == "__main__": + main() diff --git a/.claude/skills/docx/scripts/office/validators/__init__.py b/.claude/skills/docx/scripts/office/validators/__init__.py new file mode 100644 index 0000000..db092ec --- /dev/null +++ b/.claude/skills/docx/scripts/office/validators/__init__.py @@ -0,0 +1,15 @@ +""" +Validation modules for Word document processing. +""" + +from .base import BaseSchemaValidator +from .docx import DOCXSchemaValidator +from .pptx import PPTXSchemaValidator +from .redlining import RedliningValidator + +__all__ = [ + "BaseSchemaValidator", + "DOCXSchemaValidator", + "PPTXSchemaValidator", + "RedliningValidator", +] diff --git a/.claude/skills/docx/scripts/office/validators/base.py b/.claude/skills/docx/scripts/office/validators/base.py new file mode 100644 index 0000000..db4a06a --- /dev/null +++ b/.claude/skills/docx/scripts/office/validators/base.py @@ -0,0 +1,847 @@ +""" +Base validator with common validation logic for document files. +""" + +import re +from pathlib import Path + +import defusedxml.minidom +import lxml.etree + + +class BaseSchemaValidator: + + IGNORED_VALIDATION_ERRORS = [ + "hyphenationZone", + "purl.org/dc/terms", + ] + + UNIQUE_ID_REQUIREMENTS = { + "comment": ("id", "file"), + "commentrangestart": ("id", "file"), + "commentrangeend": ("id", "file"), + "bookmarkstart": ("id", "file"), + "bookmarkend": ("id", "file"), + "sldid": ("id", "file"), + "sldmasterid": ("id", "global"), + "sldlayoutid": ("id", "global"), + "cm": ("authorid", "file"), + "sheet": ("sheetid", "file"), + "definedname": ("id", "file"), + "cxnsp": ("id", "file"), + "sp": ("id", "file"), + "pic": ("id", "file"), + "grpsp": ("id", "file"), + } + + EXCLUDED_ID_CONTAINERS = { + "sectionlst", + } + + ELEMENT_RELATIONSHIP_TYPES = {} + + SCHEMA_MAPPINGS = { + "word": "ISO-IEC29500-4_2016/wml.xsd", + "ppt": "ISO-IEC29500-4_2016/pml.xsd", + "xl": "ISO-IEC29500-4_2016/sml.xsd", + "[Content_Types].xml": "ecma/fouth-edition/opc-contentTypes.xsd", + "app.xml": "ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd", + "core.xml": "ecma/fouth-edition/opc-coreProperties.xsd", + "custom.xml": "ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd", + ".rels": "ecma/fouth-edition/opc-relationships.xsd", + "people.xml": "microsoft/wml-2012.xsd", + "commentsIds.xml": "microsoft/wml-cid-2016.xsd", + "commentsExtensible.xml": "microsoft/wml-cex-2018.xsd", + "commentsExtended.xml": "microsoft/wml-2012.xsd", + "chart": "ISO-IEC29500-4_2016/dml-chart.xsd", + "theme": "ISO-IEC29500-4_2016/dml-main.xsd", + "drawing": "ISO-IEC29500-4_2016/dml-main.xsd", + } + + MC_NAMESPACE = "http://schemas.openxmlformats.org/markup-compatibility/2006" + XML_NAMESPACE = "http://www.w3.org/XML/1998/namespace" + + PACKAGE_RELATIONSHIPS_NAMESPACE = ( + "http://schemas.openxmlformats.org/package/2006/relationships" + ) + OFFICE_RELATIONSHIPS_NAMESPACE = ( + "http://schemas.openxmlformats.org/officeDocument/2006/relationships" + ) + CONTENT_TYPES_NAMESPACE = ( + "http://schemas.openxmlformats.org/package/2006/content-types" + ) + + MAIN_CONTENT_FOLDERS = {"word", "ppt", "xl"} + + OOXML_NAMESPACES = { + "http://schemas.openxmlformats.org/officeDocument/2006/math", + "http://schemas.openxmlformats.org/officeDocument/2006/relationships", + "http://schemas.openxmlformats.org/schemaLibrary/2006/main", + "http://schemas.openxmlformats.org/drawingml/2006/main", + "http://schemas.openxmlformats.org/drawingml/2006/chart", + "http://schemas.openxmlformats.org/drawingml/2006/chartDrawing", + "http://schemas.openxmlformats.org/drawingml/2006/diagram", + "http://schemas.openxmlformats.org/drawingml/2006/picture", + "http://schemas.openxmlformats.org/drawingml/2006/spreadsheetDrawing", + "http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing", + "http://schemas.openxmlformats.org/wordprocessingml/2006/main", + "http://schemas.openxmlformats.org/presentationml/2006/main", + "http://schemas.openxmlformats.org/spreadsheetml/2006/main", + "http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes", + "http://www.w3.org/XML/1998/namespace", + } + + def __init__(self, unpacked_dir, original_file=None, verbose=False): + self.unpacked_dir = Path(unpacked_dir).resolve() + self.original_file = Path(original_file) if original_file else None + self.verbose = verbose + + self.schemas_dir = Path(__file__).parent.parent / "schemas" + + patterns = ["*.xml", "*.rels"] + self.xml_files = [ + f for pattern in patterns for f in self.unpacked_dir.rglob(pattern) + ] + + if not self.xml_files: + print(f"Warning: No XML files found in {self.unpacked_dir}") + + def validate(self): + raise NotImplementedError("Subclasses must implement the validate method") + + def repair(self) -> int: + return self.repair_whitespace_preservation() + + def repair_whitespace_preservation(self) -> int: + repairs = 0 + + for xml_file in self.xml_files: + try: + content = xml_file.read_text(encoding="utf-8") + dom = defusedxml.minidom.parseString(content) + modified = False + + for elem in dom.getElementsByTagName("*"): + if elem.tagName.endswith(":t") and elem.firstChild: + text = elem.firstChild.nodeValue + if text and (text.startswith((' ', '\t')) or text.endswith((' ', '\t'))): + if elem.getAttribute("xml:space") != "preserve": + elem.setAttribute("xml:space", "preserve") + text_preview = repr(text[:30]) + "..." if len(text) > 30 else repr(text) + print(f" Repaired: {xml_file.name}: Added xml:space='preserve' to {elem.tagName}: {text_preview}") + repairs += 1 + modified = True + + if modified: + xml_file.write_bytes(dom.toxml(encoding="UTF-8")) + + except Exception: + pass + + return repairs + + def validate_xml(self): + errors = [] + + for xml_file in self.xml_files: + try: + lxml.etree.parse(str(xml_file)) + except lxml.etree.XMLSyntaxError as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {e.lineno}: {e.msg}" + ) + except Exception as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Unexpected error: {str(e)}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} XML violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All XML files are well-formed") + return True + + def validate_namespaces(self): + errors = [] + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + declared = set(root.nsmap.keys()) - {None} + + for attr_val in [ + v for k, v in root.attrib.items() if k.endswith("Ignorable") + ]: + undeclared = set(attr_val.split()) - declared + errors.extend( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Namespace '{ns}' in Ignorable but not declared" + for ns in undeclared + ) + except lxml.etree.XMLSyntaxError: + continue + + if errors: + print(f"FAILED - {len(errors)} namespace issues:") + for error in errors: + print(error) + return False + if self.verbose: + print("PASSED - All namespace prefixes properly declared") + return True + + def validate_unique_ids(self): + errors = [] + global_ids = {} + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + file_ids = {} + + mc_elements = root.xpath( + ".//mc:AlternateContent", namespaces={"mc": self.MC_NAMESPACE} + ) + for elem in mc_elements: + elem.getparent().remove(elem) + + for elem in root.iter(): + tag = ( + elem.tag.split("}")[-1].lower() + if "}" in elem.tag + else elem.tag.lower() + ) + + if tag in self.UNIQUE_ID_REQUIREMENTS: + in_excluded_container = any( + ancestor.tag.split("}")[-1].lower() in self.EXCLUDED_ID_CONTAINERS + for ancestor in elem.iterancestors() + ) + if in_excluded_container: + continue + + attr_name, scope = self.UNIQUE_ID_REQUIREMENTS[tag] + + id_value = None + for attr, value in elem.attrib.items(): + attr_local = ( + attr.split("}")[-1].lower() + if "}" in attr + else attr.lower() + ) + if attr_local == attr_name: + id_value = value + break + + if id_value is not None: + if scope == "global": + if id_value in global_ids: + prev_file, prev_line, prev_tag = global_ids[ + id_value + ] + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: Global ID '{id_value}' in <{tag}> " + f"already used in {prev_file} at line {prev_line} in <{prev_tag}>" + ) + else: + global_ids[id_value] = ( + xml_file.relative_to(self.unpacked_dir), + elem.sourceline, + tag, + ) + elif scope == "file": + key = (tag, attr_name) + if key not in file_ids: + file_ids[key] = {} + + if id_value in file_ids[key]: + prev_line = file_ids[key][id_value] + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: Duplicate {attr_name}='{id_value}' in <{tag}> " + f"(first occurrence at line {prev_line})" + ) + else: + file_ids[key][id_value] = elem.sourceline + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} ID uniqueness violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All required IDs are unique") + return True + + def validate_file_references(self): + errors = [] + + rels_files = list(self.unpacked_dir.rglob("*.rels")) + + if not rels_files: + if self.verbose: + print("PASSED - No .rels files found") + return True + + all_files = [] + for file_path in self.unpacked_dir.rglob("*"): + if ( + file_path.is_file() + and file_path.name != "[Content_Types].xml" + and not file_path.name.endswith(".rels") + ): + all_files.append(file_path.resolve()) + + all_referenced_files = set() + + if self.verbose: + print( + f"Found {len(rels_files)} .rels files and {len(all_files)} target files" + ) + + for rels_file in rels_files: + try: + rels_root = lxml.etree.parse(str(rels_file)).getroot() + + rels_dir = rels_file.parent + + referenced_files = set() + broken_refs = [] + + for rel in rels_root.findall( + ".//ns:Relationship", + namespaces={"ns": self.PACKAGE_RELATIONSHIPS_NAMESPACE}, + ): + target = rel.get("Target") + if target and not target.startswith( + ("http", "mailto:") + ): + if target.startswith("/"): + target_path = self.unpacked_dir / target.lstrip("/") + elif rels_file.name == ".rels": + target_path = self.unpacked_dir / target + else: + base_dir = rels_dir.parent + target_path = base_dir / target + + try: + target_path = target_path.resolve() + if target_path.exists() and target_path.is_file(): + referenced_files.add(target_path) + all_referenced_files.add(target_path) + else: + broken_refs.append((target, rel.sourceline)) + except (OSError, ValueError): + broken_refs.append((target, rel.sourceline)) + + if broken_refs: + rel_path = rels_file.relative_to(self.unpacked_dir) + for broken_ref, line_num in broken_refs: + errors.append( + f" {rel_path}: Line {line_num}: Broken reference to {broken_ref}" + ) + + except Exception as e: + rel_path = rels_file.relative_to(self.unpacked_dir) + errors.append(f" Error parsing {rel_path}: {e}") + + unreferenced_files = set(all_files) - all_referenced_files + + if unreferenced_files: + for unref_file in sorted(unreferenced_files): + unref_rel_path = unref_file.relative_to(self.unpacked_dir) + errors.append(f" Unreferenced file: {unref_rel_path}") + + if errors: + print(f"FAILED - Found {len(errors)} relationship validation errors:") + for error in errors: + print(error) + print( + "CRITICAL: These errors will cause the document to appear corrupt. " + + "Broken references MUST be fixed, " + + "and unreferenced files MUST be referenced or removed." + ) + return False + else: + if self.verbose: + print( + "PASSED - All references are valid and all files are properly referenced" + ) + return True + + def validate_all_relationship_ids(self): + import lxml.etree + + errors = [] + + for xml_file in self.xml_files: + if xml_file.suffix == ".rels": + continue + + rels_dir = xml_file.parent / "_rels" + rels_file = rels_dir / f"{xml_file.name}.rels" + + if not rels_file.exists(): + continue + + try: + rels_root = lxml.etree.parse(str(rels_file)).getroot() + rid_to_type = {} + + for rel in rels_root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rid = rel.get("Id") + rel_type = rel.get("Type", "") + if rid: + if rid in rid_to_type: + rels_rel_path = rels_file.relative_to(self.unpacked_dir) + errors.append( + f" {rels_rel_path}: Line {rel.sourceline}: " + f"Duplicate relationship ID '{rid}' (IDs must be unique)" + ) + type_name = ( + rel_type.split("/")[-1] if "/" in rel_type else rel_type + ) + rid_to_type[rid] = type_name + + xml_root = lxml.etree.parse(str(xml_file)).getroot() + + r_ns = self.OFFICE_RELATIONSHIPS_NAMESPACE + rid_attrs_to_check = ["id", "embed", "link"] + for elem in xml_root.iter(): + for attr_name in rid_attrs_to_check: + rid_attr = elem.get(f"{{{r_ns}}}{attr_name}") + if not rid_attr: + continue + xml_rel_path = xml_file.relative_to(self.unpacked_dir) + elem_name = ( + elem.tag.split("}")[-1] if "}" in elem.tag else elem.tag + ) + + if rid_attr not in rid_to_type: + errors.append( + f" {xml_rel_path}: Line {elem.sourceline}: " + f"<{elem_name}> r:{attr_name} references non-existent relationship '{rid_attr}' " + f"(valid IDs: {', '.join(sorted(rid_to_type.keys())[:5])}{'...' if len(rid_to_type) > 5 else ''})" + ) + elif attr_name == "id" and self.ELEMENT_RELATIONSHIP_TYPES: + expected_type = self._get_expected_relationship_type( + elem_name + ) + if expected_type: + actual_type = rid_to_type[rid_attr] + if expected_type not in actual_type.lower(): + errors.append( + f" {xml_rel_path}: Line {elem.sourceline}: " + f"<{elem_name}> references '{rid_attr}' which points to '{actual_type}' " + f"but should point to a '{expected_type}' relationship" + ) + + except Exception as e: + xml_rel_path = xml_file.relative_to(self.unpacked_dir) + errors.append(f" Error processing {xml_rel_path}: {e}") + + if errors: + print(f"FAILED - Found {len(errors)} relationship ID reference errors:") + for error in errors: + print(error) + print("\nThese ID mismatches will cause the document to appear corrupt!") + return False + else: + if self.verbose: + print("PASSED - All relationship ID references are valid") + return True + + def _get_expected_relationship_type(self, element_name): + elem_lower = element_name.lower() + + if elem_lower in self.ELEMENT_RELATIONSHIP_TYPES: + return self.ELEMENT_RELATIONSHIP_TYPES[elem_lower] + + if elem_lower.endswith("id") and len(elem_lower) > 2: + prefix = elem_lower[:-2] + if prefix.endswith("master"): + return prefix.lower() + elif prefix.endswith("layout"): + return prefix.lower() + else: + if prefix == "sld": + return "slide" + return prefix.lower() + + if elem_lower.endswith("reference") and len(elem_lower) > 9: + prefix = elem_lower[:-9] + return prefix.lower() + + return None + + def validate_content_types(self): + errors = [] + + content_types_file = self.unpacked_dir / "[Content_Types].xml" + if not content_types_file.exists(): + print("FAILED - [Content_Types].xml file not found") + return False + + try: + root = lxml.etree.parse(str(content_types_file)).getroot() + declared_parts = set() + declared_extensions = set() + + for override in root.findall( + f".//{{{self.CONTENT_TYPES_NAMESPACE}}}Override" + ): + part_name = override.get("PartName") + if part_name is not None: + declared_parts.add(part_name.lstrip("/")) + + for default in root.findall( + f".//{{{self.CONTENT_TYPES_NAMESPACE}}}Default" + ): + extension = default.get("Extension") + if extension is not None: + declared_extensions.add(extension.lower()) + + declarable_roots = { + "sld", + "sldLayout", + "sldMaster", + "presentation", + "document", + "workbook", + "worksheet", + "theme", + } + + media_extensions = { + "png": "image/png", + "jpg": "image/jpeg", + "jpeg": "image/jpeg", + "gif": "image/gif", + "bmp": "image/bmp", + "tiff": "image/tiff", + "wmf": "image/x-wmf", + "emf": "image/x-emf", + } + + all_files = list(self.unpacked_dir.rglob("*")) + all_files = [f for f in all_files if f.is_file()] + + for xml_file in self.xml_files: + path_str = str(xml_file.relative_to(self.unpacked_dir)).replace( + "\\", "/" + ) + + if any( + skip in path_str + for skip in [".rels", "[Content_Types]", "docProps/", "_rels/"] + ): + continue + + try: + root_tag = lxml.etree.parse(str(xml_file)).getroot().tag + root_name = root_tag.split("}")[-1] if "}" in root_tag else root_tag + + if root_name in declarable_roots and path_str not in declared_parts: + errors.append( + f" {path_str}: File with <{root_name}> root not declared in [Content_Types].xml" + ) + + except Exception: + continue + + for file_path in all_files: + if file_path.suffix.lower() in {".xml", ".rels"}: + continue + if file_path.name == "[Content_Types].xml": + continue + if "_rels" in file_path.parts or "docProps" in file_path.parts: + continue + + extension = file_path.suffix.lstrip(".").lower() + if extension and extension not in declared_extensions: + if extension in media_extensions: + relative_path = file_path.relative_to(self.unpacked_dir) + errors.append( + f' {relative_path}: File with extension \'{extension}\' not declared in [Content_Types].xml - should add: ' + ) + + except Exception as e: + errors.append(f" Error parsing [Content_Types].xml: {e}") + + if errors: + print(f"FAILED - Found {len(errors)} content type declaration errors:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print( + "PASSED - All content files are properly declared in [Content_Types].xml" + ) + return True + + def validate_file_against_xsd(self, xml_file, verbose=False): + xml_file = Path(xml_file).resolve() + unpacked_dir = self.unpacked_dir.resolve() + + is_valid, current_errors = self._validate_single_file_xsd( + xml_file, unpacked_dir + ) + + if is_valid is None: + return None, set() + elif is_valid: + return True, set() + + original_errors = self._get_original_file_errors(xml_file) + + assert current_errors is not None + new_errors = current_errors - original_errors + + new_errors = { + e for e in new_errors + if not any(pattern in e for pattern in self.IGNORED_VALIDATION_ERRORS) + } + + if new_errors: + if verbose: + relative_path = xml_file.relative_to(unpacked_dir) + print(f"FAILED - {relative_path}: {len(new_errors)} new error(s)") + for error in list(new_errors)[:3]: + truncated = error[:250] + "..." if len(error) > 250 else error + print(f" - {truncated}") + return False, new_errors + else: + if verbose: + print( + f"PASSED - No new errors (original had {len(current_errors)} errors)" + ) + return True, set() + + def validate_against_xsd(self): + new_errors = [] + original_error_count = 0 + valid_count = 0 + skipped_count = 0 + + for xml_file in self.xml_files: + relative_path = str(xml_file.relative_to(self.unpacked_dir)) + is_valid, new_file_errors = self.validate_file_against_xsd( + xml_file, verbose=False + ) + + if is_valid is None: + skipped_count += 1 + continue + elif is_valid and not new_file_errors: + valid_count += 1 + continue + elif is_valid: + original_error_count += 1 + valid_count += 1 + continue + + new_errors.append(f" {relative_path}: {len(new_file_errors)} new error(s)") + for error in list(new_file_errors)[:3]: + new_errors.append( + f" - {error[:250]}..." if len(error) > 250 else f" - {error}" + ) + + if self.verbose: + print(f"Validated {len(self.xml_files)} files:") + print(f" - Valid: {valid_count}") + print(f" - Skipped (no schema): {skipped_count}") + if original_error_count: + print(f" - With original errors (ignored): {original_error_count}") + print( + f" - With NEW errors: {len(new_errors) > 0 and len([e for e in new_errors if not e.startswith(' ')]) or 0}" + ) + + if new_errors: + print("\nFAILED - Found NEW validation errors:") + for error in new_errors: + print(error) + return False + else: + if self.verbose: + print("\nPASSED - No new XSD validation errors introduced") + return True + + def _get_schema_path(self, xml_file): + if xml_file.name in self.SCHEMA_MAPPINGS: + return self.schemas_dir / self.SCHEMA_MAPPINGS[xml_file.name] + + if xml_file.suffix == ".rels": + return self.schemas_dir / self.SCHEMA_MAPPINGS[".rels"] + + if "charts/" in str(xml_file) and xml_file.name.startswith("chart"): + return self.schemas_dir / self.SCHEMA_MAPPINGS["chart"] + + if "theme/" in str(xml_file) and xml_file.name.startswith("theme"): + return self.schemas_dir / self.SCHEMA_MAPPINGS["theme"] + + if xml_file.parent.name in self.MAIN_CONTENT_FOLDERS: + return self.schemas_dir / self.SCHEMA_MAPPINGS[xml_file.parent.name] + + return None + + def _clean_ignorable_namespaces(self, xml_doc): + xml_string = lxml.etree.tostring(xml_doc, encoding="unicode") + xml_copy = lxml.etree.fromstring(xml_string) + + for elem in xml_copy.iter(): + attrs_to_remove = [] + + for attr in elem.attrib: + if "{" in attr: + ns = attr.split("}")[0][1:] + if ns not in self.OOXML_NAMESPACES: + attrs_to_remove.append(attr) + + for attr in attrs_to_remove: + del elem.attrib[attr] + + self._remove_ignorable_elements(xml_copy) + + return lxml.etree.ElementTree(xml_copy) + + def _remove_ignorable_elements(self, root): + elements_to_remove = [] + + for elem in list(root): + if not hasattr(elem, "tag") or callable(elem.tag): + continue + + tag_str = str(elem.tag) + if tag_str.startswith("{"): + ns = tag_str.split("}")[0][1:] + if ns not in self.OOXML_NAMESPACES: + elements_to_remove.append(elem) + continue + + self._remove_ignorable_elements(elem) + + for elem in elements_to_remove: + root.remove(elem) + + def _preprocess_for_mc_ignorable(self, xml_doc): + root = xml_doc.getroot() + + if f"{{{self.MC_NAMESPACE}}}Ignorable" in root.attrib: + del root.attrib[f"{{{self.MC_NAMESPACE}}}Ignorable"] + + return xml_doc + + def _validate_single_file_xsd(self, xml_file, base_path): + schema_path = self._get_schema_path(xml_file) + if not schema_path: + return None, None + + try: + with open(schema_path, "rb") as xsd_file: + parser = lxml.etree.XMLParser() + xsd_doc = lxml.etree.parse( + xsd_file, parser=parser, base_url=str(schema_path) + ) + schema = lxml.etree.XMLSchema(xsd_doc) + + with open(xml_file, "r") as f: + xml_doc = lxml.etree.parse(f) + + xml_doc, _ = self._remove_template_tags_from_text_nodes(xml_doc) + xml_doc = self._preprocess_for_mc_ignorable(xml_doc) + + relative_path = xml_file.relative_to(base_path) + if ( + relative_path.parts + and relative_path.parts[0] in self.MAIN_CONTENT_FOLDERS + ): + xml_doc = self._clean_ignorable_namespaces(xml_doc) + + if schema.validate(xml_doc): + return True, set() + else: + errors = set() + for error in schema.error_log: + errors.add(error.message) + return False, errors + + except Exception as e: + return False, {str(e)} + + def _get_original_file_errors(self, xml_file): + if self.original_file is None: + return set() + + import tempfile + import zipfile + + xml_file = Path(xml_file).resolve() + unpacked_dir = self.unpacked_dir.resolve() + relative_path = xml_file.relative_to(unpacked_dir) + + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + with zipfile.ZipFile(self.original_file, "r") as zip_ref: + zip_ref.extractall(temp_path) + + original_xml_file = temp_path / relative_path + + if not original_xml_file.exists(): + return set() + + is_valid, errors = self._validate_single_file_xsd( + original_xml_file, temp_path + ) + return errors if errors else set() + + def _remove_template_tags_from_text_nodes(self, xml_doc): + warnings = [] + template_pattern = re.compile(r"\{\{[^}]*\}\}") + + xml_string = lxml.etree.tostring(xml_doc, encoding="unicode") + xml_copy = lxml.etree.fromstring(xml_string) + + def process_text_content(text, content_type): + if not text: + return text + matches = list(template_pattern.finditer(text)) + if matches: + for match in matches: + warnings.append( + f"Found template tag in {content_type}: {match.group()}" + ) + return template_pattern.sub("", text) + return text + + for elem in xml_copy.iter(): + if not hasattr(elem, "tag") or callable(elem.tag): + continue + tag_str = str(elem.tag) + if tag_str.endswith("}t") or tag_str == "t": + continue + + elem.text = process_text_content(elem.text, "text content") + elem.tail = process_text_content(elem.tail, "tail content") + + return lxml.etree.ElementTree(xml_copy), warnings + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/.claude/skills/docx/scripts/office/validators/docx.py b/.claude/skills/docx/scripts/office/validators/docx.py new file mode 100644 index 0000000..fec405e --- /dev/null +++ b/.claude/skills/docx/scripts/office/validators/docx.py @@ -0,0 +1,446 @@ +""" +Validator for Word document XML files against XSD schemas. +""" + +import random +import re +import tempfile +import zipfile + +import defusedxml.minidom +import lxml.etree + +from .base import BaseSchemaValidator + + +class DOCXSchemaValidator(BaseSchemaValidator): + + WORD_2006_NAMESPACE = "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + W14_NAMESPACE = "http://schemas.microsoft.com/office/word/2010/wordml" + W16CID_NAMESPACE = "http://schemas.microsoft.com/office/word/2016/wordml/cid" + + ELEMENT_RELATIONSHIP_TYPES = {} + + def validate(self): + if not self.validate_xml(): + return False + + all_valid = True + if not self.validate_namespaces(): + all_valid = False + + if not self.validate_unique_ids(): + all_valid = False + + if not self.validate_file_references(): + all_valid = False + + if not self.validate_content_types(): + all_valid = False + + if not self.validate_against_xsd(): + all_valid = False + + if not self.validate_whitespace_preservation(): + all_valid = False + + if not self.validate_deletions(): + all_valid = False + + if not self.validate_insertions(): + all_valid = False + + if not self.validate_all_relationship_ids(): + all_valid = False + + if not self.validate_id_constraints(): + all_valid = False + + if not self.validate_comment_markers(): + all_valid = False + + self.compare_paragraph_counts() + + return all_valid + + def validate_whitespace_preservation(self): + errors = [] + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + + for elem in root.iter(f"{{{self.WORD_2006_NAMESPACE}}}t"): + if elem.text: + text = elem.text + if re.search(r"^[ \t\n\r]", text) or re.search( + r"[ \t\n\r]$", text + ): + xml_space_attr = f"{{{self.XML_NAMESPACE}}}space" + if ( + xml_space_attr not in elem.attrib + or elem.attrib[xml_space_attr] != "preserve" + ): + text_preview = ( + repr(text)[:50] + "..." + if len(repr(text)) > 50 + else repr(text) + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: w:t element with whitespace missing xml:space='preserve': {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} whitespace preservation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All whitespace is properly preserved") + return True + + def validate_deletions(self): + errors = [] + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + namespaces = {"w": self.WORD_2006_NAMESPACE} + + for t_elem in root.xpath(".//w:del//w:t", namespaces=namespaces): + if t_elem.text: + text_preview = ( + repr(t_elem.text)[:50] + "..." + if len(repr(t_elem.text)) > 50 + else repr(t_elem.text) + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {t_elem.sourceline}: found within : {text_preview}" + ) + + for instr_elem in root.xpath( + ".//w:del//w:instrText", namespaces=namespaces + ): + text_preview = ( + repr(instr_elem.text or "")[:50] + "..." + if len(repr(instr_elem.text or "")) > 50 + else repr(instr_elem.text or "") + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {instr_elem.sourceline}: found within (use ): {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} deletion validation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - No w:t elements found within w:del elements") + return True + + def count_paragraphs_in_unpacked(self): + count = 0 + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + paragraphs = root.findall(f".//{{{self.WORD_2006_NAMESPACE}}}p") + count = len(paragraphs) + except Exception as e: + print(f"Error counting paragraphs in unpacked document: {e}") + + return count + + def count_paragraphs_in_original(self): + original = self.original_file + if original is None: + return 0 + + count = 0 + + try: + with tempfile.TemporaryDirectory() as temp_dir: + with zipfile.ZipFile(original, "r") as zip_ref: + zip_ref.extractall(temp_dir) + + doc_xml_path = temp_dir + "/word/document.xml" + root = lxml.etree.parse(doc_xml_path).getroot() + + paragraphs = root.findall(f".//{{{self.WORD_2006_NAMESPACE}}}p") + count = len(paragraphs) + + except Exception as e: + print(f"Error counting paragraphs in original document: {e}") + + return count + + def validate_insertions(self): + errors = [] + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + namespaces = {"w": self.WORD_2006_NAMESPACE} + + invalid_elements = root.xpath( + ".//w:ins//w:delText[not(ancestor::w:del)]", namespaces=namespaces + ) + + for elem in invalid_elements: + text_preview = ( + repr(elem.text or "")[:50] + "..." + if len(repr(elem.text or "")) > 50 + else repr(elem.text or "") + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: within : {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} insertion validation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - No w:delText elements within w:ins elements") + return True + + def compare_paragraph_counts(self): + original_count = self.count_paragraphs_in_original() + new_count = self.count_paragraphs_in_unpacked() + + diff = new_count - original_count + diff_str = f"+{diff}" if diff > 0 else str(diff) + print(f"\nParagraphs: {original_count} → {new_count} ({diff_str})") + + def _parse_id_value(self, val: str, base: int = 16) -> int: + return int(val, base) + + def validate_id_constraints(self): + errors = [] + para_id_attr = f"{{{self.W14_NAMESPACE}}}paraId" + durable_id_attr = f"{{{self.W16CID_NAMESPACE}}}durableId" + + for xml_file in self.xml_files: + try: + for elem in lxml.etree.parse(str(xml_file)).iter(): + if val := elem.get(para_id_attr): + if self._parse_id_value(val, base=16) >= 0x80000000: + errors.append( + f" {xml_file.name}:{elem.sourceline}: paraId={val} >= 0x80000000" + ) + + if val := elem.get(durable_id_attr): + if xml_file.name == "numbering.xml": + try: + if self._parse_id_value(val, base=10) >= 0x7FFFFFFF: + errors.append( + f" {xml_file.name}:{elem.sourceline}: " + f"durableId={val} >= 0x7FFFFFFF" + ) + except ValueError: + errors.append( + f" {xml_file.name}:{elem.sourceline}: " + f"durableId={val} must be decimal in numbering.xml" + ) + else: + if self._parse_id_value(val, base=16) >= 0x7FFFFFFF: + errors.append( + f" {xml_file.name}:{elem.sourceline}: " + f"durableId={val} >= 0x7FFFFFFF" + ) + except Exception: + pass + + if errors: + print(f"FAILED - {len(errors)} ID constraint violations:") + for e in errors: + print(e) + elif self.verbose: + print("PASSED - All paraId/durableId values within constraints") + return not errors + + def validate_comment_markers(self): + errors = [] + + document_xml = None + comments_xml = None + for xml_file in self.xml_files: + if xml_file.name == "document.xml" and "word" in str(xml_file): + document_xml = xml_file + elif xml_file.name == "comments.xml": + comments_xml = xml_file + + if not document_xml: + if self.verbose: + print("PASSED - No document.xml found (skipping comment validation)") + return True + + try: + doc_root = lxml.etree.parse(str(document_xml)).getroot() + namespaces = {"w": self.WORD_2006_NAMESPACE} + + range_starts = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in doc_root.xpath( + ".//w:commentRangeStart", namespaces=namespaces + ) + } + range_ends = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in doc_root.xpath( + ".//w:commentRangeEnd", namespaces=namespaces + ) + } + references = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in doc_root.xpath( + ".//w:commentReference", namespaces=namespaces + ) + } + + orphaned_ends = range_ends - range_starts + for comment_id in sorted( + orphaned_ends, key=lambda x: int(x) if x and x.isdigit() else 0 + ): + errors.append( + f' document.xml: commentRangeEnd id="{comment_id}" has no matching commentRangeStart' + ) + + orphaned_starts = range_starts - range_ends + for comment_id in sorted( + orphaned_starts, key=lambda x: int(x) if x and x.isdigit() else 0 + ): + errors.append( + f' document.xml: commentRangeStart id="{comment_id}" has no matching commentRangeEnd' + ) + + comment_ids = set() + if comments_xml and comments_xml.exists(): + comments_root = lxml.etree.parse(str(comments_xml)).getroot() + comment_ids = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in comments_root.xpath( + ".//w:comment", namespaces=namespaces + ) + } + + marker_ids = range_starts | range_ends | references + invalid_refs = marker_ids - comment_ids + for comment_id in sorted( + invalid_refs, key=lambda x: int(x) if x and x.isdigit() else 0 + ): + if comment_id: + errors.append( + f' document.xml: marker id="{comment_id}" references non-existent comment' + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append(f" Error parsing XML: {e}") + + if errors: + print(f"FAILED - {len(errors)} comment marker violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All comment markers properly paired") + return True + + def repair(self) -> int: + repairs = super().repair() + repairs += self.repair_durableId() + return repairs + + def repair_durableId(self) -> int: + repairs = 0 + + for xml_file in self.xml_files: + try: + content = xml_file.read_text(encoding="utf-8") + dom = defusedxml.minidom.parseString(content) + modified = False + + for elem in dom.getElementsByTagName("*"): + if not elem.hasAttribute("w16cid:durableId"): + continue + + durable_id = elem.getAttribute("w16cid:durableId") + needs_repair = False + + if xml_file.name == "numbering.xml": + try: + needs_repair = ( + self._parse_id_value(durable_id, base=10) >= 0x7FFFFFFF + ) + except ValueError: + needs_repair = True + else: + try: + needs_repair = ( + self._parse_id_value(durable_id, base=16) >= 0x7FFFFFFF + ) + except ValueError: + needs_repair = True + + if needs_repair: + value = random.randint(1, 0x7FFFFFFE) + if xml_file.name == "numbering.xml": + new_id = str(value) + else: + new_id = f"{value:08X}" + + elem.setAttribute("w16cid:durableId", new_id) + print( + f" Repaired: {xml_file.name}: durableId {durable_id} → {new_id}" + ) + repairs += 1 + modified = True + + if modified: + xml_file.write_bytes(dom.toxml(encoding="UTF-8")) + + except Exception: + pass + + return repairs + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/.claude/skills/docx/scripts/office/validators/pptx.py b/.claude/skills/docx/scripts/office/validators/pptx.py new file mode 100644 index 0000000..09842aa --- /dev/null +++ b/.claude/skills/docx/scripts/office/validators/pptx.py @@ -0,0 +1,275 @@ +""" +Validator for PowerPoint presentation XML files against XSD schemas. +""" + +import re + +from .base import BaseSchemaValidator + + +class PPTXSchemaValidator(BaseSchemaValidator): + + PRESENTATIONML_NAMESPACE = ( + "http://schemas.openxmlformats.org/presentationml/2006/main" + ) + + ELEMENT_RELATIONSHIP_TYPES = { + "sldid": "slide", + "sldmasterid": "slidemaster", + "notesmasterid": "notesmaster", + "sldlayoutid": "slidelayout", + "themeid": "theme", + "tablestyleid": "tablestyles", + } + + def validate(self): + if not self.validate_xml(): + return False + + all_valid = True + if not self.validate_namespaces(): + all_valid = False + + if not self.validate_unique_ids(): + all_valid = False + + if not self.validate_uuid_ids(): + all_valid = False + + if not self.validate_file_references(): + all_valid = False + + if not self.validate_slide_layout_ids(): + all_valid = False + + if not self.validate_content_types(): + all_valid = False + + if not self.validate_against_xsd(): + all_valid = False + + if not self.validate_notes_slide_references(): + all_valid = False + + if not self.validate_all_relationship_ids(): + all_valid = False + + if not self.validate_no_duplicate_slide_layouts(): + all_valid = False + + return all_valid + + def validate_uuid_ids(self): + import lxml.etree + + errors = [] + uuid_pattern = re.compile( + r"^[\{\(]?[0-9A-Fa-f]{8}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{12}[\}\)]?$" + ) + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + + for elem in root.iter(): + for attr, value in elem.attrib.items(): + attr_name = attr.split("}")[-1].lower() + if attr_name == "id" or attr_name.endswith("id"): + if self._looks_like_uuid(value): + if not uuid_pattern.match(value): + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: ID '{value}' appears to be a UUID but contains invalid hex characters" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} UUID ID validation errors:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All UUID-like IDs contain valid hex values") + return True + + def _looks_like_uuid(self, value): + clean_value = value.strip("{}()").replace("-", "") + return len(clean_value) == 32 and all(c.isalnum() for c in clean_value) + + def validate_slide_layout_ids(self): + import lxml.etree + + errors = [] + + slide_masters = list(self.unpacked_dir.glob("ppt/slideMasters/*.xml")) + + if not slide_masters: + if self.verbose: + print("PASSED - No slide masters found") + return True + + for slide_master in slide_masters: + try: + root = lxml.etree.parse(str(slide_master)).getroot() + + rels_file = slide_master.parent / "_rels" / f"{slide_master.name}.rels" + + if not rels_file.exists(): + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: " + f"Missing relationships file: {rels_file.relative_to(self.unpacked_dir)}" + ) + continue + + rels_root = lxml.etree.parse(str(rels_file)).getroot() + + valid_layout_rids = set() + for rel in rels_root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rel_type = rel.get("Type", "") + if "slideLayout" in rel_type: + valid_layout_rids.add(rel.get("Id")) + + for sld_layout_id in root.findall( + f".//{{{self.PRESENTATIONML_NAMESPACE}}}sldLayoutId" + ): + r_id = sld_layout_id.get( + f"{{{self.OFFICE_RELATIONSHIPS_NAMESPACE}}}id" + ) + layout_id = sld_layout_id.get("id") + + if r_id and r_id not in valid_layout_rids: + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: " + f"Line {sld_layout_id.sourceline}: sldLayoutId with id='{layout_id}' " + f"references r:id='{r_id}' which is not found in slide layout relationships" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} slide layout ID validation errors:") + for error in errors: + print(error) + print( + "Remove invalid references or add missing slide layouts to the relationships file." + ) + return False + else: + if self.verbose: + print("PASSED - All slide layout IDs reference valid slide layouts") + return True + + def validate_no_duplicate_slide_layouts(self): + import lxml.etree + + errors = [] + slide_rels_files = list(self.unpacked_dir.glob("ppt/slides/_rels/*.xml.rels")) + + for rels_file in slide_rels_files: + try: + root = lxml.etree.parse(str(rels_file)).getroot() + + layout_rels = [ + rel + for rel in root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ) + if "slideLayout" in rel.get("Type", "") + ] + + if len(layout_rels) > 1: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: has {len(layout_rels)} slideLayout references" + ) + + except Exception as e: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print("FAILED - Found slides with duplicate slideLayout references:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All slides have exactly one slideLayout reference") + return True + + def validate_notes_slide_references(self): + import lxml.etree + + errors = [] + notes_slide_references = {} + + slide_rels_files = list(self.unpacked_dir.glob("ppt/slides/_rels/*.xml.rels")) + + if not slide_rels_files: + if self.verbose: + print("PASSED - No slide relationship files found") + return True + + for rels_file in slide_rels_files: + try: + root = lxml.etree.parse(str(rels_file)).getroot() + + for rel in root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rel_type = rel.get("Type", "") + if "notesSlide" in rel_type: + target = rel.get("Target", "") + if target: + normalized_target = target.replace("../", "") + + slide_name = rels_file.stem.replace( + ".xml", "" + ) + + if normalized_target not in notes_slide_references: + notes_slide_references[normalized_target] = [] + notes_slide_references[normalized_target].append( + (slide_name, rels_file) + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + for target, references in notes_slide_references.items(): + if len(references) > 1: + slide_names = [ref[0] for ref in references] + errors.append( + f" Notes slide '{target}' is referenced by multiple slides: {', '.join(slide_names)}" + ) + for slide_name, rels_file in references: + errors.append(f" - {rels_file.relative_to(self.unpacked_dir)}") + + if errors: + print( + f"FAILED - Found {len([e for e in errors if not e.startswith(' ')])} notes slide reference validation errors:" + ) + for error in errors: + print(error) + print("Each slide may optionally have its own slide file.") + return False + else: + if self.verbose: + print("PASSED - All notes slide references are unique") + return True + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/.claude/skills/docx/scripts/office/validators/redlining.py b/.claude/skills/docx/scripts/office/validators/redlining.py new file mode 100644 index 0000000..71c81b6 --- /dev/null +++ b/.claude/skills/docx/scripts/office/validators/redlining.py @@ -0,0 +1,247 @@ +""" +Validator for tracked changes in Word documents. +""" + +import subprocess +import tempfile +import zipfile +from pathlib import Path + + +class RedliningValidator: + + def __init__(self, unpacked_dir, original_docx, verbose=False, author="Claude"): + self.unpacked_dir = Path(unpacked_dir) + self.original_docx = Path(original_docx) + self.verbose = verbose + self.author = author + self.namespaces = { + "w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + } + + def repair(self) -> int: + return 0 + + def validate(self): + modified_file = self.unpacked_dir / "word" / "document.xml" + if not modified_file.exists(): + print(f"FAILED - Modified document.xml not found at {modified_file}") + return False + + try: + import xml.etree.ElementTree as ET + + tree = ET.parse(modified_file) + root = tree.getroot() + + del_elements = root.findall(".//w:del", self.namespaces) + ins_elements = root.findall(".//w:ins", self.namespaces) + + author_del_elements = [ + elem + for elem in del_elements + if elem.get(f"{{{self.namespaces['w']}}}author") == self.author + ] + author_ins_elements = [ + elem + for elem in ins_elements + if elem.get(f"{{{self.namespaces['w']}}}author") == self.author + ] + + if not author_del_elements and not author_ins_elements: + if self.verbose: + print(f"PASSED - No tracked changes by {self.author} found.") + return True + + except Exception: + pass + + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + try: + with zipfile.ZipFile(self.original_docx, "r") as zip_ref: + zip_ref.extractall(temp_path) + except Exception as e: + print(f"FAILED - Error unpacking original docx: {e}") + return False + + original_file = temp_path / "word" / "document.xml" + if not original_file.exists(): + print( + f"FAILED - Original document.xml not found in {self.original_docx}" + ) + return False + + try: + import xml.etree.ElementTree as ET + + modified_tree = ET.parse(modified_file) + modified_root = modified_tree.getroot() + original_tree = ET.parse(original_file) + original_root = original_tree.getroot() + except ET.ParseError as e: + print(f"FAILED - Error parsing XML files: {e}") + return False + + self._remove_author_tracked_changes(original_root) + self._remove_author_tracked_changes(modified_root) + + modified_text = self._extract_text_content(modified_root) + original_text = self._extract_text_content(original_root) + + if modified_text != original_text: + error_message = self._generate_detailed_diff( + original_text, modified_text + ) + print(error_message) + return False + + if self.verbose: + print(f"PASSED - All changes by {self.author} are properly tracked") + return True + + def _generate_detailed_diff(self, original_text, modified_text): + error_parts = [ + f"FAILED - Document text doesn't match after removing {self.author}'s tracked changes", + "", + "Likely causes:", + " 1. Modified text inside another author's or tags", + " 2. Made edits without proper tracked changes", + " 3. Didn't nest inside when deleting another's insertion", + "", + "For pre-redlined documents, use correct patterns:", + " - To reject another's INSERTION: Nest inside their ", + " - To restore another's DELETION: Add new AFTER their ", + "", + ] + + git_diff = self._get_git_word_diff(original_text, modified_text) + if git_diff: + error_parts.extend(["Differences:", "============", git_diff]) + else: + error_parts.append("Unable to generate word diff (git not available)") + + return "\n".join(error_parts) + + def _get_git_word_diff(self, original_text, modified_text): + try: + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + original_file = temp_path / "original.txt" + modified_file = temp_path / "modified.txt" + + original_file.write_text(original_text, encoding="utf-8") + modified_file.write_text(modified_text, encoding="utf-8") + + result = subprocess.run( + [ + "git", + "diff", + "--word-diff=plain", + "--word-diff-regex=.", + "-U0", + "--no-index", + str(original_file), + str(modified_file), + ], + capture_output=True, + text=True, + ) + + if result.stdout.strip(): + lines = result.stdout.split("\n") + content_lines = [] + in_content = False + for line in lines: + if line.startswith("@@"): + in_content = True + continue + if in_content and line.strip(): + content_lines.append(line) + + if content_lines: + return "\n".join(content_lines) + + result = subprocess.run( + [ + "git", + "diff", + "--word-diff=plain", + "-U0", + "--no-index", + str(original_file), + str(modified_file), + ], + capture_output=True, + text=True, + ) + + if result.stdout.strip(): + lines = result.stdout.split("\n") + content_lines = [] + in_content = False + for line in lines: + if line.startswith("@@"): + in_content = True + continue + if in_content and line.strip(): + content_lines.append(line) + return "\n".join(content_lines) + + except (subprocess.CalledProcessError, FileNotFoundError, Exception): + pass + + return None + + def _remove_author_tracked_changes(self, root): + ins_tag = f"{{{self.namespaces['w']}}}ins" + del_tag = f"{{{self.namespaces['w']}}}del" + author_attr = f"{{{self.namespaces['w']}}}author" + + for parent in root.iter(): + to_remove = [] + for child in parent: + if child.tag == ins_tag and child.get(author_attr) == self.author: + to_remove.append(child) + for elem in to_remove: + parent.remove(elem) + + deltext_tag = f"{{{self.namespaces['w']}}}delText" + t_tag = f"{{{self.namespaces['w']}}}t" + + for parent in root.iter(): + to_process = [] + for child in parent: + if child.tag == del_tag and child.get(author_attr) == self.author: + to_process.append((child, list(parent).index(child))) + + for del_elem, del_index in reversed(to_process): + for elem in del_elem.iter(): + if elem.tag == deltext_tag: + elem.tag = t_tag + + for child in reversed(list(del_elem)): + parent.insert(del_index, child) + parent.remove(del_elem) + + def _extract_text_content(self, root): + p_tag = f"{{{self.namespaces['w']}}}p" + t_tag = f"{{{self.namespaces['w']}}}t" + + paragraphs = [] + for p_elem in root.findall(f".//{p_tag}"): + text_parts = [] + for t_elem in p_elem.findall(f".//{t_tag}"): + if t_elem.text: + text_parts.append(t_elem.text) + paragraph_text = "".join(text_parts) + if paragraph_text: + paragraphs.append(paragraph_text) + + return "\n".join(paragraphs) + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/.claude/skills/docx/scripts/templates/comments.xml b/.claude/skills/docx/scripts/templates/comments.xml new file mode 100644 index 0000000..cd01a7d --- /dev/null +++ b/.claude/skills/docx/scripts/templates/comments.xml @@ -0,0 +1,3 @@ + + + diff --git a/.claude/skills/docx/scripts/templates/commentsExtended.xml b/.claude/skills/docx/scripts/templates/commentsExtended.xml new file mode 100644 index 0000000..411003c --- /dev/null +++ b/.claude/skills/docx/scripts/templates/commentsExtended.xml @@ -0,0 +1,3 @@ + + + diff --git a/.claude/skills/docx/scripts/templates/commentsExtensible.xml b/.claude/skills/docx/scripts/templates/commentsExtensible.xml new file mode 100644 index 0000000..f5572d7 --- /dev/null +++ b/.claude/skills/docx/scripts/templates/commentsExtensible.xml @@ -0,0 +1,3 @@ + + + diff --git a/.claude/skills/docx/scripts/templates/commentsIds.xml b/.claude/skills/docx/scripts/templates/commentsIds.xml new file mode 100644 index 0000000..32f1629 --- /dev/null +++ b/.claude/skills/docx/scripts/templates/commentsIds.xml @@ -0,0 +1,3 @@ + + + diff --git a/.claude/skills/docx/scripts/templates/people.xml b/.claude/skills/docx/scripts/templates/people.xml new file mode 100644 index 0000000..3803d2d --- /dev/null +++ b/.claude/skills/docx/scripts/templates/people.xml @@ -0,0 +1,3 @@ + + + diff --git a/.claude/skills/mcp-admin-cleanup-node_modules/SKILL.md b/.claude/skills/mcp-admin-cleanup-node_modules/SKILL.md new file mode 100644 index 0000000..23b0cbc --- /dev/null +++ b/.claude/skills/mcp-admin-cleanup-node_modules/SKILL.md @@ -0,0 +1,121 @@ +--- +name: mcp-admin-cleanup-node_modules +description: 使用 D8D Admin MCP 工具清理模板或项目的 node_modules 目录，回收大量存储空间。当用户需要清理项目/模板的依赖以回收存储空间时触发。包括存储扫描、列出模板、查看详情、执行清理的完整流程。注意：仅限管理员用户（ID 1、6、26）使用。 +--- + +# node_modules 清理 + +完整的 node_modules 清理工作流程：**发现 → 定位 → 清理 → 验证**。 + +## ⚠️ NFS 异步删除延迟说明 + +**重要**：清理操作完成后，立即用 `ls` 命令检查可能会发现目录仍然存在。 + +**原因**： +- 代码存储在 NFS 挂载目录中 +- 清理通过 `spawn` 在后台子进程执行 +- NFS 大目录删除是异步的 + +**正确做法**： +- ❌ 不要用 `ls` 立即验证 +- ✅ 稍等片刻（几秒到几十秒）后再检查 +- ✅ 清理任务已在后台执行 + +## 完整工作流程 + +### 步骤 1：存储扫描（发现高占用）🔍 + +使用 `d8d_admin_storage_scan_dry_run` 全局扫描，找出高占用的工作空间/模板： + +```typescript +mcp__d8d_admin__storage_scan_dry_run({ + detail_level: "summary" // summary=简洁汇总(推荐), standard=标准模式, detailed=详细模式 +}) +``` + +**输出包含**： +- 📊 全局存储汇总（总扫描点、差异、孤立目录） +- 📁 存储类型占用分析（code, postgresql, minio 等） +- 🏆 **Top 15 工作空间存储排行** ← 重点看这个 +- 💡 清理建议 + +**从 Top 15 排行中选择目标工作空间 ID** + +### 步骤 2：列出工作空间的模板 + +使用 `d8d_admin_list_all_templates` 查看目标工作空间下的所有模板： + +```typescript +mcp__d8d_admin__list_all_templates({ + limit: 50, + response_format: "markdown" +}) +``` + +**输出包含**：模板 ID、名称、工作空间、用户 ID、创建时间 + +**筛选出目标模板 ID** + +### 步骤 3：查看模板详情（可选） + +使用 `d8d_admin_get_template_by_id` 获取模板完整信息： + +```typescript +mcp__d8d_admin__get_template_by_id({ + template_id: 162, + response_format: "markdown" +}) +``` + +**输出包含**：工作空间 ID、创建者 ID、容器配置等 + +### 步骤 4：预览清理 + +使用 `d8d_admin_cleanup_node_modules` 预览可回收空间： + +```typescript +mcp__d8d_admin__cleanup_node_modules({ + workspace_id: 176, + item_id: 162, + item_type: "template", + user_id: 21, + dry_run: true +}) +``` + +**输出包含**：node_modules 大小、.pnpm-store 大小、可回收空间 + +### 步骤 5：执行清理 + +确认后设置 `dry_run=false`： + +```typescript +mcp__d8d_admin__cleanup_node_modules({ + workspace_id: 176, + item_id: 162, + item_type: "template", + user_id: 21, + dry_run: false // 实际删除 +}) +``` + +### 步骤 6：验证结果 + +稍等片刻（NFS 异步删除），重新调用存储扫描或预览工具确认效果。 + +## 快速清理流程（已知目标） + +如果已知道目标模板，跳过步骤 1-3，直接执行： + +``` +步骤 4（预览） → 步骤 5（清理） → 步骤 6（验证） +``` + +## 工具参数速查 + +| 工具 | 主要参数 | 用途 | +|------|----------|------| +| `d8d_admin_storage_scan_dry_run` | detail_level | 全局存储扫描，发现高占用 | +| `d8d_admin_list_all_templates` | limit, search | 列出所有模板 | +| `d8d_admin_get_template_by_id` | template_id | 查看模板详情 | +| `d8d_admin_cleanup_node_modules` | workspace_id, item_id, item_type, user_id, dry_run | 清理 node_modules | diff --git a/.claude/skills/mcp-builder/LICENSE.txt b/.claude/skills/mcp-builder/LICENSE.txt new file mode 100644 index 0000000..7a4a3ea --- /dev/null +++ b/.claude/skills/mcp-builder/LICENSE.txt @@ -0,0 +1,202 @@ + + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [yyyy] [name of copyright owner] + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. \ No newline at end of file diff --git a/.claude/skills/mcp-builder/SKILL.md b/.claude/skills/mcp-builder/SKILL.md new file mode 100644 index 0000000..8a1a77a --- /dev/null +++ b/.claude/skills/mcp-builder/SKILL.md @@ -0,0 +1,236 @@ +--- +name: mcp-builder +description: Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). +license: Complete terms in LICENSE.txt +--- + +# MCP Server Development Guide + +## Overview + +Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks. + +--- + +# Process + +## 🚀 High-Level Workflow + +Creating a high-quality MCP server involves four main phases: + +### Phase 1: Deep Research and Planning + +#### 1.1 Understand Modern MCP Design + +**API Coverage vs. Workflow Tools:** +Balance comprehensive API endpoint coverage with specialized workflow tools. Workflow tools can be more convenient for specific tasks, while comprehensive coverage gives agents flexibility to compose operations. Performance varies by client—some clients benefit from code execution that combines basic tools, while others work better with higher-level workflows. When uncertain, prioritize comprehensive API coverage. + +**Tool Naming and Discoverability:** +Clear, descriptive tool names help agents find the right tools quickly. Use consistent prefixes (e.g., `github_create_issue`, `github_list_repos`) and action-oriented naming. + +**Context Management:** +Agents benefit from concise tool descriptions and the ability to filter/paginate results. Design tools that return focused, relevant data. Some clients support code execution which can help agents filter and process data efficiently. + +**Actionable Error Messages:** +Error messages should guide agents toward solutions with specific suggestions and next steps. + +#### 1.2 Study MCP Protocol Documentation + +**Navigate the MCP specification:** + +Start with the sitemap to find relevant pages: `https://modelcontextprotocol.io/sitemap.xml` + +Then fetch specific pages with `.md` suffix for markdown format (e.g., `https://modelcontextprotocol.io/specification/draft.md`). + +Key pages to review: +- Specification overview and architecture +- Transport mechanisms (streamable HTTP, stdio) +- Tool, resource, and prompt definitions + +#### 1.3 Study Framework Documentation + +**Recommended stack:** +- **Language**: TypeScript (high-quality SDK support and good compatibility in many execution environments e.g. MCPB. Plus AI models are good at generating TypeScript code, benefiting from its broad usage, static typing and good linting tools) +- **Transport**: Streamable HTTP for remote servers, using stateless JSON (simpler to scale and maintain, as opposed to stateful sessions and streaming responses). stdio for local servers. + +**Load framework documentation:** + +- **MCP Best Practices**: [📋 View Best Practices](./reference/mcp_best_practices.md) - Core guidelines + +**For TypeScript (recommended):** +- **TypeScript SDK**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md` +- [⚡ TypeScript Guide](./reference/node_mcp_server.md) - TypeScript patterns and examples + +**For Python:** +- **Python SDK**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md` +- [🐍 Python Guide](./reference/python_mcp_server.md) - Python patterns and examples + +#### 1.4 Plan Your Implementation + +**Understand the API:** +Review the service's API documentation to identify key endpoints, authentication requirements, and data models. Use web search and WebFetch as needed. + +**Tool Selection:** +Prioritize comprehensive API coverage. List endpoints to implement, starting with the most common operations. + +--- + +### Phase 2: Implementation + +#### 2.1 Set Up Project Structure + +See language-specific guides for project setup: +- [⚡ TypeScript Guide](./reference/node_mcp_server.md) - Project structure, package.json, tsconfig.json +- [🐍 Python Guide](./reference/python_mcp_server.md) - Module organization, dependencies + +#### 2.2 Implement Core Infrastructure + +Create shared utilities: +- API client with authentication +- Error handling helpers +- Response formatting (JSON/Markdown) +- Pagination support + +#### 2.3 Implement Tools + +For each tool: + +**Input Schema:** +- Use Zod (TypeScript) or Pydantic (Python) +- Include constraints and clear descriptions +- Add examples in field descriptions + +**Output Schema:** +- Define `outputSchema` where possible for structured data +- Use `structuredContent` in tool responses (TypeScript SDK feature) +- Helps clients understand and process tool outputs + +**Tool Description:** +- Concise summary of functionality +- Parameter descriptions +- Return type schema + +**Implementation:** +- Async/await for I/O operations +- Proper error handling with actionable messages +- Support pagination where applicable +- Return both text content and structured data when using modern SDKs + +**Annotations:** +- `readOnlyHint`: true/false +- `destructiveHint`: true/false +- `idempotentHint`: true/false +- `openWorldHint`: true/false + +--- + +### Phase 3: Review and Test + +#### 3.1 Code Quality + +Review for: +- No duplicated code (DRY principle) +- Consistent error handling +- Full type coverage +- Clear tool descriptions + +#### 3.2 Build and Test + +**TypeScript:** +- Run `npm run build` to verify compilation +- Test with MCP Inspector: `npx @modelcontextprotocol/inspector` + +**Python:** +- Verify syntax: `python -m py_compile your_server.py` +- Test with MCP Inspector + +See language-specific guides for detailed testing approaches and quality checklists. + +--- + +### Phase 4: Create Evaluations + +After implementing your MCP server, create comprehensive evaluations to test its effectiveness. + +**Load [✅ Evaluation Guide](./reference/evaluation.md) for complete evaluation guidelines.** + +#### 4.1 Understand Evaluation Purpose + +Use evaluations to test whether LLMs can effectively use your MCP server to answer realistic, complex questions. + +#### 4.2 Create 10 Evaluation Questions + +To create effective evaluations, follow the process outlined in the evaluation guide: + +1. **Tool Inspection**: List available tools and understand their capabilities +2. **Content Exploration**: Use READ-ONLY operations to explore available data +3. **Question Generation**: Create 10 complex, realistic questions +4. **Answer Verification**: Solve each question yourself to verify answers + +#### 4.3 Evaluation Requirements + +Ensure each question is: +- **Independent**: Not dependent on other questions +- **Read-only**: Only non-destructive operations required +- **Complex**: Requiring multiple tool calls and deep exploration +- **Realistic**: Based on real use cases humans would care about +- **Verifiable**: Single, clear answer that can be verified by string comparison +- **Stable**: Answer won't change over time + +#### 4.4 Output Format + +Create an XML file with this structure: + +```xml + + + Find discussions about AI model launches with animal codenames. One model needed a specific safety designation that uses the format ASL-X. What number X was being determined for the model named after a spotted wild cat? + 3 + + + +``` + +--- + +# Reference Files + +## 📚 Documentation Library + +Load these resources as needed during development: + +### Core MCP Documentation (Load First) +- **MCP Protocol**: Start with sitemap at `https://modelcontextprotocol.io/sitemap.xml`, then fetch specific pages with `.md` suffix +- [📋 MCP Best Practices](./reference/mcp_best_practices.md) - Universal MCP guidelines including: + - Server and tool naming conventions + - Response format guidelines (JSON vs Markdown) + - Pagination best practices + - Transport selection (streamable HTTP vs stdio) + - Security and error handling standards + +### SDK Documentation (Load During Phase 1/2) +- **Python SDK**: Fetch from `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md` +- **TypeScript SDK**: Fetch from `https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md` + +### Language-Specific Implementation Guides (Load During Phase 2) +- [🐍 Python Implementation Guide](./reference/python_mcp_server.md) - Complete Python/FastMCP guide with: + - Server initialization patterns + - Pydantic model examples + - Tool registration with `@mcp.tool` + - Complete working examples + - Quality checklist + +- [⚡ TypeScript Implementation Guide](./reference/node_mcp_server.md) - Complete TypeScript guide with: + - Project structure + - Zod schema patterns + - Tool registration with `server.registerTool` + - Complete working examples + - Quality checklist + +### Evaluation Guide (Load During Phase 4) +- [✅ Evaluation Guide](./reference/evaluation.md) - Complete evaluation creation guide with: + - Question creation guidelines + - Answer verification strategies + - XML format specifications + - Example questions and answers + - Running an evaluation with the provided scripts diff --git a/.claude/skills/mcp-builder/reference/evaluation.md b/.claude/skills/mcp-builder/reference/evaluation.md new file mode 100644 index 0000000..87e9bb7 --- /dev/null +++ b/.claude/skills/mcp-builder/reference/evaluation.md @@ -0,0 +1,602 @@ +# MCP Server Evaluation Guide + +## Overview + +This document provides guidance on creating comprehensive evaluations for MCP servers. Evaluations test whether LLMs can effectively use your MCP server to answer realistic, complex questions using only the tools provided. + +--- + +## Quick Reference + +### Evaluation Requirements +- Create 10 human-readable questions +- Questions must be READ-ONLY, INDEPENDENT, NON-DESTRUCTIVE +- Each question requires multiple tool calls (potentially dozens) +- Answers must be single, verifiable values +- Answers must be STABLE (won't change over time) + +### Output Format +```xml + + + Your question here + Single verifiable answer + + +``` + +--- + +## Purpose of Evaluations + +The measure of quality of an MCP server is NOT how well or comprehensively the server implements tools, but how well these implementations (input/output schemas, docstrings/descriptions, functionality) enable LLMs with no other context and access ONLY to the MCP servers to answer realistic and difficult questions. + +## Evaluation Overview + +Create 10 human-readable questions requiring ONLY READ-ONLY, INDEPENDENT, NON-DESTRUCTIVE, and IDEMPOTENT operations to answer. Each question should be: +- Realistic +- Clear and concise +- Unambiguous +- Complex, requiring potentially dozens of tool calls or steps +- Answerable with a single, verifiable value that you identify in advance + +## Question Guidelines + +### Core Requirements + +1. **Questions MUST be independent** + - Each question should NOT depend on the answer to any other question + - Should not assume prior write operations from processing another question + +2. **Questions MUST require ONLY NON-DESTRUCTIVE AND IDEMPOTENT tool use** + - Should not instruct or require modifying state to arrive at the correct answer + +3. **Questions must be REALISTIC, CLEAR, CONCISE, and COMPLEX** + - Must require another LLM to use multiple (potentially dozens of) tools or steps to answer + +### Complexity and Depth + +4. **Questions must require deep exploration** + - Consider multi-hop questions requiring multiple sub-questions and sequential tool calls + - Each step should benefit from information found in previous questions + +5. **Questions may require extensive paging** + - May need paging through multiple pages of results + - May require querying old data (1-2 years out-of-date) to find niche information + - The questions must be DIFFICULT + +6. **Questions must require deep understanding** + - Rather than surface-level knowledge + - May pose complex ideas as True/False questions requiring evidence + - May use multiple-choice format where LLM must search different hypotheses + +7. **Questions must not be solvable with straightforward keyword search** + - Do not include specific keywords from the target content + - Use synonyms, related concepts, or paraphrases + - Require multiple searches, analyzing multiple related items, extracting context, then deriving the answer + +### Tool Testing + +8. **Questions should stress-test tool return values** + - May elicit tools returning large JSON objects or lists, overwhelming the LLM + - Should require understanding multiple modalities of data: + - IDs and names + - Timestamps and datetimes (months, days, years, seconds) + - File IDs, names, extensions, and mimetypes + - URLs, GIDs, etc. + - Should probe the tool's ability to return all useful forms of data + +9. **Questions should MOSTLY reflect real human use cases** + - The kinds of information retrieval tasks that HUMANS assisted by an LLM would care about + +10. **Questions may require dozens of tool calls** + - This challenges LLMs with limited context + - Encourages MCP server tools to reduce information returned + +11. **Include ambiguous questions** + - May be ambiguous OR require difficult decisions on which tools to call + - Force the LLM to potentially make mistakes or misinterpret + - Ensure that despite AMBIGUITY, there is STILL A SINGLE VERIFIABLE ANSWER + +### Stability + +12. **Questions must be designed so the answer DOES NOT CHANGE** + - Do not ask questions that rely on "current state" which is dynamic + - For example, do not count: + - Number of reactions to a post + - Number of replies to a thread + - Number of members in a channel + +13. **DO NOT let the MCP server RESTRICT the kinds of questions you create** + - Create challenging and complex questions + - Some may not be solvable with the available MCP server tools + - Questions may require specific output formats (datetime vs. epoch time, JSON vs. MARKDOWN) + - Questions may require dozens of tool calls to complete + +## Answer Guidelines + +### Verification + +1. **Answers must be VERIFIABLE via direct string comparison** + - If the answer can be re-written in many formats, clearly specify the output format in the QUESTION + - Examples: "Use YYYY/MM/DD.", "Respond True or False.", "Answer A, B, C, or D and nothing else." + - Answer should be a single VERIFIABLE value such as: + - User ID, user name, display name, first name, last name + - Channel ID, channel name + - Message ID, string + - URL, title + - Numerical quantity + - Timestamp, datetime + - Boolean (for True/False questions) + - Email address, phone number + - File ID, file name, file extension + - Multiple choice answer + - Answers must not require special formatting or complex, structured output + - Answer will be verified using DIRECT STRING COMPARISON + +### Readability + +2. **Answers should generally prefer HUMAN-READABLE formats** + - Examples: names, first name, last name, datetime, file name, message string, URL, yes/no, true/false, a/b/c/d + - Rather than opaque IDs (though IDs are acceptable) + - The VAST MAJORITY of answers should be human-readable + +### Stability + +3. **Answers must be STABLE/STATIONARY** + - Look at old content (e.g., conversations that have ended, projects that have launched, questions answered) + - Create QUESTIONS based on "closed" concepts that will always return the same answer + - Questions may ask to consider a fixed time window to insulate from non-stationary answers + - Rely on context UNLIKELY to change + - Example: if finding a paper name, be SPECIFIC enough so answer is not confused with papers published later + +4. **Answers must be CLEAR and UNAMBIGUOUS** + - Questions must be designed so there is a single, clear answer + - Answer can be derived from using the MCP server tools + +### Diversity + +5. **Answers must be DIVERSE** + - Answer should be a single VERIFIABLE value in diverse modalities and formats + - User concept: user ID, user name, display name, first name, last name, email address, phone number + - Channel concept: channel ID, channel name, channel topic + - Message concept: message ID, message string, timestamp, month, day, year + +6. **Answers must NOT be complex structures** + - Not a list of values + - Not a complex object + - Not a list of IDs or strings + - Not natural language text + - UNLESS the answer can be straightforwardly verified using DIRECT STRING COMPARISON + - And can be realistically reproduced + - It should be unlikely that an LLM would return the same list in any other order or format + +## Evaluation Process + +### Step 1: Documentation Inspection + +Read the documentation of the target API to understand: +- Available endpoints and functionality +- If ambiguity exists, fetch additional information from the web +- Parallelize this step AS MUCH AS POSSIBLE +- Ensure each subagent is ONLY examining documentation from the file system or on the web + +### Step 2: Tool Inspection + +List the tools available in the MCP server: +- Inspect the MCP server directly +- Understand input/output schemas, docstrings, and descriptions +- WITHOUT calling the tools themselves at this stage + +### Step 3: Developing Understanding + +Repeat steps 1 & 2 until you have a good understanding: +- Iterate multiple times +- Think about the kinds of tasks you want to create +- Refine your understanding +- At NO stage should you READ the code of the MCP server implementation itself +- Use your intuition and understanding to create reasonable, realistic, but VERY challenging tasks + +### Step 4: Read-Only Content Inspection + +After understanding the API and tools, USE the MCP server tools: +- Inspect content using READ-ONLY and NON-DESTRUCTIVE operations ONLY +- Goal: identify specific content (e.g., users, channels, messages, projects, tasks) for creating realistic questions +- Should NOT call any tools that modify state +- Will NOT read the code of the MCP server implementation itself +- Parallelize this step with individual sub-agents pursuing independent explorations +- Ensure each subagent is only performing READ-ONLY, NON-DESTRUCTIVE, and IDEMPOTENT operations +- BE CAREFUL: SOME TOOLS may return LOTS OF DATA which would cause you to run out of CONTEXT +- Make INCREMENTAL, SMALL, AND TARGETED tool calls for exploration +- In all tool call requests, use the `limit` parameter to limit results (<10) +- Use pagination + +### Step 5: Task Generation + +After inspecting the content, create 10 human-readable questions: +- An LLM should be able to answer these with the MCP server +- Follow all question and answer guidelines above + +## Output Format + +Each QA pair consists of a question and an answer. The output should be an XML file with this structure: + +```xml + + + Find the project created in Q2 2024 with the highest number of completed tasks. What is the project name? + Website Redesign + + + Search for issues labeled as "bug" that were closed in March 2024. Which user closed the most issues? Provide their username. + sarah_dev + + + Look for pull requests that modified files in the /api directory and were merged between January 1 and January 31, 2024. How many different contributors worked on these PRs? + 7 + + + Find the repository with the most stars that was created before 2023. What is the repository name? + data-pipeline + + +``` + +## Evaluation Examples + +### Good Questions + +**Example 1: Multi-hop question requiring deep exploration (GitHub MCP)** +```xml + + Find the repository that was archived in Q3 2023 and had previously been the most forked project in the organization. What was the primary programming language used in that repository? + Python + +``` + +This question is good because: +- Requires multiple searches to find archived repositories +- Needs to identify which had the most forks before archival +- Requires examining repository details for the language +- Answer is a simple, verifiable value +- Based on historical (closed) data that won't change + +**Example 2: Requires understanding context without keyword matching (Project Management MCP)** +```xml + + Locate the initiative focused on improving customer onboarding that was completed in late 2023. The project lead created a retrospective document after completion. What was the lead's role title at that time? + Product Manager + +``` + +This question is good because: +- Doesn't use specific project name ("initiative focused on improving customer onboarding") +- Requires finding completed projects from specific timeframe +- Needs to identify the project lead and their role +- Requires understanding context from retrospective documents +- Answer is human-readable and stable +- Based on completed work (won't change) + +**Example 3: Complex aggregation requiring multiple steps (Issue Tracker MCP)** +```xml + + Among all bugs reported in January 2024 that were marked as critical priority, which assignee resolved the highest percentage of their assigned bugs within 48 hours? Provide the assignee's username. + alex_eng + +``` + +This question is good because: +- Requires filtering bugs by date, priority, and status +- Needs to group by assignee and calculate resolution rates +- Requires understanding timestamps to determine 48-hour windows +- Tests pagination (potentially many bugs to process) +- Answer is a single username +- Based on historical data from specific time period + +**Example 4: Requires synthesis across multiple data types (CRM MCP)** +```xml + + Find the account that upgraded from the Starter to Enterprise plan in Q4 2023 and had the highest annual contract value. What industry does this account operate in? + Healthcare + +``` + +This question is good because: +- Requires understanding subscription tier changes +- Needs to identify upgrade events in specific timeframe +- Requires comparing contract values +- Must access account industry information +- Answer is simple and verifiable +- Based on completed historical transactions + +### Poor Questions + +**Example 1: Answer changes over time** +```xml + + How many open issues are currently assigned to the engineering team? + 47 + +``` + +This question is poor because: +- The answer will change as issues are created, closed, or reassigned +- Not based on stable/stationary data +- Relies on "current state" which is dynamic + +**Example 2: Too easy with keyword search** +```xml + + Find the pull request with title "Add authentication feature" and tell me who created it. + developer123 + +``` + +This question is poor because: +- Can be solved with a straightforward keyword search for exact title +- Doesn't require deep exploration or understanding +- No synthesis or analysis needed + +**Example 3: Ambiguous answer format** +```xml + + List all the repositories that have Python as their primary language. + repo1, repo2, repo3, data-pipeline, ml-tools + +``` + +This question is poor because: +- Answer is a list that could be returned in any order +- Difficult to verify with direct string comparison +- LLM might format differently (JSON array, comma-separated, newline-separated) +- Better to ask for a specific aggregate (count) or superlative (most stars) + +## Verification Process + +After creating evaluations: + +1. **Examine the XML file** to understand the schema +2. **Load each task instruction** and in parallel using the MCP server and tools, identify the correct answer by attempting to solve the task YOURSELF +3. **Flag any operations** that require WRITE or DESTRUCTIVE operations +4. **Accumulate all CORRECT answers** and replace any incorrect answers in the document +5. **Remove any ``** that require WRITE or DESTRUCTIVE operations + +Remember to parallelize solving tasks to avoid running out of context, then accumulate all answers and make changes to the file at the end. + +## Tips for Creating Quality Evaluations + +1. **Think Hard and Plan Ahead** before generating tasks +2. **Parallelize Where Opportunity Arises** to speed up the process and manage context +3. **Focus on Realistic Use Cases** that humans would actually want to accomplish +4. **Create Challenging Questions** that test the limits of the MCP server's capabilities +5. **Ensure Stability** by using historical data and closed concepts +6. **Verify Answers** by solving the questions yourself using the MCP server tools +7. **Iterate and Refine** based on what you learn during the process + +--- + +# Running Evaluations + +After creating your evaluation file, you can use the provided evaluation harness to test your MCP server. + +## Setup + +1. **Install Dependencies** + + ```bash + pip install -r scripts/requirements.txt + ``` + + Or install manually: + ```bash + pip install anthropic mcp + ``` + +2. **Set API Key** + + ```bash + export ANTHROPIC_API_KEY=your_api_key_here + ``` + +## Evaluation File Format + +Evaluation files use XML format with `` elements: + +```xml + + + Find the project created in Q2 2024 with the highest number of completed tasks. What is the project name? + Website Redesign + + + Search for issues labeled as "bug" that were closed in March 2024. Which user closed the most issues? Provide their username. + sarah_dev + + +``` + +## Running Evaluations + +The evaluation script (`scripts/evaluation.py`) supports three transport types: + +**Important:** +- **stdio transport**: The evaluation script automatically launches and manages the MCP server process for you. Do not run the server manually. +- **sse/http transports**: You must start the MCP server separately before running the evaluation. The script connects to the already-running server at the specified URL. + +### 1. Local STDIO Server + +For locally-run MCP servers (script launches the server automatically): + +```bash +python scripts/evaluation.py \ + -t stdio \ + -c python \ + -a my_mcp_server.py \ + evaluation.xml +``` + +With environment variables: +```bash +python scripts/evaluation.py \ + -t stdio \ + -c python \ + -a my_mcp_server.py \ + -e API_KEY=abc123 \ + -e DEBUG=true \ + evaluation.xml +``` + +### 2. Server-Sent Events (SSE) + +For SSE-based MCP servers (you must start the server first): + +```bash +python scripts/evaluation.py \ + -t sse \ + -u https://example.com/mcp \ + -H "Authorization: Bearer token123" \ + -H "X-Custom-Header: value" \ + evaluation.xml +``` + +### 3. HTTP (Streamable HTTP) + +For HTTP-based MCP servers (you must start the server first): + +```bash +python scripts/evaluation.py \ + -t http \ + -u https://example.com/mcp \ + -H "Authorization: Bearer token123" \ + evaluation.xml +``` + +## Command-Line Options + +``` +usage: evaluation.py [-h] [-t {stdio,sse,http}] [-m MODEL] [-c COMMAND] + [-a ARGS [ARGS ...]] [-e ENV [ENV ...]] [-u URL] + [-H HEADERS [HEADERS ...]] [-o OUTPUT] + eval_file + +positional arguments: + eval_file Path to evaluation XML file + +optional arguments: + -h, --help Show help message + -t, --transport Transport type: stdio, sse, or http (default: stdio) + -m, --model Claude model to use (default: claude-3-7-sonnet-20250219) + -o, --output Output file for report (default: print to stdout) + +stdio options: + -c, --command Command to run MCP server (e.g., python, node) + -a, --args Arguments for the command (e.g., server.py) + -e, --env Environment variables in KEY=VALUE format + +sse/http options: + -u, --url MCP server URL + -H, --header HTTP headers in 'Key: Value' format +``` + +## Output + +The evaluation script generates a detailed report including: + +- **Summary Statistics**: + - Accuracy (correct/total) + - Average task duration + - Average tool calls per task + - Total tool calls + +- **Per-Task Results**: + - Prompt and expected response + - Actual response from the agent + - Whether the answer was correct (✅/❌) + - Duration and tool call details + - Agent's summary of its approach + - Agent's feedback on the tools + +### Save Report to File + +```bash +python scripts/evaluation.py \ + -t stdio \ + -c python \ + -a my_server.py \ + -o evaluation_report.md \ + evaluation.xml +``` + +## Complete Example Workflow + +Here's a complete example of creating and running an evaluation: + +1. **Create your evaluation file** (`my_evaluation.xml`): + +```xml + + + Find the user who created the most issues in January 2024. What is their username? + alice_developer + + + Among all pull requests merged in Q1 2024, which repository had the highest number? Provide the repository name. + backend-api + + + Find the project that was completed in December 2023 and had the longest duration from start to finish. How many days did it take? + 127 + + +``` + +2. **Install dependencies**: + +```bash +pip install -r scripts/requirements.txt +export ANTHROPIC_API_KEY=your_api_key +``` + +3. **Run evaluation**: + +```bash +python scripts/evaluation.py \ + -t stdio \ + -c python \ + -a github_mcp_server.py \ + -e GITHUB_TOKEN=ghp_xxx \ + -o github_eval_report.md \ + my_evaluation.xml +``` + +4. **Review the report** in `github_eval_report.md` to: + - See which questions passed/failed + - Read the agent's feedback on your tools + - Identify areas for improvement + - Iterate on your MCP server design + +## Troubleshooting + +### Connection Errors + +If you get connection errors: +- **STDIO**: Verify the command and arguments are correct +- **SSE/HTTP**: Check the URL is accessible and headers are correct +- Ensure any required API keys are set in environment variables or headers + +### Low Accuracy + +If many evaluations fail: +- Review the agent's feedback for each task +- Check if tool descriptions are clear and comprehensive +- Verify input parameters are well-documented +- Consider whether tools return too much or too little data +- Ensure error messages are actionable + +### Timeout Issues + +If tasks are timing out: +- Use a more capable model (e.g., `claude-3-7-sonnet-20250219`) +- Check if tools are returning too much data +- Verify pagination is working correctly +- Consider simplifying complex questions \ No newline at end of file diff --git a/.claude/skills/mcp-builder/reference/mcp_best_practices.md b/.claude/skills/mcp-builder/reference/mcp_best_practices.md new file mode 100644 index 0000000..b9d343c --- /dev/null +++ b/.claude/skills/mcp-builder/reference/mcp_best_practices.md @@ -0,0 +1,249 @@ +# MCP Server Best Practices + +## Quick Reference + +### Server Naming +- **Python**: `{service}_mcp` (e.g., `slack_mcp`) +- **Node/TypeScript**: `{service}-mcp-server` (e.g., `slack-mcp-server`) + +### Tool Naming +- Use snake_case with service prefix +- Format: `{service}_{action}_{resource}` +- Example: `slack_send_message`, `github_create_issue` + +### Response Formats +- Support both JSON and Markdown formats +- JSON for programmatic processing +- Markdown for human readability + +### Pagination +- Always respect `limit` parameter +- Return `has_more`, `next_offset`, `total_count` +- Default to 20-50 items + +### Transport +- **Streamable HTTP**: For remote servers, multi-client scenarios +- **stdio**: For local integrations, command-line tools +- Avoid SSE (deprecated in favor of streamable HTTP) + +--- + +## Server Naming Conventions + +Follow these standardized naming patterns: + +**Python**: Use format `{service}_mcp` (lowercase with underscores) +- Examples: `slack_mcp`, `github_mcp`, `jira_mcp` + +**Node/TypeScript**: Use format `{service}-mcp-server` (lowercase with hyphens) +- Examples: `slack-mcp-server`, `github-mcp-server`, `jira-mcp-server` + +The name should be general, descriptive of the service being integrated, easy to infer from the task description, and without version numbers. + +--- + +## Tool Naming and Design + +### Tool Naming + +1. **Use snake_case**: `search_users`, `create_project`, `get_channel_info` +2. **Include service prefix**: Anticipate that your MCP server may be used alongside other MCP servers + - Use `slack_send_message` instead of just `send_message` + - Use `github_create_issue` instead of just `create_issue` +3. **Be action-oriented**: Start with verbs (get, list, search, create, etc.) +4. **Be specific**: Avoid generic names that could conflict with other servers + +### Tool Design + +- Tool descriptions must narrowly and unambiguously describe functionality +- Descriptions must precisely match actual functionality +- Provide tool annotations (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) +- Keep tool operations focused and atomic + +--- + +## Response Formats + +All tools that return data should support multiple formats: + +### JSON Format (`response_format="json"`) +- Machine-readable structured data +- Include all available fields and metadata +- Consistent field names and types +- Use for programmatic processing + +### Markdown Format (`response_format="markdown"`, typically default) +- Human-readable formatted text +- Use headers, lists, and formatting for clarity +- Convert timestamps to human-readable format +- Show display names with IDs in parentheses +- Omit verbose metadata + +--- + +## Pagination + +For tools that list resources: + +- **Always respect the `limit` parameter** +- **Implement pagination**: Use `offset` or cursor-based pagination +- **Return pagination metadata**: Include `has_more`, `next_offset`/`next_cursor`, `total_count` +- **Never load all results into memory**: Especially important for large datasets +- **Default to reasonable limits**: 20-50 items is typical + +Example pagination response: +```json +{ + "total": 150, + "count": 20, + "offset": 0, + "items": [...], + "has_more": true, + "next_offset": 20 +} +``` + +--- + +## Transport Options + +### Streamable HTTP + +**Best for**: Remote servers, web services, multi-client scenarios + +**Characteristics**: +- Bidirectional communication over HTTP +- Supports multiple simultaneous clients +- Can be deployed as a web service +- Enables server-to-client notifications + +**Use when**: +- Serving multiple clients simultaneously +- Deploying as a cloud service +- Integration with web applications + +### stdio + +**Best for**: Local integrations, command-line tools + +**Characteristics**: +- Standard input/output stream communication +- Simple setup, no network configuration needed +- Runs as a subprocess of the client + +**Use when**: +- Building tools for local development environments +- Integrating with desktop applications +- Single-user, single-session scenarios + +**Note**: stdio servers should NOT log to stdout (use stderr for logging) + +### Transport Selection + +| Criterion | stdio | Streamable HTTP | +|-----------|-------|-----------------| +| **Deployment** | Local | Remote | +| **Clients** | Single | Multiple | +| **Complexity** | Low | Medium | +| **Real-time** | No | Yes | + +--- + +## Security Best Practices + +### Authentication and Authorization + +**OAuth 2.1**: +- Use secure OAuth 2.1 with certificates from recognized authorities +- Validate access tokens before processing requests +- Only accept tokens specifically intended for your server + +**API Keys**: +- Store API keys in environment variables, never in code +- Validate keys on server startup +- Provide clear error messages when authentication fails + +### Input Validation + +- Sanitize file paths to prevent directory traversal +- Validate URLs and external identifiers +- Check parameter sizes and ranges +- Prevent command injection in system calls +- Use schema validation (Pydantic/Zod) for all inputs + +### Error Handling + +- Don't expose internal errors to clients +- Log security-relevant errors server-side +- Provide helpful but not revealing error messages +- Clean up resources after errors + +### DNS Rebinding Protection + +For streamable HTTP servers running locally: +- Enable DNS rebinding protection +- Validate the `Origin` header on all incoming connections +- Bind to `127.0.0.1` rather than `0.0.0.0` + +--- + +## Tool Annotations + +Provide annotations to help clients understand tool behavior: + +| Annotation | Type | Default | Description | +|-----------|------|---------|-------------| +| `readOnlyHint` | boolean | false | Tool does not modify its environment | +| `destructiveHint` | boolean | true | Tool may perform destructive updates | +| `idempotentHint` | boolean | false | Repeated calls with same args have no additional effect | +| `openWorldHint` | boolean | true | Tool interacts with external entities | + +**Important**: Annotations are hints, not security guarantees. Clients should not make security-critical decisions based solely on annotations. + +--- + +## Error Handling + +- Use standard JSON-RPC error codes +- Report tool errors within result objects (not protocol-level errors) +- Provide helpful, specific error messages with suggested next steps +- Don't expose internal implementation details +- Clean up resources properly on errors + +Example error handling: +```typescript +try { + const result = performOperation(); + return { content: [{ type: "text", text: result }] }; +} catch (error) { + return { + isError: true, + content: [{ + type: "text", + text: `Error: ${error.message}. Try using filter='active_only' to reduce results.` + }] + }; +} +``` + +--- + +## Testing Requirements + +Comprehensive testing should cover: + +- **Functional testing**: Verify correct execution with valid/invalid inputs +- **Integration testing**: Test interaction with external systems +- **Security testing**: Validate auth, input sanitization, rate limiting +- **Performance testing**: Check behavior under load, timeouts +- **Error handling**: Ensure proper error reporting and cleanup + +--- + +## Documentation Requirements + +- Provide clear documentation of all tools and capabilities +- Include working examples (at least 3 per major feature) +- Document security considerations +- Specify required permissions and access levels +- Document rate limits and performance characteristics diff --git a/.claude/skills/mcp-builder/reference/node_mcp_server.md b/.claude/skills/mcp-builder/reference/node_mcp_server.md new file mode 100644 index 0000000..f6e5df9 --- /dev/null +++ b/.claude/skills/mcp-builder/reference/node_mcp_server.md @@ -0,0 +1,970 @@ +# Node/TypeScript MCP Server Implementation Guide + +## Overview + +This document provides Node/TypeScript-specific best practices and examples for implementing MCP servers using the MCP TypeScript SDK. It covers project structure, server setup, tool registration patterns, input validation with Zod, error handling, and complete working examples. + +--- + +## Quick Reference + +### Key Imports +```typescript +import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; +import { StreamableHTTPServerTransport } from "@modelcontextprotocol/sdk/server/streamableHttp.js"; +import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js"; +import express from "express"; +import { z } from "zod"; +``` + +### Server Initialization +```typescript +const server = new McpServer({ + name: "service-mcp-server", + version: "1.0.0" +}); +``` + +### Tool Registration Pattern +```typescript +server.registerTool( + "tool_name", + { + title: "Tool Display Name", + description: "What the tool does", + inputSchema: { param: z.string() }, + outputSchema: { result: z.string() } + }, + async ({ param }) => { + const output = { result: `Processed: ${param}` }; + return { + content: [{ type: "text", text: JSON.stringify(output) }], + structuredContent: output // Modern pattern for structured data + }; + } +); +``` + +--- + +## MCP TypeScript SDK + +The official MCP TypeScript SDK provides: +- `McpServer` class for server initialization +- `registerTool` method for tool registration +- Zod schema integration for runtime input validation +- Type-safe tool handler implementations + +**IMPORTANT - Use Modern APIs Only:** +- **DO use**: `server.registerTool()`, `server.registerResource()`, `server.registerPrompt()` +- **DO NOT use**: Old deprecated APIs such as `server.tool()`, `server.setRequestHandler(ListToolsRequestSchema, ...)`, or manual handler registration +- The `register*` methods provide better type safety, automatic schema handling, and are the recommended approach + +See the MCP SDK documentation in the references for complete details. + +## Server Naming Convention + +Node/TypeScript MCP servers must follow this naming pattern: +- **Format**: `{service}-mcp-server` (lowercase with hyphens) +- **Examples**: `github-mcp-server`, `jira-mcp-server`, `stripe-mcp-server` + +The name should be: +- General (not tied to specific features) +- Descriptive of the service/API being integrated +- Easy to infer from the task description +- Without version numbers or dates + +## Project Structure + +Create the following structure for Node/TypeScript MCP servers: + +``` +{service}-mcp-server/ +├── package.json +├── tsconfig.json +├── README.md +├── src/ +│ ├── index.ts # Main entry point with McpServer initialization +│ ├── types.ts # TypeScript type definitions and interfaces +│ ├── tools/ # Tool implementations (one file per domain) +│ ├── services/ # API clients and shared utilities +│ ├── schemas/ # Zod validation schemas +│ └── constants.ts # Shared constants (API_URL, CHARACTER_LIMIT, etc.) +└── dist/ # Built JavaScript files (entry point: dist/index.js) +``` + +## Tool Implementation + +### Tool Naming + +Use snake_case for tool names (e.g., "search_users", "create_project", "get_channel_info") with clear, action-oriented names. + +**Avoid Naming Conflicts**: Include the service context to prevent overlaps: +- Use "slack_send_message" instead of just "send_message" +- Use "github_create_issue" instead of just "create_issue" +- Use "asana_list_tasks" instead of just "list_tasks" + +### Tool Structure + +Tools are registered using the `registerTool` method with the following requirements: +- Use Zod schemas for runtime input validation and type safety +- The `description` field must be explicitly provided - JSDoc comments are NOT automatically extracted +- Explicitly provide `title`, `description`, `inputSchema`, and `annotations` +- The `inputSchema` must be a Zod schema object (not a JSON schema) +- Type all parameters and return values explicitly + +```typescript +import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; +import { z } from "zod"; + +const server = new McpServer({ + name: "example-mcp", + version: "1.0.0" +}); + +// Zod schema for input validation +const UserSearchInputSchema = z.object({ + query: z.string() + .min(2, "Query must be at least 2 characters") + .max(200, "Query must not exceed 200 characters") + .describe("Search string to match against names/emails"), + limit: z.number() + .int() + .min(1) + .max(100) + .default(20) + .describe("Maximum results to return"), + offset: z.number() + .int() + .min(0) + .default(0) + .describe("Number of results to skip for pagination"), + response_format: z.nativeEnum(ResponseFormat) + .default(ResponseFormat.MARKDOWN) + .describe("Output format: 'markdown' for human-readable or 'json' for machine-readable") +}).strict(); + +// Type definition from Zod schema +type UserSearchInput = z.infer; + +server.registerTool( + "example_search_users", + { + title: "Search Example Users", + description: `Search for users in the Example system by name, email, or team. + +This tool searches across all user profiles in the Example platform, supporting partial matches and various search filters. It does NOT create or modify users, only searches existing ones. + +Args: + - query (string): Search string to match against names/emails + - limit (number): Maximum results to return, between 1-100 (default: 20) + - offset (number): Number of results to skip for pagination (default: 0) + - response_format ('markdown' | 'json'): Output format (default: 'markdown') + +Returns: + For JSON format: Structured data with schema: + { + "total": number, // Total number of matches found + "count": number, // Number of results in this response + "offset": number, // Current pagination offset + "users": [ + { + "id": string, // User ID (e.g., "U123456789") + "name": string, // Full name (e.g., "John Doe") + "email": string, // Email address + "team": string, // Team name (optional) + "active": boolean // Whether user is active + } + ], + "has_more": boolean, // Whether more results are available + "next_offset": number // Offset for next page (if has_more is true) + } + +Examples: + - Use when: "Find all marketing team members" -> params with query="team:marketing" + - Use when: "Search for John's account" -> params with query="john" + - Don't use when: You need to create a user (use example_create_user instead) + +Error Handling: + - Returns "Error: Rate limit exceeded" if too many requests (429 status) + - Returns "No users found matching ''" if search returns empty`, + inputSchema: UserSearchInputSchema, + annotations: { + readOnlyHint: true, + destructiveHint: false, + idempotentHint: true, + openWorldHint: true + } + }, + async (params: UserSearchInput) => { + try { + // Input validation is handled by Zod schema + // Make API request using validated parameters + const data = await makeApiRequest( + "users/search", + "GET", + undefined, + { + q: params.query, + limit: params.limit, + offset: params.offset + } + ); + + const users = data.users || []; + const total = data.total || 0; + + if (!users.length) { + return { + content: [{ + type: "text", + text: `No users found matching '${params.query}'` + }] + }; + } + + // Prepare structured output + const output = { + total, + count: users.length, + offset: params.offset, + users: users.map((user: any) => ({ + id: user.id, + name: user.name, + email: user.email, + ...(user.team ? { team: user.team } : {}), + active: user.active ?? true + })), + has_more: total > params.offset + users.length, + ...(total > params.offset + users.length ? { + next_offset: params.offset + users.length + } : {}) + }; + + // Format text representation based on requested format + let textContent: string; + if (params.response_format === ResponseFormat.MARKDOWN) { + const lines = [`# User Search Results: '${params.query}'`, "", + `Found ${total} users (showing ${users.length})`, ""]; + for (const user of users) { + lines.push(`## ${user.name} (${user.id})`); + lines.push(`- **Email**: ${user.email}`); + if (user.team) lines.push(`- **Team**: ${user.team}`); + lines.push(""); + } + textContent = lines.join("\n"); + } else { + textContent = JSON.stringify(output, null, 2); + } + + return { + content: [{ type: "text", text: textContent }], + structuredContent: output // Modern pattern for structured data + }; + } catch (error) { + return { + content: [{ + type: "text", + text: handleApiError(error) + }] + }; + } + } +); +``` + +## Zod Schemas for Input Validation + +Zod provides runtime type validation: + +```typescript +import { z } from "zod"; + +// Basic schema with validation +const CreateUserSchema = z.object({ + name: z.string() + .min(1, "Name is required") + .max(100, "Name must not exceed 100 characters"), + email: z.string() + .email("Invalid email format"), + age: z.number() + .int("Age must be a whole number") + .min(0, "Age cannot be negative") + .max(150, "Age cannot be greater than 150") +}).strict(); // Use .strict() to forbid extra fields + +// Enums +enum ResponseFormat { + MARKDOWN = "markdown", + JSON = "json" +} + +const SearchSchema = z.object({ + response_format: z.nativeEnum(ResponseFormat) + .default(ResponseFormat.MARKDOWN) + .describe("Output format") +}); + +// Optional fields with defaults +const PaginationSchema = z.object({ + limit: z.number() + .int() + .min(1) + .max(100) + .default(20) + .describe("Maximum results to return"), + offset: z.number() + .int() + .min(0) + .default(0) + .describe("Number of results to skip") +}); +``` + +## Response Format Options + +Support multiple output formats for flexibility: + +```typescript +enum ResponseFormat { + MARKDOWN = "markdown", + JSON = "json" +} + +const inputSchema = z.object({ + query: z.string(), + response_format: z.nativeEnum(ResponseFormat) + .default(ResponseFormat.MARKDOWN) + .describe("Output format: 'markdown' for human-readable or 'json' for machine-readable") +}); +``` + +**Markdown format**: +- Use headers, lists, and formatting for clarity +- Convert timestamps to human-readable format +- Show display names with IDs in parentheses +- Omit verbose metadata +- Group related information logically + +**JSON format**: +- Return complete, structured data suitable for programmatic processing +- Include all available fields and metadata +- Use consistent field names and types + +## Pagination Implementation + +For tools that list resources: + +```typescript +const ListSchema = z.object({ + limit: z.number().int().min(1).max(100).default(20), + offset: z.number().int().min(0).default(0) +}); + +async function listItems(params: z.infer) { + const data = await apiRequest(params.limit, params.offset); + + const response = { + total: data.total, + count: data.items.length, + offset: params.offset, + items: data.items, + has_more: data.total > params.offset + data.items.length, + next_offset: data.total > params.offset + data.items.length + ? params.offset + data.items.length + : undefined + }; + + return JSON.stringify(response, null, 2); +} +``` + +## Character Limits and Truncation + +Add a CHARACTER_LIMIT constant to prevent overwhelming responses: + +```typescript +// At module level in constants.ts +export const CHARACTER_LIMIT = 25000; // Maximum response size in characters + +async function searchTool(params: SearchInput) { + let result = generateResponse(data); + + // Check character limit and truncate if needed + if (result.length > CHARACTER_LIMIT) { + const truncatedData = data.slice(0, Math.max(1, data.length / 2)); + response.data = truncatedData; + response.truncated = true; + response.truncation_message = + `Response truncated from ${data.length} to ${truncatedData.length} items. ` + + `Use 'offset' parameter or add filters to see more results.`; + result = JSON.stringify(response, null, 2); + } + + return result; +} +``` + +## Error Handling + +Provide clear, actionable error messages: + +```typescript +import axios, { AxiosError } from "axios"; + +function handleApiError(error: unknown): string { + if (error instanceof AxiosError) { + if (error.response) { + switch (error.response.status) { + case 404: + return "Error: Resource not found. Please check the ID is correct."; + case 403: + return "Error: Permission denied. You don't have access to this resource."; + case 429: + return "Error: Rate limit exceeded. Please wait before making more requests."; + default: + return `Error: API request failed with status ${error.response.status}`; + } + } else if (error.code === "ECONNABORTED") { + return "Error: Request timed out. Please try again."; + } + } + return `Error: Unexpected error occurred: ${error instanceof Error ? error.message : String(error)}`; +} +``` + +## Shared Utilities + +Extract common functionality into reusable functions: + +```typescript +// Shared API request function +async function makeApiRequest( + endpoint: string, + method: "GET" | "POST" | "PUT" | "DELETE" = "GET", + data?: any, + params?: any +): Promise { + try { + const response = await axios({ + method, + url: `${API_BASE_URL}/${endpoint}`, + data, + params, + timeout: 30000, + headers: { + "Content-Type": "application/json", + "Accept": "application/json" + } + }); + return response.data; + } catch (error) { + throw error; + } +} +``` + +## Async/Await Best Practices + +Always use async/await for network requests and I/O operations: + +```typescript +// Good: Async network request +async function fetchData(resourceId: string): Promise { + const response = await axios.get(`${API_URL}/resource/${resourceId}`); + return response.data; +} + +// Bad: Promise chains +function fetchData(resourceId: string): Promise { + return axios.get(`${API_URL}/resource/${resourceId}`) + .then(response => response.data); // Harder to read and maintain +} +``` + +## TypeScript Best Practices + +1. **Use Strict TypeScript**: Enable strict mode in tsconfig.json +2. **Define Interfaces**: Create clear interface definitions for all data structures +3. **Avoid `any`**: Use proper types or `unknown` instead of `any` +4. **Zod for Runtime Validation**: Use Zod schemas to validate external data +5. **Type Guards**: Create type guard functions for complex type checking +6. **Error Handling**: Always use try-catch with proper error type checking +7. **Null Safety**: Use optional chaining (`?.`) and nullish coalescing (`??`) + +```typescript +// Good: Type-safe with Zod and interfaces +interface UserResponse { + id: string; + name: string; + email: string; + team?: string; + active: boolean; +} + +const UserSchema = z.object({ + id: z.string(), + name: z.string(), + email: z.string().email(), + team: z.string().optional(), + active: z.boolean() +}); + +type User = z.infer; + +async function getUser(id: string): Promise { + const data = await apiCall(`/users/${id}`); + return UserSchema.parse(data); // Runtime validation +} + +// Bad: Using any +async function getUser(id: string): Promise { + return await apiCall(`/users/${id}`); // No type safety +} +``` + +## Package Configuration + +### package.json + +```json +{ + "name": "{service}-mcp-server", + "version": "1.0.0", + "description": "MCP server for {Service} API integration", + "type": "module", + "main": "dist/index.js", + "scripts": { + "start": "node dist/index.js", + "dev": "tsx watch src/index.ts", + "build": "tsc", + "clean": "rm -rf dist" + }, + "engines": { + "node": ">=18" + }, + "dependencies": { + "@modelcontextprotocol/sdk": "^1.6.1", + "axios": "^1.7.9", + "zod": "^3.23.8" + }, + "devDependencies": { + "@types/node": "^22.10.0", + "tsx": "^4.19.2", + "typescript": "^5.7.2" + } +} +``` + +### tsconfig.json + +```json +{ + "compilerOptions": { + "target": "ES2022", + "module": "Node16", + "moduleResolution": "Node16", + "lib": ["ES2022"], + "outDir": "./dist", + "rootDir": "./src", + "strict": true, + "esModuleInterop": true, + "skipLibCheck": true, + "forceConsistentCasingInFileNames": true, + "declaration": true, + "declarationMap": true, + "sourceMap": true, + "allowSyntheticDefaultImports": true + }, + "include": ["src/**/*"], + "exclude": ["node_modules", "dist"] +} +``` + +## Complete Example + +```typescript +#!/usr/bin/env node +/** + * MCP Server for Example Service. + * + * This server provides tools to interact with Example API, including user search, + * project management, and data export capabilities. + */ + +import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; +import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js"; +import { z } from "zod"; +import axios, { AxiosError } from "axios"; + +// Constants +const API_BASE_URL = "https://api.example.com/v1"; +const CHARACTER_LIMIT = 25000; + +// Enums +enum ResponseFormat { + MARKDOWN = "markdown", + JSON = "json" +} + +// Zod schemas +const UserSearchInputSchema = z.object({ + query: z.string() + .min(2, "Query must be at least 2 characters") + .max(200, "Query must not exceed 200 characters") + .describe("Search string to match against names/emails"), + limit: z.number() + .int() + .min(1) + .max(100) + .default(20) + .describe("Maximum results to return"), + offset: z.number() + .int() + .min(0) + .default(0) + .describe("Number of results to skip for pagination"), + response_format: z.nativeEnum(ResponseFormat) + .default(ResponseFormat.MARKDOWN) + .describe("Output format: 'markdown' for human-readable or 'json' for machine-readable") +}).strict(); + +type UserSearchInput = z.infer; + +// Shared utility functions +async function makeApiRequest( + endpoint: string, + method: "GET" | "POST" | "PUT" | "DELETE" = "GET", + data?: any, + params?: any +): Promise { + try { + const response = await axios({ + method, + url: `${API_BASE_URL}/${endpoint}`, + data, + params, + timeout: 30000, + headers: { + "Content-Type": "application/json", + "Accept": "application/json" + } + }); + return response.data; + } catch (error) { + throw error; + } +} + +function handleApiError(error: unknown): string { + if (error instanceof AxiosError) { + if (error.response) { + switch (error.response.status) { + case 404: + return "Error: Resource not found. Please check the ID is correct."; + case 403: + return "Error: Permission denied. You don't have access to this resource."; + case 429: + return "Error: Rate limit exceeded. Please wait before making more requests."; + default: + return `Error: API request failed with status ${error.response.status}`; + } + } else if (error.code === "ECONNABORTED") { + return "Error: Request timed out. Please try again."; + } + } + return `Error: Unexpected error occurred: ${error instanceof Error ? error.message : String(error)}`; +} + +// Create MCP server instance +const server = new McpServer({ + name: "example-mcp", + version: "1.0.0" +}); + +// Register tools +server.registerTool( + "example_search_users", + { + title: "Search Example Users", + description: `[Full description as shown above]`, + inputSchema: UserSearchInputSchema, + annotations: { + readOnlyHint: true, + destructiveHint: false, + idempotentHint: true, + openWorldHint: true + } + }, + async (params: UserSearchInput) => { + // Implementation as shown above + } +); + +// Main function +// For stdio (local): +async function runStdio() { + if (!process.env.EXAMPLE_API_KEY) { + console.error("ERROR: EXAMPLE_API_KEY environment variable is required"); + process.exit(1); + } + + const transport = new StdioServerTransport(); + await server.connect(transport); + console.error("MCP server running via stdio"); +} + +// For streamable HTTP (remote): +async function runHTTP() { + if (!process.env.EXAMPLE_API_KEY) { + console.error("ERROR: EXAMPLE_API_KEY environment variable is required"); + process.exit(1); + } + + const app = express(); + app.use(express.json()); + + app.post('/mcp', async (req, res) => { + const transport = new StreamableHTTPServerTransport({ + sessionIdGenerator: undefined, + enableJsonResponse: true + }); + res.on('close', () => transport.close()); + await server.connect(transport); + await transport.handleRequest(req, res, req.body); + }); + + const port = parseInt(process.env.PORT || '3000'); + app.listen(port, () => { + console.error(`MCP server running on http://localhost:${port}/mcp`); + }); +} + +// Choose transport based on environment +const transport = process.env.TRANSPORT || 'stdio'; +if (transport === 'http') { + runHTTP().catch(error => { + console.error("Server error:", error); + process.exit(1); + }); +} else { + runStdio().catch(error => { + console.error("Server error:", error); + process.exit(1); + }); +} +``` + +--- + +## Advanced MCP Features + +### Resource Registration + +Expose data as resources for efficient, URI-based access: + +```typescript +import { ResourceTemplate } from "@modelcontextprotocol/sdk/types.js"; + +// Register a resource with URI template +server.registerResource( + { + uri: "file://documents/{name}", + name: "Document Resource", + description: "Access documents by name", + mimeType: "text/plain" + }, + async (uri: string) => { + // Extract parameter from URI + const match = uri.match(/^file:\/\/documents\/(.+)$/); + if (!match) { + throw new Error("Invalid URI format"); + } + + const documentName = match[1]; + const content = await loadDocument(documentName); + + return { + contents: [{ + uri, + mimeType: "text/plain", + text: content + }] + }; + } +); + +// List available resources dynamically +server.registerResourceList(async () => { + const documents = await getAvailableDocuments(); + return { + resources: documents.map(doc => ({ + uri: `file://documents/${doc.name}`, + name: doc.name, + mimeType: "text/plain", + description: doc.description + })) + }; +}); +``` + +**When to use Resources vs Tools:** +- **Resources**: For data access with simple URI-based parameters +- **Tools**: For complex operations requiring validation and business logic +- **Resources**: When data is relatively static or template-based +- **Tools**: When operations have side effects or complex workflows + +### Transport Options + +The TypeScript SDK supports two main transport mechanisms: + +#### Streamable HTTP (Recommended for Remote Servers) + +```typescript +import { StreamableHTTPServerTransport } from "@modelcontextprotocol/sdk/server/streamableHttp.js"; +import express from "express"; + +const app = express(); +app.use(express.json()); + +app.post('/mcp', async (req, res) => { + // Create new transport for each request (stateless, prevents request ID collisions) + const transport = new StreamableHTTPServerTransport({ + sessionIdGenerator: undefined, + enableJsonResponse: true + }); + + res.on('close', () => transport.close()); + + await server.connect(transport); + await transport.handleRequest(req, res, req.body); +}); + +app.listen(3000); +``` + +#### stdio (For Local Integrations) + +```typescript +import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js"; + +const transport = new StdioServerTransport(); +await server.connect(transport); +``` + +**Transport selection:** +- **Streamable HTTP**: Web services, remote access, multiple clients +- **stdio**: Command-line tools, local development, subprocess integration + +### Notification Support + +Notify clients when server state changes: + +```typescript +// Notify when tools list changes +server.notification({ + method: "notifications/tools/list_changed" +}); + +// Notify when resources change +server.notification({ + method: "notifications/resources/list_changed" +}); +``` + +Use notifications sparingly - only when server capabilities genuinely change. + +--- + +## Code Best Practices + +### Code Composability and Reusability + +Your implementation MUST prioritize composability and code reuse: + +1. **Extract Common Functionality**: + - Create reusable helper functions for operations used across multiple tools + - Build shared API clients for HTTP requests instead of duplicating code + - Centralize error handling logic in utility functions + - Extract business logic into dedicated functions that can be composed + - Extract shared markdown or JSON field selection & formatting functionality + +2. **Avoid Duplication**: + - NEVER copy-paste similar code between tools + - If you find yourself writing similar logic twice, extract it into a function + - Common operations like pagination, filtering, field selection, and formatting should be shared + - Authentication/authorization logic should be centralized + +## Building and Running + +Always build your TypeScript code before running: + +```bash +# Build the project +npm run build + +# Run the server +npm start + +# Development with auto-reload +npm run dev +``` + +Always ensure `npm run build` completes successfully before considering the implementation complete. + +## Quality Checklist + +Before finalizing your Node/TypeScript MCP server implementation, ensure: + +### Strategic Design +- [ ] Tools enable complete workflows, not just API endpoint wrappers +- [ ] Tool names reflect natural task subdivisions +- [ ] Response formats optimize for agent context efficiency +- [ ] Human-readable identifiers used where appropriate +- [ ] Error messages guide agents toward correct usage + +### Implementation Quality +- [ ] FOCUSED IMPLEMENTATION: Most important and valuable tools implemented +- [ ] All tools registered using `registerTool` with complete configuration +- [ ] All tools include `title`, `description`, `inputSchema`, and `annotations` +- [ ] Annotations correctly set (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) +- [ ] All tools use Zod schemas for runtime input validation with `.strict()` enforcement +- [ ] All Zod schemas have proper constraints and descriptive error messages +- [ ] All tools have comprehensive descriptions with explicit input/output types +- [ ] Descriptions include return value examples and complete schema documentation +- [ ] Error messages are clear, actionable, and educational + +### TypeScript Quality +- [ ] TypeScript interfaces are defined for all data structures +- [ ] Strict TypeScript is enabled in tsconfig.json +- [ ] No use of `any` type - use `unknown` or proper types instead +- [ ] All async functions have explicit Promise return types +- [ ] Error handling uses proper type guards (e.g., `axios.isAxiosError`, `z.ZodError`) + +### Advanced Features (where applicable) +- [ ] Resources registered for appropriate data endpoints +- [ ] Appropriate transport configured (stdio or streamable HTTP) +- [ ] Notifications implemented for dynamic server capabilities +- [ ] Type-safe with SDK interfaces + +### Project Configuration +- [ ] Package.json includes all necessary dependencies +- [ ] Build script produces working JavaScript in dist/ directory +- [ ] Main entry point is properly configured as dist/index.js +- [ ] Server name follows format: `{service}-mcp-server` +- [ ] tsconfig.json properly configured with strict mode + +### Code Quality +- [ ] Pagination is properly implemented where applicable +- [ ] Large responses check CHARACTER_LIMIT constant and truncate with clear messages +- [ ] Filtering options are provided for potentially large result sets +- [ ] All network operations handle timeouts and connection errors gracefully +- [ ] Common functionality is extracted into reusable functions +- [ ] Return types are consistent across similar operations + +### Testing and Build +- [ ] `npm run build` completes successfully without errors +- [ ] dist/index.js created and executable +- [ ] Server runs: `node dist/index.js --help` +- [ ] All imports resolve correctly +- [ ] Sample tool calls work as expected \ No newline at end of file diff --git a/.claude/skills/mcp-builder/reference/python_mcp_server.md b/.claude/skills/mcp-builder/reference/python_mcp_server.md new file mode 100644 index 0000000..cf7ec99 --- /dev/null +++ b/.claude/skills/mcp-builder/reference/python_mcp_server.md @@ -0,0 +1,719 @@ +# Python MCP Server Implementation Guide + +## Overview + +This document provides Python-specific best practices and examples for implementing MCP servers using the MCP Python SDK. It covers server setup, tool registration patterns, input validation with Pydantic, error handling, and complete working examples. + +--- + +## Quick Reference + +### Key Imports +```python +from mcp.server.fastmcp import FastMCP +from pydantic import BaseModel, Field, field_validator, ConfigDict +from typing import Optional, List, Dict, Any +from enum import Enum +import httpx +``` + +### Server Initialization +```python +mcp = FastMCP("service_mcp") +``` + +### Tool Registration Pattern +```python +@mcp.tool(name="tool_name", annotations={...}) +async def tool_function(params: InputModel) -> str: + # Implementation + pass +``` + +--- + +## MCP Python SDK and FastMCP + +The official MCP Python SDK provides FastMCP, a high-level framework for building MCP servers. It provides: +- Automatic description and inputSchema generation from function signatures and docstrings +- Pydantic model integration for input validation +- Decorator-based tool registration with `@mcp.tool` + +**For complete SDK documentation, use WebFetch to load:** +`https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md` + +## Server Naming Convention + +Python MCP servers must follow this naming pattern: +- **Format**: `{service}_mcp` (lowercase with underscores) +- **Examples**: `github_mcp`, `jira_mcp`, `stripe_mcp` + +The name should be: +- General (not tied to specific features) +- Descriptive of the service/API being integrated +- Easy to infer from the task description +- Without version numbers or dates + +## Tool Implementation + +### Tool Naming + +Use snake_case for tool names (e.g., "search_users", "create_project", "get_channel_info") with clear, action-oriented names. + +**Avoid Naming Conflicts**: Include the service context to prevent overlaps: +- Use "slack_send_message" instead of just "send_message" +- Use "github_create_issue" instead of just "create_issue" +- Use "asana_list_tasks" instead of just "list_tasks" + +### Tool Structure with FastMCP + +Tools are defined using the `@mcp.tool` decorator with Pydantic models for input validation: + +```python +from pydantic import BaseModel, Field, ConfigDict +from mcp.server.fastmcp import FastMCP + +# Initialize the MCP server +mcp = FastMCP("example_mcp") + +# Define Pydantic model for input validation +class ServiceToolInput(BaseModel): + '''Input model for service tool operation.''' + model_config = ConfigDict( + str_strip_whitespace=True, # Auto-strip whitespace from strings + validate_assignment=True, # Validate on assignment + extra='forbid' # Forbid extra fields + ) + + param1: str = Field(..., description="First parameter description (e.g., 'user123', 'project-abc')", min_length=1, max_length=100) + param2: Optional[int] = Field(default=None, description="Optional integer parameter with constraints", ge=0, le=1000) + tags: Optional[List[str]] = Field(default_factory=list, description="List of tags to apply", max_items=10) + +@mcp.tool( + name="service_tool_name", + annotations={ + "title": "Human-Readable Tool Title", + "readOnlyHint": True, # Tool does not modify environment + "destructiveHint": False, # Tool does not perform destructive operations + "idempotentHint": True, # Repeated calls have no additional effect + "openWorldHint": False # Tool does not interact with external entities + } +) +async def service_tool_name(params: ServiceToolInput) -> str: + '''Tool description automatically becomes the 'description' field. + + This tool performs a specific operation on the service. It validates all inputs + using the ServiceToolInput Pydantic model before processing. + + Args: + params (ServiceToolInput): Validated input parameters containing: + - param1 (str): First parameter description + - param2 (Optional[int]): Optional parameter with default + - tags (Optional[List[str]]): List of tags + + Returns: + str: JSON-formatted response containing operation results + ''' + # Implementation here + pass +``` + +## Pydantic v2 Key Features + +- Use `model_config` instead of nested `Config` class +- Use `field_validator` instead of deprecated `validator` +- Use `model_dump()` instead of deprecated `dict()` +- Validators require `@classmethod` decorator +- Type hints are required for validator methods + +```python +from pydantic import BaseModel, Field, field_validator, ConfigDict + +class CreateUserInput(BaseModel): + model_config = ConfigDict( + str_strip_whitespace=True, + validate_assignment=True + ) + + name: str = Field(..., description="User's full name", min_length=1, max_length=100) + email: str = Field(..., description="User's email address", pattern=r'^[\w\.-]+@[\w\.-]+\.\w+$') + age: int = Field(..., description="User's age", ge=0, le=150) + + @field_validator('email') + @classmethod + def validate_email(cls, v: str) -> str: + if not v.strip(): + raise ValueError("Email cannot be empty") + return v.lower() +``` + +## Response Format Options + +Support multiple output formats for flexibility: + +```python +from enum import Enum + +class ResponseFormat(str, Enum): + '''Output format for tool responses.''' + MARKDOWN = "markdown" + JSON = "json" + +class UserSearchInput(BaseModel): + query: str = Field(..., description="Search query") + response_format: ResponseFormat = Field( + default=ResponseFormat.MARKDOWN, + description="Output format: 'markdown' for human-readable or 'json' for machine-readable" + ) +``` + +**Markdown format**: +- Use headers, lists, and formatting for clarity +- Convert timestamps to human-readable format (e.g., "2024-01-15 10:30:00 UTC" instead of epoch) +- Show display names with IDs in parentheses (e.g., "@john.doe (U123456)") +- Omit verbose metadata (e.g., show only one profile image URL, not all sizes) +- Group related information logically + +**JSON format**: +- Return complete, structured data suitable for programmatic processing +- Include all available fields and metadata +- Use consistent field names and types + +## Pagination Implementation + +For tools that list resources: + +```python +class ListInput(BaseModel): + limit: Optional[int] = Field(default=20, description="Maximum results to return", ge=1, le=100) + offset: Optional[int] = Field(default=0, description="Number of results to skip for pagination", ge=0) + +async def list_items(params: ListInput) -> str: + # Make API request with pagination + data = await api_request(limit=params.limit, offset=params.offset) + + # Return pagination info + response = { + "total": data["total"], + "count": len(data["items"]), + "offset": params.offset, + "items": data["items"], + "has_more": data["total"] > params.offset + len(data["items"]), + "next_offset": params.offset + len(data["items"]) if data["total"] > params.offset + len(data["items"]) else None + } + return json.dumps(response, indent=2) +``` + +## Error Handling + +Provide clear, actionable error messages: + +```python +def _handle_api_error(e: Exception) -> str: + '''Consistent error formatting across all tools.''' + if isinstance(e, httpx.HTTPStatusError): + if e.response.status_code == 404: + return "Error: Resource not found. Please check the ID is correct." + elif e.response.status_code == 403: + return "Error: Permission denied. You don't have access to this resource." + elif e.response.status_code == 429: + return "Error: Rate limit exceeded. Please wait before making more requests." + return f"Error: API request failed with status {e.response.status_code}" + elif isinstance(e, httpx.TimeoutException): + return "Error: Request timed out. Please try again." + return f"Error: Unexpected error occurred: {type(e).__name__}" +``` + +## Shared Utilities + +Extract common functionality into reusable functions: + +```python +# Shared API request function +async def _make_api_request(endpoint: str, method: str = "GET", **kwargs) -> dict: + '''Reusable function for all API calls.''' + async with httpx.AsyncClient() as client: + response = await client.request( + method, + f"{API_BASE_URL}/{endpoint}", + timeout=30.0, + **kwargs + ) + response.raise_for_status() + return response.json() +``` + +## Async/Await Best Practices + +Always use async/await for network requests and I/O operations: + +```python +# Good: Async network request +async def fetch_data(resource_id: str) -> dict: + async with httpx.AsyncClient() as client: + response = await client.get(f"{API_URL}/resource/{resource_id}") + response.raise_for_status() + return response.json() + +# Bad: Synchronous request +def fetch_data(resource_id: str) -> dict: + response = requests.get(f"{API_URL}/resource/{resource_id}") # Blocks + return response.json() +``` + +## Type Hints + +Use type hints throughout: + +```python +from typing import Optional, List, Dict, Any + +async def get_user(user_id: str) -> Dict[str, Any]: + data = await fetch_user(user_id) + return {"id": data["id"], "name": data["name"]} +``` + +## Tool Docstrings + +Every tool must have comprehensive docstrings with explicit type information: + +```python +async def search_users(params: UserSearchInput) -> str: + ''' + Search for users in the Example system by name, email, or team. + + This tool searches across all user profiles in the Example platform, + supporting partial matches and various search filters. It does NOT + create or modify users, only searches existing ones. + + Args: + params (UserSearchInput): Validated input parameters containing: + - query (str): Search string to match against names/emails (e.g., "john", "@example.com", "team:marketing") + - limit (Optional[int]): Maximum results to return, between 1-100 (default: 20) + - offset (Optional[int]): Number of results to skip for pagination (default: 0) + + Returns: + str: JSON-formatted string containing search results with the following schema: + + Success response: + { + "total": int, # Total number of matches found + "count": int, # Number of results in this response + "offset": int, # Current pagination offset + "users": [ + { + "id": str, # User ID (e.g., "U123456789") + "name": str, # Full name (e.g., "John Doe") + "email": str, # Email address (e.g., "john@example.com") + "team": str # Team name (e.g., "Marketing") - optional + } + ] + } + + Error response: + "Error: " or "No users found matching ''" + + Examples: + - Use when: "Find all marketing team members" -> params with query="team:marketing" + - Use when: "Search for John's account" -> params with query="john" + - Don't use when: You need to create a user (use example_create_user instead) + - Don't use when: You have a user ID and need full details (use example_get_user instead) + + Error Handling: + - Input validation errors are handled by Pydantic model + - Returns "Error: Rate limit exceeded" if too many requests (429 status) + - Returns "Error: Invalid API authentication" if API key is invalid (401 status) + - Returns formatted list of results or "No users found matching 'query'" + ''' +``` + +## Complete Example + +See below for a complete Python MCP server example: + +```python +#!/usr/bin/env python3 +''' +MCP Server for Example Service. + +This server provides tools to interact with Example API, including user search, +project management, and data export capabilities. +''' + +from typing import Optional, List, Dict, Any +from enum import Enum +import httpx +from pydantic import BaseModel, Field, field_validator, ConfigDict +from mcp.server.fastmcp import FastMCP + +# Initialize the MCP server +mcp = FastMCP("example_mcp") + +# Constants +API_BASE_URL = "https://api.example.com/v1" + +# Enums +class ResponseFormat(str, Enum): + '''Output format for tool responses.''' + MARKDOWN = "markdown" + JSON = "json" + +# Pydantic Models for Input Validation +class UserSearchInput(BaseModel): + '''Input model for user search operations.''' + model_config = ConfigDict( + str_strip_whitespace=True, + validate_assignment=True + ) + + query: str = Field(..., description="Search string to match against names/emails", min_length=2, max_length=200) + limit: Optional[int] = Field(default=20, description="Maximum results to return", ge=1, le=100) + offset: Optional[int] = Field(default=0, description="Number of results to skip for pagination", ge=0) + response_format: ResponseFormat = Field(default=ResponseFormat.MARKDOWN, description="Output format") + + @field_validator('query') + @classmethod + def validate_query(cls, v: str) -> str: + if not v.strip(): + raise ValueError("Query cannot be empty or whitespace only") + return v.strip() + +# Shared utility functions +async def _make_api_request(endpoint: str, method: str = "GET", **kwargs) -> dict: + '''Reusable function for all API calls.''' + async with httpx.AsyncClient() as client: + response = await client.request( + method, + f"{API_BASE_URL}/{endpoint}", + timeout=30.0, + **kwargs + ) + response.raise_for_status() + return response.json() + +def _handle_api_error(e: Exception) -> str: + '''Consistent error formatting across all tools.''' + if isinstance(e, httpx.HTTPStatusError): + if e.response.status_code == 404: + return "Error: Resource not found. Please check the ID is correct." + elif e.response.status_code == 403: + return "Error: Permission denied. You don't have access to this resource." + elif e.response.status_code == 429: + return "Error: Rate limit exceeded. Please wait before making more requests." + return f"Error: API request failed with status {e.response.status_code}" + elif isinstance(e, httpx.TimeoutException): + return "Error: Request timed out. Please try again." + return f"Error: Unexpected error occurred: {type(e).__name__}" + +# Tool definitions +@mcp.tool( + name="example_search_users", + annotations={ + "title": "Search Example Users", + "readOnlyHint": True, + "destructiveHint": False, + "idempotentHint": True, + "openWorldHint": True + } +) +async def example_search_users(params: UserSearchInput) -> str: + '''Search for users in the Example system by name, email, or team. + + [Full docstring as shown above] + ''' + try: + # Make API request using validated parameters + data = await _make_api_request( + "users/search", + params={ + "q": params.query, + "limit": params.limit, + "offset": params.offset + } + ) + + users = data.get("users", []) + total = data.get("total", 0) + + if not users: + return f"No users found matching '{params.query}'" + + # Format response based on requested format + if params.response_format == ResponseFormat.MARKDOWN: + lines = [f"# User Search Results: '{params.query}'", ""] + lines.append(f"Found {total} users (showing {len(users)})") + lines.append("") + + for user in users: + lines.append(f"## {user['name']} ({user['id']})") + lines.append(f"- **Email**: {user['email']}") + if user.get('team'): + lines.append(f"- **Team**: {user['team']}") + lines.append("") + + return "\n".join(lines) + + else: + # Machine-readable JSON format + import json + response = { + "total": total, + "count": len(users), + "offset": params.offset, + "users": users + } + return json.dumps(response, indent=2) + + except Exception as e: + return _handle_api_error(e) + +if __name__ == "__main__": + mcp.run() +``` + +--- + +## Advanced FastMCP Features + +### Context Parameter Injection + +FastMCP can automatically inject a `Context` parameter into tools for advanced capabilities like logging, progress reporting, resource reading, and user interaction: + +```python +from mcp.server.fastmcp import FastMCP, Context + +mcp = FastMCP("example_mcp") + +@mcp.tool() +async def advanced_search(query: str, ctx: Context) -> str: + '''Advanced tool with context access for logging and progress.''' + + # Report progress for long operations + await ctx.report_progress(0.25, "Starting search...") + + # Log information for debugging + await ctx.log_info("Processing query", {"query": query, "timestamp": datetime.now()}) + + # Perform search + results = await search_api(query) + await ctx.report_progress(0.75, "Formatting results...") + + # Access server configuration + server_name = ctx.fastmcp.name + + return format_results(results) + +@mcp.tool() +async def interactive_tool(resource_id: str, ctx: Context) -> str: + '''Tool that can request additional input from users.''' + + # Request sensitive information when needed + api_key = await ctx.elicit( + prompt="Please provide your API key:", + input_type="password" + ) + + # Use the provided key + return await api_call(resource_id, api_key) +``` + +**Context capabilities:** +- `ctx.report_progress(progress, message)` - Report progress for long operations +- `ctx.log_info(message, data)` / `ctx.log_error()` / `ctx.log_debug()` - Logging +- `ctx.elicit(prompt, input_type)` - Request input from users +- `ctx.fastmcp.name` - Access server configuration +- `ctx.read_resource(uri)` - Read MCP resources + +### Resource Registration + +Expose data as resources for efficient, template-based access: + +```python +@mcp.resource("file://documents/{name}") +async def get_document(name: str) -> str: + '''Expose documents as MCP resources. + + Resources are useful for static or semi-static data that doesn't + require complex parameters. They use URI templates for flexible access. + ''' + document_path = f"./docs/{name}" + with open(document_path, "r") as f: + return f.read() + +@mcp.resource("config://settings/{key}") +async def get_setting(key: str, ctx: Context) -> str: + '''Expose configuration as resources with context.''' + settings = await load_settings() + return json.dumps(settings.get(key, {})) +``` + +**When to use Resources vs Tools:** +- **Resources**: For data access with simple parameters (URI templates) +- **Tools**: For complex operations with validation and business logic + +### Structured Output Types + +FastMCP supports multiple return types beyond strings: + +```python +from typing import TypedDict +from dataclasses import dataclass +from pydantic import BaseModel + +# TypedDict for structured returns +class UserData(TypedDict): + id: str + name: str + email: str + +@mcp.tool() +async def get_user_typed(user_id: str) -> UserData: + '''Returns structured data - FastMCP handles serialization.''' + return {"id": user_id, "name": "John Doe", "email": "john@example.com"} + +# Pydantic models for complex validation +class DetailedUser(BaseModel): + id: str + name: str + email: str + created_at: datetime + metadata: Dict[str, Any] + +@mcp.tool() +async def get_user_detailed(user_id: str) -> DetailedUser: + '''Returns Pydantic model - automatically generates schema.''' + user = await fetch_user(user_id) + return DetailedUser(**user) +``` + +### Lifespan Management + +Initialize resources that persist across requests: + +```python +from contextlib import asynccontextmanager + +@asynccontextmanager +async def app_lifespan(): + '''Manage resources that live for the server's lifetime.''' + # Initialize connections, load config, etc. + db = await connect_to_database() + config = load_configuration() + + # Make available to all tools + yield {"db": db, "config": config} + + # Cleanup on shutdown + await db.close() + +mcp = FastMCP("example_mcp", lifespan=app_lifespan) + +@mcp.tool() +async def query_data(query: str, ctx: Context) -> str: + '''Access lifespan resources through context.''' + db = ctx.request_context.lifespan_state["db"] + results = await db.query(query) + return format_results(results) +``` + +### Transport Options + +FastMCP supports two main transport mechanisms: + +```python +# stdio transport (for local tools) - default +if __name__ == "__main__": + mcp.run() + +# Streamable HTTP transport (for remote servers) +if __name__ == "__main__": + mcp.run(transport="streamable_http", port=8000) +``` + +**Transport selection:** +- **stdio**: Command-line tools, local integrations, subprocess execution +- **Streamable HTTP**: Web services, remote access, multiple clients + +--- + +## Code Best Practices + +### Code Composability and Reusability + +Your implementation MUST prioritize composability and code reuse: + +1. **Extract Common Functionality**: + - Create reusable helper functions for operations used across multiple tools + - Build shared API clients for HTTP requests instead of duplicating code + - Centralize error handling logic in utility functions + - Extract business logic into dedicated functions that can be composed + - Extract shared markdown or JSON field selection & formatting functionality + +2. **Avoid Duplication**: + - NEVER copy-paste similar code between tools + - If you find yourself writing similar logic twice, extract it into a function + - Common operations like pagination, filtering, field selection, and formatting should be shared + - Authentication/authorization logic should be centralized + +### Python-Specific Best Practices + +1. **Use Type Hints**: Always include type annotations for function parameters and return values +2. **Pydantic Models**: Define clear Pydantic models for all input validation +3. **Avoid Manual Validation**: Let Pydantic handle input validation with constraints +4. **Proper Imports**: Group imports (standard library, third-party, local) +5. **Error Handling**: Use specific exception types (httpx.HTTPStatusError, not generic Exception) +6. **Async Context Managers**: Use `async with` for resources that need cleanup +7. **Constants**: Define module-level constants in UPPER_CASE + +## Quality Checklist + +Before finalizing your Python MCP server implementation, ensure: + +### Strategic Design +- [ ] Tools enable complete workflows, not just API endpoint wrappers +- [ ] Tool names reflect natural task subdivisions +- [ ] Response formats optimize for agent context efficiency +- [ ] Human-readable identifiers used where appropriate +- [ ] Error messages guide agents toward correct usage + +### Implementation Quality +- [ ] FOCUSED IMPLEMENTATION: Most important and valuable tools implemented +- [ ] All tools have descriptive names and documentation +- [ ] Return types are consistent across similar operations +- [ ] Error handling is implemented for all external calls +- [ ] Server name follows format: `{service}_mcp` +- [ ] All network operations use async/await +- [ ] Common functionality is extracted into reusable functions +- [ ] Error messages are clear, actionable, and educational +- [ ] Outputs are properly validated and formatted + +### Tool Configuration +- [ ] All tools implement 'name' and 'annotations' in the decorator +- [ ] Annotations correctly set (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) +- [ ] All tools use Pydantic BaseModel for input validation with Field() definitions +- [ ] All Pydantic Fields have explicit types and descriptions with constraints +- [ ] All tools have comprehensive docstrings with explicit input/output types +- [ ] Docstrings include complete schema structure for dict/JSON returns +- [ ] Pydantic models handle input validation (no manual validation needed) + +### Advanced Features (where applicable) +- [ ] Context injection used for logging, progress, or elicitation +- [ ] Resources registered for appropriate data endpoints +- [ ] Lifespan management implemented for persistent connections +- [ ] Structured output types used (TypedDict, Pydantic models) +- [ ] Appropriate transport configured (stdio or streamable HTTP) + +### Code Quality +- [ ] File includes proper imports including Pydantic imports +- [ ] Pagination is properly implemented where applicable +- [ ] Filtering options are provided for potentially large result sets +- [ ] All async functions are properly defined with `async def` +- [ ] HTTP client usage follows async patterns with proper context managers +- [ ] Type hints are used throughout the code +- [ ] Constants are defined at module level in UPPER_CASE + +### Testing +- [ ] Server runs successfully: `python your_server.py --help` +- [ ] All imports resolve correctly +- [ ] Sample tool calls work as expected +- [ ] Error scenarios handled gracefully \ No newline at end of file diff --git a/.claude/skills/mcp-builder/scripts/connections.py b/.claude/skills/mcp-builder/scripts/connections.py new file mode 100644 index 0000000..ffcd0da --- /dev/null +++ b/.claude/skills/mcp-builder/scripts/connections.py @@ -0,0 +1,151 @@ +"""Lightweight connection handling for MCP servers.""" + +from abc import ABC, abstractmethod +from contextlib import AsyncExitStack +from typing import Any + +from mcp import ClientSession, StdioServerParameters +from mcp.client.sse import sse_client +from mcp.client.stdio import stdio_client +from mcp.client.streamable_http import streamablehttp_client + + +class MCPConnection(ABC): + """Base class for MCP server connections.""" + + def __init__(self): + self.session = None + self._stack = None + + @abstractmethod + def _create_context(self): + """Create the connection context based on connection type.""" + + async def __aenter__(self): + """Initialize MCP server connection.""" + self._stack = AsyncExitStack() + await self._stack.__aenter__() + + try: + ctx = self._create_context() + result = await self._stack.enter_async_context(ctx) + + if len(result) == 2: + read, write = result + elif len(result) == 3: + read, write, _ = result + else: + raise ValueError(f"Unexpected context result: {result}") + + session_ctx = ClientSession(read, write) + self.session = await self._stack.enter_async_context(session_ctx) + await self.session.initialize() + return self + except BaseException: + await self._stack.__aexit__(None, None, None) + raise + + async def __aexit__(self, exc_type, exc_val, exc_tb): + """Clean up MCP server connection resources.""" + if self._stack: + await self._stack.__aexit__(exc_type, exc_val, exc_tb) + self.session = None + self._stack = None + + async def list_tools(self) -> list[dict[str, Any]]: + """Retrieve available tools from the MCP server.""" + response = await self.session.list_tools() + return [ + { + "name": tool.name, + "description": tool.description, + "input_schema": tool.inputSchema, + } + for tool in response.tools + ] + + async def call_tool(self, tool_name: str, arguments: dict[str, Any]) -> Any: + """Call a tool on the MCP server with provided arguments.""" + result = await self.session.call_tool(tool_name, arguments=arguments) + return result.content + + +class MCPConnectionStdio(MCPConnection): + """MCP connection using standard input/output.""" + + def __init__(self, command: str, args: list[str] = None, env: dict[str, str] = None): + super().__init__() + self.command = command + self.args = args or [] + self.env = env + + def _create_context(self): + return stdio_client( + StdioServerParameters(command=self.command, args=self.args, env=self.env) + ) + + +class MCPConnectionSSE(MCPConnection): + """MCP connection using Server-Sent Events.""" + + def __init__(self, url: str, headers: dict[str, str] = None): + super().__init__() + self.url = url + self.headers = headers or {} + + def _create_context(self): + return sse_client(url=self.url, headers=self.headers) + + +class MCPConnectionHTTP(MCPConnection): + """MCP connection using Streamable HTTP.""" + + def __init__(self, url: str, headers: dict[str, str] = None): + super().__init__() + self.url = url + self.headers = headers or {} + + def _create_context(self): + return streamablehttp_client(url=self.url, headers=self.headers) + + +def create_connection( + transport: str, + command: str = None, + args: list[str] = None, + env: dict[str, str] = None, + url: str = None, + headers: dict[str, str] = None, +) -> MCPConnection: + """Factory function to create the appropriate MCP connection. + + Args: + transport: Connection type ("stdio", "sse", or "http") + command: Command to run (stdio only) + args: Command arguments (stdio only) + env: Environment variables (stdio only) + url: Server URL (sse and http only) + headers: HTTP headers (sse and http only) + + Returns: + MCPConnection instance + """ + transport = transport.lower() + + if transport == "stdio": + if not command: + raise ValueError("Command is required for stdio transport") + return MCPConnectionStdio(command=command, args=args, env=env) + + elif transport == "sse": + if not url: + raise ValueError("URL is required for sse transport") + return MCPConnectionSSE(url=url, headers=headers) + + elif transport in ["http", "streamable_http", "streamable-http"]: + if not url: + raise ValueError("URL is required for http transport") + return MCPConnectionHTTP(url=url, headers=headers) + + else: + raise ValueError(f"Unsupported transport type: {transport}. Use 'stdio', 'sse', or 'http'") diff --git a/.claude/skills/mcp-builder/scripts/evaluation.py b/.claude/skills/mcp-builder/scripts/evaluation.py new file mode 100644 index 0000000..4177856 --- /dev/null +++ b/.claude/skills/mcp-builder/scripts/evaluation.py @@ -0,0 +1,373 @@ +"""MCP Server Evaluation Harness + +This script evaluates MCP servers by running test questions against them using Claude. +""" + +import argparse +import asyncio +import json +import re +import sys +import time +import traceback +import xml.etree.ElementTree as ET +from pathlib import Path +from typing import Any + +from anthropic import Anthropic + +from connections import create_connection + +EVALUATION_PROMPT = """You are an AI assistant with access to tools. + +When given a task, you MUST: +1. Use the available tools to complete the task +2. Provide summary of each step in your approach, wrapped in tags +3. Provide feedback on the tools provided, wrapped in tags +4. Provide your final response, wrapped in tags + +Summary Requirements: +- In your tags, you must explain: + - The steps you took to complete the task + - Which tools you used, in what order, and why + - The inputs you provided to each tool + - The outputs you received from each tool + - A summary for how you arrived at the response + +Feedback Requirements: +- In your tags, provide constructive feedback on the tools: + - Comment on tool names: Are they clear and descriptive? + - Comment on input parameters: Are they well-documented? Are required vs optional parameters clear? + - Comment on descriptions: Do they accurately describe what the tool does? + - Comment on any errors encountered during tool usage: Did the tool fail to execute? Did the tool return too many tokens? + - Identify specific areas for improvement and explain WHY they would help + - Be specific and actionable in your suggestions + +Response Requirements: +- Your response should be concise and directly address what was asked +- Always wrap your final response in tags +- If you cannot solve the task return NOT_FOUND +- For numeric responses, provide just the number +- For IDs, provide just the ID +- For names or text, provide the exact text requested +- Your response should go last""" + + +def parse_evaluation_file(file_path: Path) -> list[dict[str, Any]]: + """Parse XML evaluation file with qa_pair elements.""" + try: + tree = ET.parse(file_path) + root = tree.getroot() + evaluations = [] + + for qa_pair in root.findall(".//qa_pair"): + question_elem = qa_pair.find("question") + answer_elem = qa_pair.find("answer") + + if question_elem is not None and answer_elem is not None: + evaluations.append({ + "question": (question_elem.text or "").strip(), + "answer": (answer_elem.text or "").strip(), + }) + + return evaluations + except Exception as e: + print(f"Error parsing evaluation file {file_path}: {e}") + return [] + + +def extract_xml_content(text: str, tag: str) -> str | None: + """Extract content from XML tags.""" + pattern = rf"<{tag}>(.*?)" + matches = re.findall(pattern, text, re.DOTALL) + return matches[-1].strip() if matches else None + + +async def agent_loop( + client: Anthropic, + model: str, + question: str, + tools: list[dict[str, Any]], + connection: Any, +) -> tuple[str, dict[str, Any]]: + """Run the agent loop with MCP tools.""" + messages = [{"role": "user", "content": question}] + + response = await asyncio.to_thread( + client.messages.create, + model=model, + max_tokens=4096, + system=EVALUATION_PROMPT, + messages=messages, + tools=tools, + ) + + messages.append({"role": "assistant", "content": response.content}) + + tool_metrics = {} + + while response.stop_reason == "tool_use": + tool_use = next(block for block in response.content if block.type == "tool_use") + tool_name = tool_use.name + tool_input = tool_use.input + + tool_start_ts = time.time() + try: + tool_result = await connection.call_tool(tool_name, tool_input) + tool_response = json.dumps(tool_result) if isinstance(tool_result, (dict, list)) else str(tool_result) + except Exception as e: + tool_response = f"Error executing tool {tool_name}: {str(e)}\n" + tool_response += traceback.format_exc() + tool_duration = time.time() - tool_start_ts + + if tool_name not in tool_metrics: + tool_metrics[tool_name] = {"count": 0, "durations": []} + tool_metrics[tool_name]["count"] += 1 + tool_metrics[tool_name]["durations"].append(tool_duration) + + messages.append({ + "role": "user", + "content": [{ + "type": "tool_result", + "tool_use_id": tool_use.id, + "content": tool_response, + }] + }) + + response = await asyncio.to_thread( + client.messages.create, + model=model, + max_tokens=4096, + system=EVALUATION_PROMPT, + messages=messages, + tools=tools, + ) + messages.append({"role": "assistant", "content": response.content}) + + response_text = next( + (block.text for block in response.content if hasattr(block, "text")), + None, + ) + return response_text, tool_metrics + + +async def evaluate_single_task( + client: Anthropic, + model: str, + qa_pair: dict[str, Any], + tools: list[dict[str, Any]], + connection: Any, + task_index: int, +) -> dict[str, Any]: + """Evaluate a single QA pair with the given tools.""" + start_time = time.time() + + print(f"Task {task_index + 1}: Running task with question: {qa_pair['question']}") + response, tool_metrics = await agent_loop(client, model, qa_pair["question"], tools, connection) + + response_value = extract_xml_content(response, "response") + summary = extract_xml_content(response, "summary") + feedback = extract_xml_content(response, "feedback") + + duration_seconds = time.time() - start_time + + return { + "question": qa_pair["question"], + "expected": qa_pair["answer"], + "actual": response_value, + "score": int(response_value == qa_pair["answer"]) if response_value else 0, + "total_duration": duration_seconds, + "tool_calls": tool_metrics, + "num_tool_calls": sum(len(metrics["durations"]) for metrics in tool_metrics.values()), + "summary": summary, + "feedback": feedback, + } + + +REPORT_HEADER = """ +# Evaluation Report + +## Summary + +- **Accuracy**: {correct}/{total} ({accuracy:.1f}%) +- **Average Task Duration**: {average_duration_s:.2f}s +- **Average Tool Calls per Task**: {average_tool_calls:.2f} +- **Total Tool Calls**: {total_tool_calls} + +--- +""" + +TASK_TEMPLATE = """ +### Task {task_num} + +**Question**: {question} +**Ground Truth Answer**: `{expected_answer}` +**Actual Answer**: `{actual_answer}` +**Correct**: {correct_indicator} +**Duration**: {total_duration:.2f}s +**Tool Calls**: {tool_calls} + +**Summary** +{summary} + +**Feedback** +{feedback} + +--- +""" + + +async def run_evaluation( + eval_path: Path, + connection: Any, + model: str = "claude-3-7-sonnet-20250219", +) -> str: + """Run evaluation with MCP server tools.""" + print("🚀 Starting Evaluation") + + client = Anthropic() + + tools = await connection.list_tools() + print(f"📋 Loaded {len(tools)} tools from MCP server") + + qa_pairs = parse_evaluation_file(eval_path) + print(f"📋 Loaded {len(qa_pairs)} evaluation tasks") + + results = [] + for i, qa_pair in enumerate(qa_pairs): + print(f"Processing task {i + 1}/{len(qa_pairs)}") + result = await evaluate_single_task(client, model, qa_pair, tools, connection, i) + results.append(result) + + correct = sum(r["score"] for r in results) + accuracy = (correct / len(results)) * 100 if results else 0 + average_duration_s = sum(r["total_duration"] for r in results) / len(results) if results else 0 + average_tool_calls = sum(r["num_tool_calls"] for r in results) / len(results) if results else 0 + total_tool_calls = sum(r["num_tool_calls"] for r in results) + + report = REPORT_HEADER.format( + correct=correct, + total=len(results), + accuracy=accuracy, + average_duration_s=average_duration_s, + average_tool_calls=average_tool_calls, + total_tool_calls=total_tool_calls, + ) + + report += "".join([ + TASK_TEMPLATE.format( + task_num=i + 1, + question=qa_pair["question"], + expected_answer=qa_pair["answer"], + actual_answer=result["actual"] or "N/A", + correct_indicator="✅" if result["score"] else "❌", + total_duration=result["total_duration"], + tool_calls=json.dumps(result["tool_calls"], indent=2), + summary=result["summary"] or "N/A", + feedback=result["feedback"] or "N/A", + ) + for i, (qa_pair, result) in enumerate(zip(qa_pairs, results)) + ]) + + return report + + +def parse_headers(header_list: list[str]) -> dict[str, str]: + """Parse header strings in format 'Key: Value' into a dictionary.""" + headers = {} + if not header_list: + return headers + + for header in header_list: + if ":" in header: + key, value = header.split(":", 1) + headers[key.strip()] = value.strip() + else: + print(f"Warning: Ignoring malformed header: {header}") + return headers + + +def parse_env_vars(env_list: list[str]) -> dict[str, str]: + """Parse environment variable strings in format 'KEY=VALUE' into a dictionary.""" + env = {} + if not env_list: + return env + + for env_var in env_list: + if "=" in env_var: + key, value = env_var.split("=", 1) + env[key.strip()] = value.strip() + else: + print(f"Warning: Ignoring malformed environment variable: {env_var}") + return env + + +async def main(): + parser = argparse.ArgumentParser( + description="Evaluate MCP servers using test questions", + formatter_class=argparse.RawDescriptionHelpFormatter, + epilog=""" +Examples: + # Evaluate a local stdio MCP server + python evaluation.py -t stdio -c python -a my_server.py eval.xml + + # Evaluate an SSE MCP server + python evaluation.py -t sse -u https://example.com/mcp -H "Authorization: Bearer token" eval.xml + + # Evaluate an HTTP MCP server with custom model + python evaluation.py -t http -u https://example.com/mcp -m claude-3-5-sonnet-20241022 eval.xml + """, + ) + + parser.add_argument("eval_file", type=Path, help="Path to evaluation XML file") + parser.add_argument("-t", "--transport", choices=["stdio", "sse", "http"], default="stdio", help="Transport type (default: stdio)") + parser.add_argument("-m", "--model", default="claude-3-7-sonnet-20250219", help="Claude model to use (default: claude-3-7-sonnet-20250219)") + + stdio_group = parser.add_argument_group("stdio options") + stdio_group.add_argument("-c", "--command", help="Command to run MCP server (stdio only)") + stdio_group.add_argument("-a", "--args", nargs="+", help="Arguments for the command (stdio only)") + stdio_group.add_argument("-e", "--env", nargs="+", help="Environment variables in KEY=VALUE format (stdio only)") + + remote_group = parser.add_argument_group("sse/http options") + remote_group.add_argument("-u", "--url", help="MCP server URL (sse/http only)") + remote_group.add_argument("-H", "--header", nargs="+", dest="headers", help="HTTP headers in 'Key: Value' format (sse/http only)") + + parser.add_argument("-o", "--output", type=Path, help="Output file for evaluation report (default: stdout)") + + args = parser.parse_args() + + if not args.eval_file.exists(): + print(f"Error: Evaluation file not found: {args.eval_file}") + sys.exit(1) + + headers = parse_headers(args.headers) if args.headers else None + env_vars = parse_env_vars(args.env) if args.env else None + + try: + connection = create_connection( + transport=args.transport, + command=args.command, + args=args.args, + env=env_vars, + url=args.url, + headers=headers, + ) + except ValueError as e: + print(f"Error: {e}") + sys.exit(1) + + print(f"🔗 Connecting to MCP server via {args.transport}...") + + async with connection: + print("✅ Connected successfully") + report = await run_evaluation(args.eval_file, connection, args.model) + + if args.output: + args.output.write_text(report) + print(f"\n✅ Report saved to {args.output}") + else: + print("\n" + report) + + +if __name__ == "__main__": + asyncio.run(main()) diff --git a/.claude/skills/mcp-builder/scripts/example_evaluation.xml b/.claude/skills/mcp-builder/scripts/example_evaluation.xml new file mode 100644 index 0000000..41e4459 --- /dev/null +++ b/.claude/skills/mcp-builder/scripts/example_evaluation.xml @@ -0,0 +1,22 @@ + + + Calculate the compound interest on $10,000 invested at 5% annual interest rate, compounded monthly for 3 years. What is the final amount in dollars (rounded to 2 decimal places)? + 11614.72 + + + A projectile is launched at a 45-degree angle with an initial velocity of 50 m/s. Calculate the total distance (in meters) it has traveled from the launch point after 2 seconds, assuming g=9.8 m/s². Round to 2 decimal places. + 87.25 + + + A sphere has a volume of 500 cubic meters. Calculate its surface area in square meters. Round to 2 decimal places. + 304.65 + + + Calculate the population standard deviation of this dataset: [12, 15, 18, 22, 25, 30, 35]. Round to 2 decimal places. + 7.61 + + + Calculate the pH of a solution with a hydrogen ion concentration of 3.5 × 10^-5 M. Round to 2 decimal places. + 4.46 + + diff --git a/.claude/skills/mcp-builder/scripts/requirements.txt b/.claude/skills/mcp-builder/scripts/requirements.txt new file mode 100644 index 0000000..e73e5d1 --- /dev/null +++ b/.claude/skills/mcp-builder/scripts/requirements.txt @@ -0,0 +1,2 @@ +anthropic>=0.39.0 +mcp>=1.1.0 diff --git a/.claude/skills/mcp-container-install-bmad.skill b/.claude/skills/mcp-container-install-bmad.skill new file mode 100644 index 0000000000000000000000000000000000000000..24336d9077555780cd5293018afbecf11dd238f8 GIT binary patch literal 1374 zcmV-k1)=&-O9KQH000080BS~JT*CVt!R!P80PYC@00;m808>jzOiV6qWSv%9Q`<%q ze%G(q5i^;VL3IOdnqfMf;nIgZFq8MTV+lzGwU*?Om^d&C(B9qVG}pk=xe&>?IzuW6r6CQ zTe9`nMI+mK`x8D`xM&o}<`GWs;In$W@Q9R(#%j5JB-*prZ%i%jkK+siZ+En;p#!s59vwb?zhrF|Gx3bUXFB)mGT5?zN7mW7>ooQP~HYGn3D)B4_yOR^f(lzCwms;+m9oSC=^ z<0;Eb#OEV{AKg?EG1Z2X^kBv@&6thkn3Padf%*;RWmDG^h9*mthC)m-rV`SWihx{( zYKKOODJOK*a0D~q#1l?0vl-Q?=MpsTmP_njb*CAk(L;{BMEXx`lda_^R%1(%e7l?O$lkFF5~=pQNMdD%e4iw+BCl zA2-hg7*_nUhxw{wO^WHnOJ)FC4k*Ol-=jtDQg+>X6VS~DtKPErt@zZRpeu&pn?%^Yxeo8ru_X{j8Mp`eqg>yBq_6qAjF!2i11M~=% z8>8-JZlQYLo7=S}(5?QUAuzLqWt*07;g5imUtTdVOv87;R2YO3uKVFJ1&86Wdj>8~ zHcj&il|O())tHKD_B0&=ISo2Qa8q6u*L$6HtEuoZ3@)QemZbAIzseRvE&5jva1q#q zqLjK34j32=W%!_ghw-g8_0f!^#~6jk?hCTJ!x|5DBOsBPLlip|+}yzBZMb#meAiyM zQL~FU{~IaqK^N+z#!%?GIZsa9!<4sG@m_8Rh4ZiMpeOkL$uAAu$U$OVb8y$<{EE+# zXB4jgB3;M{`XPMhuxwa+ff}O0p&{yPaBxU~p%69|;f@Gqo%Vx1`ScDoyA5VA6oO_W zd?s>#15ir=0u%!j000080BS~JT*CVt!R!P80PYC@00;m800000000000HlEc0000} gOG!*jE^TB`O9ci1000010096t0000I1poj507~|Q-T(jq literal 0 HcmV?d00001 diff --git a/.claude/skills/mcp-container-install-bmad/SKILL.md b/.claude/skills/mcp-container-install-bmad/SKILL.md new file mode 100644 index 0000000..e217fe0 --- /dev/null +++ b/.claude/skills/mcp-container-install-bmad/SKILL.md @@ -0,0 +1,158 @@ +--- +name: mcp-container-install-bmad +description: 在 D8D 开发容器中安装 BMAD (Build More, Architect Dreams)。使用此技能当用户需要在容器中安装 BMAD 时，例如：新创建的模板/项目、需要配置 BMAD 环境的容器、或明确提到"安装 BMAD"、"安装 bmad-method"等关键词时触发。 +--- + +# MCP 容器 BMAD 安装 + +## 概述 + +在 D8D 开发容器中使用 `npx bmad-method install` 安装 BMAD 平台，支持自定义安装参数。 + +--- + +## 安装命令 + +### 默认安装（推荐） + +```bash +npx bmad-method install \ + --directory /mnt/code/{workspace_id}-{item_id}-{item_type}-{group}/ \ + --modules bmm \ + --tools claude-code \ + --communication-language chinese \ + --document-output-language chinese \ + --yes +``` + +**默认参数说明：** +| 参数 | 值 | 说明 | +|------|------|------| +| `--modules` | `bmm` | 安装 BMAD Method 模块（敏捷 AI 驱动开发） | +| `--tools` | `claude-code` | 配置 Claude Code 工具 | +| `--communication-language` | `chinese` | 代理沟通语言为中文 | +| `--document-output-language` | `chinese` | 文档输出语言为中文 | +| `--yes` | - | 跳过确认提示 | + +--- + +## 使用 MCP 工具执行 + +### 方式 1：标准安装（推荐首选） + +```typescript +{ + "workspace_id": <工作空间 ID>, + "item_id": <模板/项目 ID>, + "item_type": "template" 或 "project", + "command": ["/bin/sh", "-c", "cd /mnt/code/{workspace_id}-{item_id}-{item_type}-{group}/ && npx bmad-method install --directory /mnt/code/{workspace_id}-{item_id}-{item_type}-{group}/ --modules bmm --tools claude-code --communication-language chinese --document-output-language chinese --yes"], + "timeout": 120000 +} +``` + +### 方式 2：管道输入（备用方案） + +**⚠️ 当 `--yes` 参数不完整时使用此方式** + +BMAD 6.x 的 `--yes` 参数可能无法处理所有交互式提示。此时使用管道输入自动填写剩余提示： + +```typescript +{ + "workspace_id": <工作空间 ID>, + "item_id": <模板/项目 ID>, + "item_type": "template" 或 "project", + "command": ["/bin/sh", "-c", "cd /mnt/code/{workspace_id}-{item_id}-{item_type}-{group}/ && echo -e 'Root\\n' | npx bmad-method install --directory /mnt/code/{workspace_id}-{item_id}-{item_type}-{group}/ --modules bmm --tools claude-code --communication-language chinese --document-output-language chinese --yes"], + "timeout": 300000 +} +``` + +**管道输入说明：** +- `echo -e 'Root\\n'` - 自动填写 "What should agents call you?" 提示 +- `\\n` - 模拟回车键确认 +- 如有多个提示，用 `\\n` 分隔：`echo -e 'No\\nRoot\\n'` + +**需要处理的交互式提示：** +1. "Add custom modules..." → 输入 `No` 或直接回车（`--yes` 已处理） +2. "What should agents call you?" → 输入用户名（如 `Root`） +3. 其他确认提示 → `--yes` 已处理 + +--- + +## 自定义参数 + +### 模块选项 + +| 模块 | 说明 | +|------|------| +| `bmm` | BMAD Method - 敏捷 AI 驱动开发工作流 | +| `bmb` | BMAD Business - 业务分析和产品规划 | + +多模块使用逗号分隔：`--modules bmm,bmb` + +### 工具选项 + +| 工具 | 说明 | +|------|------| +| `claude-code` | Claude Code 配置 | +| `cursor` | Cursor IDE 配置 | +| `none` | 跳过工具配置 | + +### 语言选项 + +支持的语言：`chinese`, `english`, `spanish` 等 + +--- + +## 验证安装 + +安装完成后验证： + +```bash +ls -la _bmad/ +cat _bmad/core/config.yaml +``` + +期望输出： +- `_bmad/` 目录存在 +- `config.yaml` 包含正确的语言配置 + +--- + +## 常见问题 + +### `--yes` 参数不完整怎么办？ + +**现象：** BMAD 6.x 的 `--yes` 参数可能无法跳过所有交互式提示，安装过程会卡住等待输入。 + +**解决方案：** 使用**方式 2（管道输入）**备用方案，通过 `echo -e` 预填充剩余提示。 + +**推荐流程：** +1. 先尝试方式 1（标准安装） +2. 如果卡住，Ctrl+C 中断，改用方式 2（管道输入） + +### 容器工作目录格式 + +工作目录命名规则：`{workspace_id}-{item_id}-{item_type}-{group}` + +示例： +- 模板 ID 233：`223-233-template-6` +- 项目 ID 456：`123-456-project-7` + +### 安装后验证 + +```bash +ls -la _bmad/ +cat _bmad/core/config.yaml +``` + +期望输出： +- `_bmad/` 目录存在 +- `config.yaml` 包含 `communication_language: chinese` +- `bmm/` 目录存在，包含技能和代理 + +### 安装失败怎么办？ + +1. 检查网络连接：`ping -c 3 registry.npmjs.org` +2. 清理缓存重试：`rm -rf _bmad/` 后重新安装 +3. 检查磁盘空间：`df -h /mnt/code/` +4. 查看完整错误日志 diff --git a/.claude/skills/mcp-d8d-admin-install/SKILL.md b/.claude/skills/mcp-d8d-admin-install/SKILL.md new file mode 100644 index 0000000..fa375db --- /dev/null +++ b/.claude/skills/mcp-d8d-admin-install/SKILL.md @@ -0,0 +1,491 @@ +--- +name: mcp-d8d-admin-install +description: "帮助管理员用户在 Claude Code 中配置和安装 D8D Admin MCP 服务器连接。当用户需要配置 Admin MCP 连接、获取管理员认证 token、或排查 Admin MCP 连接问题时触发。注意：此技能仅适用于管理员用户 ID 1、6、26。" +--- + +# D8D Admin MCP 服务器安装配置 + +## 概述 + +D8D Admin MCP 服务器提供了通过 Model Context Protocol (MCP) 访问 D8D 平台管理员功能的能力。与普通 D8D MCP 不同，Admin MCP 允许执行跨用户的管理操作，如查询所有工作空间、强制停止容器等。 + +**⚠️ 重要：Admin MCP 仅限管理员用户使用，需要管理员权限验证。** + +--- + +## 服务器信息 + +| 配置项 | 值 | +|--------|-----| +| **Admin MCP 端点** | `http://localhost:23957/mcp-admin` | +| **传输协议** | HTTP | +| **认证方式** | Bearer Token + 管理员权限双重验证 | +| **管理员用户 ID** | `1, 6, 26` | + +--- + +## 🔍 第一步：检查本地环境配置 + +**⚠️ 重要**：不同的 Git Worktree 可能有不同的本地配置，必须先检查当前 worktree 的环境变量。 + +### 检查本地配置文件 + +```bash +# 检查当前 worktree 中是否存在本地配置文件 +echo "=== 检查本地配置文件 ===" + +# 按优先级检查配置文件 +if [ -f .env.local ]; then + echo "✅ 找到 .env.local" + cat .env.local | grep -E "(D8D|API|PORT|ADMIN)" || true +elif [ -f .env ]; then + echo "✅ 找到 .env" + cat .env | grep -E "(D8D|API|PORT|ADMIN)" || true +else + echo "ℹ️ 未找到本地配置文件，使用默认配置" +fi +``` + +### 从配置文件读取端点 + +```bash +# 读取本地配置（如果存在） +if [ -f .env.local ]; then + source .env.local +elif [ -f .env ]; then + source .env +fi + +# 使用本地配置或默认值 +D8D_API_URL=${D8D_API_URL:-"http://localhost:23957"} +D8D_ADMIN_PORT=${D8D_ADMIN_PORT:-"23957"} +D8D_ADMIN_PHONE=${D8D_ADMIN_PHONE:-"18617351030"} +D8D_ADMIN_CODE=${D8D_ADMIN_CODE:-"220290"} + +echo "使用配置：" +echo " API URL: $D8D_API_URL" +echo " 端口: $D8D_ADMIN_PORT" +echo " 测试账号: $D8D_ADMIN_PHONE" +``` + +### 配置文件示例 + +如果需要在 worktree 中创建本地配置，可以创建 `.env.local`： + +```bash +# .env.local - Worktree 本地配置 +D8D_API_URL=http://localhost:23957 +D8D_ADMIN_PORT=23957 +D8D_ADMIN_PHONE=18617351030 +D8D_ADMIN_CODE=220290 +``` + +--- + +## 获取认证 Token + +### 方法 1：使用测试账号（推荐） + +D8D 提供固定验证码测试账号： + +| 项目 | 值 | +|------|-----| +| **手机号** | `18617351030` | +| **验证码** | `220290`（固定验证码） | + +### 方法 2：通过 API 获取 Token + +```bash +curl -X POST http://localhost:23957/api/v1/auth/login/sms \ + -H "Content-Type: application/json" \ + -d '{"phone":"18617351030","code":"220290"}' +``` + +**响应示例：** +```json +{ + "code": 0, + "message": "success", + "data": { + "token": "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9...", + "user": { + "id": 1, + "phone": "18617351030" + } + } +} +``` + +**⚠️ 权限检查：** 登录后，系统会验证用户 ID 是否在管理员列表中（[1, 6, 26]）。非管理员用户无法访问 Admin MCP。 + +复制返回的 `token` 值用于 MCP 配置。 + +--- + +## Claude MCP 配置 + +### ⚠️ 重要：Worktree 目录配置 + +如果你在 **Git Worktree** 中工作（例如 `/mnt/code-fast/d8d-worktrees/merge-epics`），使用 Claude Code CLI 配置时可能会将配置添加到原始仓库目录。 + +**推荐方式：直接编辑配置文件**（适用于所有场景） + +```bash +# 0. 先加载本地配置（如果有） +if [ -f .env.local ]; then + source .env.local +elif [ -f .env ]; then + source .env +fi + +# 使用本地配置或默认值 +D8D_API_URL=${D8D_API_URL:-"http://localhost:23957"} +D8D_ADMIN_PHONE=${D8D_ADMIN_PHONE:-"18617351030"} +D8D_ADMIN_CODE=${D8D_ADMIN_CODE:-"220290"} + +# 1. 获取当前工作目录 +PROJECT_DIR=$(pwd) + +# 2. 获取 Token（使用本地配置的端点和账号） +TOKEN=$(curl -s -X POST $D8D_API_URL/api/v1/auth/login/sms \ + -H "Content-Type: application/json" \ + -d "{\"phone\":\"$D8D_ADMIN_PHONE\",\"code\":\"$D8D_ADMIN_CODE\"}" | jq -r '.token') + +# 3. 添加配置（使用 jq 直接编辑） +jq --arg dir "$PROJECT_DIR" --arg token "$TOKEN" --arg url "$D8D_API_URL" \ + '.projects[$dir] = { + "allowedTools": [], + "mcpContextUris": [], + "mcpServers": { + "d8d-admin": { + "type": "http", + "url": "\($url)/mcp-admin", + "headers": { + "Authorization": "Bearer \($token)" + } + } + }, + "enabledMcpjsonServers": [], + "disabledMcpjsonServers": [], + "hasTrustDialogAccepted": false, + "projectOnboardingSeenCount": 0, + "hasClaudeMdExternalIncludesApproved": false, + "hasClaudeMdExternalIncludesWarningShown": false + }' ~/.claude.json > /tmp/claude-new.json && mv /tmp/claude-new.json ~/.claude.json +``` + +### 使用 Claude Code CLI 配置（项目级别） + +**说明**：使用 `--scope project` 会在项目目录下**自动生成** `.mcp.json` 配置文件。此文件由 CLI 命令管理，**不要手动编辑**。 + +```bash +# 获取 token 后，使用以下命令配置 Admin MCP（项目级别） +/root/.local/bin/claude mcp add --scope project --transport http d8d-admin "http://localhost:23957/mcp-admin" \ + --header "Authorization: Bearer YOUR_TOKEN_HERE" +``` + +**⚠️ Cloud Claude 环境注意事项**： +- 在 Cloud Claude 中运行此命令时，输出会被吞掉 +- 命令会**成功执行并生成** `.mcp.json` 文件 +- 使用 `cat .mcp.json` 或 `Read .mcp.json` 验证文件是否生成 + +### 配置 Claude Desktop + +编辑 Claude Desktop 配置文件（`claude_desktop_config.json`）： + +```json +{ + "mcpServers": { + "d8d": { + "transport": { + "type": "streamable_http", + "url": "http://localhost:23957/mcp", + "headers": { + "Authorization": "Bearer YOUR_TOKEN_HERE" + } + } + }, + "d8d-admin": { + "transport": { + "type": "streamable_http", + "url": "http://localhost:23957/mcp-admin", + "headers": { + "Authorization": "Bearer YOUR_TOKEN_HERE" + } + } + } + } +} +``` + +### 更新现有 MCP 配置 + +如果 Admin MCP 已配置，需要更新 token： + +```bash +# 删除旧配置（项目级别） +/root/.local/bin/claude mcp remove --scope project d8d-admin + +# 重新添加新配置（项目级别） +/root/.local/bin/claude mcp add --scope project --transport http d8d-admin "http://localhost:23957/mcp-admin" \ + --header "Authorization: Bearer YOUR_NEW_TOKEN" +``` + +**⚠️ 重要说明**： +- `.mcp.json` 文件由 CLI 命令**自动生成和管理** +- **不要手动编辑**此文件 +- 如需更新配置，使用 `claude mcp remove` + `claude mcp add` 命令 +- **此文件已添加到 `.gitignore`，不会提交到仓库**（每个开发者/环境单独配置） +- Cloud Claude 环境中执行后使用 `cat .mcp.json` 验证配置已更新 + +--- + +## 验证连接 + +配置完成后，验证 MCP 连接： + +### ⚠️ Cloud Claude 环境特殊说明 + +**在 Cloud Claude 环境中运行 Claude CLI 命令时**，由于是在 Claude 命令环境中再次调用 Claude 命令，输出无法直接显示。**必须先输出到文件，再读取文件查看**。 + +**正确方式**： +```bash +# 将命令输出保存到文件，然后读取文件 +/root/.local/bin/claude mcp list > /tmp/mcp-list-output.txt 2>&1 +cat /tmp/mcp-list-output.txt +``` + +**错误方式**（输出不会显示）： +```bash +# ❌ 直接执行命令，输出会被吞掉 +/root/.local/bin/claude mcp list +``` + +### 验证命令 + +```bash +# 列出已配置的 MCP 服务器（输出到文件） +/root/.local/bin/claude mcp list > /tmp/mcp-list-output.txt 2>&1 + +# 查看输出 +cat /tmp/mcp-list-output.txt + +# 或使用 Read 工具读取 +Read /tmp/mcp-list-output.txt + +# 查看 Admin MCP 可用工具 +# 在 Claude Code 对话中询问："列出 D8D Admin MCP 的所有工具" +``` + +--- + +## 可用工具 + +配置成功后，D8D Admin MCP 提供以下工具类别： + +### 工作空间管理工具 +- `d8d_admin_list_all_workspaces` - 列出所有工作空间（跨用户查询） +- `d8d_admin_get_workspace_by_id` - 获取工作空间详情（通过 ID） + +### 模板管理工具 +- `d8d_admin_list_all_templates` - 列出所有模板（跨用户查询） +- `d8d_admin_get_template_by_id` - 获取模板详情（通过 ID） + +### 容器管理工具 +- `d8d_admin_force_stop_dev_container` - 强制停止开发容器（返回操作指导） +- `d8d_admin_force_stop_prd_container` - 强制停止生产容器（返回操作指导） +- `d8d_admin_restart_container` - 重启容器（返回操作指导） + +**⚠️ 注意：** 危险操作工具（如批量删除工作空间/模板）目前未注册，代码已保留供将来使用。 + +--- + +## 与普通 D8D MCP 的区别 + +| 特性 | D8D MCP | Admin MCP | +|------|---------|-----------| +| **端点** | `/mcp` | `/mcp-admin` | +| **权限** | 普通用户 | 仅管理员 | +| **数据范围** | 当前用户资源 | 所有用户资源 | +| **操作类型** | 用户级 CRUD | 跨用户查询 + 管理操作 | + +**典型使用场景：** +- **D8D MCP**: 用户管理自己的工作空间、模板、容器 +- **Admin MCP**: 管理员查看所有用户资源、执行跨用户管理操作 + +--- + +## 故障排查 + +### 问题 1：权限不足（403 Forbidden） + +**错误信息：** `需要管理员权限` + +**解决方案：** +1. 确认当前登录用户 ID 在管理员列表中（1, 6, 26） +2. 使用管理员账号登录：`curl -X POST http://localhost:23957/api/v1/auth/login/sms -H "Content-Type: application/json" -d '{"phone":"管理员手机号","code":"验证码"}'` +3. 更新 MCP 配置中的 token + +### 问题 2：认证失败（401 Unauthorized） + +**错误信息：** `Unauthorized: Missing Authorization header` 或 `Forbidden: Invalid token` + +**解决方案：** +1. 确认 token 未过期（token 有效期通常为 7 天） +2. 重新获取 token：`curl -X POST http://localhost:23957/api/v1/auth/login/sms -H "Content-Type: application/json" -d '{"phone":"18617351030","code":"220290"}'` +3. 更新 MCP 配置中的 token + +### 问题 3：连接超时 + +**错误信息：** 请求超时或无法连接 + +**解决方案：** +1. 确认 D8D 服务正在运行：`curl http://localhost:23957/health` +2. 检查端口是否正确：Admin MCP 使用相同的端口 `23957`，但路径为 `/mcp-admin` +3. 检查防火墙设置 + +### 问题 4：工具未找到 + +**错误信息：** `Tool not found` + +**解决方案：** +1. 确认工具名称格式：`d8d_admin_{action}_{resource}` +2. 查看可用工具列表：在 Claude Code 中询问 "D8D Admin MCP 有哪些工具？" +3. 确认端点路径正确：`/mcp-admin` 而非 `/mcp` + +### 问题 5：D8D 服务未启动 + +**检查服务状态：** +```bash +# 检查端口是否监听 +lsof -i :23957 + +# 或检查进程 +ps aux | grep d8d +``` + +**启动 D8D 服务：** +```bash +cd /mnt/code-fast/d8d-worktrees/feat-epic-32 +pnpm dev +``` + +--- + +## 测试连接 + +配置完成后，可以通过以下方式测试： + +### 在 Claude Code 中测试 + +``` +用户：使用 Admin MCP 列出所有工作空间 + +Claude 应该调用 d8d_admin_list_all_workspaces 工具并返回所有用户的工作空间列表。 +``` + +### 直接 API 测试 + +```bash +# 测试健康检查 +curl http://localhost:23957/health + +# 测试 Admin MCP 端点 +curl -X POST http://localhost:23957/mcp-admin \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer YOUR_TOKEN" \ + -d '{"jsonrpc":"2.0","id":1,"method":"ping"}' +``` + +--- + +## Token 刷新 + +Token 有效期为 7 天，过期后需要重新获取： + +### 方法 1：更新当前目录配置（推荐，支持 Worktree） + +```bash +# 0. 先加载本地配置（如果有） +if [ -f .env.local ]; then + source .env.local +elif [ -f .env ]; then + source .env +fi + +# 使用本地配置或默认值 +D8D_API_URL=${D8D_API_URL:-"http://localhost:23957"} +D8D_ADMIN_PHONE=${D8D_ADMIN_PHONE:-"18617351030"} +D8D_ADMIN_CODE=${D8D_ADMIN_CODE:-"220290"} + +# 1. 获取当前目录和新 token（使用本地配置） +PROJECT_DIR=$(pwd) +NEW_TOKEN=$(curl -s -X POST $D8D_API_URL/api/v1/auth/login/sms \ + -H "Content-Type: application/json" \ + -d "{\"phone\":\"$D8D_ADMIN_PHONE\",\"code\":\"$D8D_ADMIN_CODE\"}" | jq -r '.token') + +# 2. 更新配置 +jq --arg dir "$PROJECT_DIR" --arg token "$NEW_TOKEN" \ + '.projects[$dir].mcpServers."d8d-admin".headers.Authorization = "Bearer \($token)"' \ + ~/.claude.json > /tmp/claude-new.json && mv /tmp/claude-new.json ~/.claude.json +``` + +### 方法 2：使用 CLI（项目级别） + +```bash +# 1. 获取新 token +NEW_TOKEN=$(curl -s -X POST http://localhost:23957/api/v1/auth/login/sms \ + -H "Content-Type: application/json" \ + -d '{"phone":"18617351030","code":"220290"}' | jq -r '.token') + +# 2. 更新 MCP 配置（项目级别） +/root/.local/bin/claude mcp remove --scope project d8d-admin +/root/.local/bin/claude mcp add --scope project --transport http d8d-admin "http://localhost:23957/mcp-admin" \ + --header "Authorization: Bearer $NEW_TOKEN" +``` + +**⚠️ Cloud Claude 环境**：执行后使用 `cat .mcp.json` 验证配置已更新。 + +--- + +## 附录：完整配置示例 + +### Claude Desktop 配置文件位置 + +- **Linux/macOS**: `~/.config/claude/claude_desktop_config.json` +- **Windows**: `%APPDATA%\Claude\claude_desktop_config.json` + +### 完整配置示例（同时配置 D8D MCP 和 Admin MCP） + +```json +{ + "mcpServers": { + "d8d": { + "transport": { + "type": "streamable_http", + "url": "http://localhost:23957/mcp", + "headers": { + "Authorization": "Bearer eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9..." + } + } + }, + "d8d-admin": { + "transport": { + "type": "streamable_http", + "url": "http://localhost:23957/mcp-admin", + "headers": { + "Authorization": "Bearer eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9..." + } + } + } + } +} +``` + +--- + +## 相关文档 + +- [D8D MCP 服务器文档](https://localhost:23957/doc) - 普通 D8D MCP 配置 +- [Admin MCP 技术规范](./_bmad-output/implementation-artifacts/tech-spec-admin-mcp-server-full.md) - Admin MCP 详细技术文档 +- [MCP 协议规范](https://modelcontextprotocol.io/) diff --git a/.claude/skills/mcp-d8d-install/SKILL.md b/.claude/skills/mcp-d8d-install/SKILL.md new file mode 100644 index 0000000..7f177fd --- /dev/null +++ b/.claude/skills/mcp-d8d-install/SKILL.md @@ -0,0 +1,442 @@ +--- +name: mcp-d8d-install +description: 帮助用户在 Claude Code 中配置和安装 D8D MCP 服务器连接。当用户需要配置 D8D MCP 连接、获取认证 token、或排查 MCP 连接问题时触发。 +--- + +# D8D MCP 服务器安装配置 + +## 概述 + +D8D MCP 服务器提供了通过 Model Context Protocol (MCP) 访问 D8D 平台功能的能力。本指南帮助您在 Claude Code 中配置 MCP 连接。 + +--- + +## 服务器信息 + +**⚠️ 重要说明**：D8D 提供**两个 MCP 服务**，使用**同一个端口**，仅端点路径不同。 + +| MCP 服务 | 端点路径 | 说明 | +|----------|----------|------| +| **d8d** | `/mcp` | D8D 主功能 MCP（工作空间、模板、容器管理） | +| **d8d-admin** | `/mcp-admin` | D8D 管理后台 MCP（用户、订阅、配额管理） | + +| 配置项 | 值 | +|--------|-----| +| **默认端口** | `23957`（不同 worktree 可能不同） | +| **传输协议** | HTTP | +| **认证方式** | Bearer Token（通过手机号+验证码登录获取） | + +**端口示例**： +- `feat-epic-32` worktree: 端口 `23957` +- `merge-epics` worktree: 端口 `43959` + +--- + +## 🔍 第一步：检查本地环境配置 + +**⚠️ 重要**：不同的 Git Worktree 可能有不同的本地配置，必须先检查当前 worktree 的环境变量和实际运行端口。 + +### 自动检测运行端口 + +```bash +# 检查当前 D8D 服务实际运行的端口 +echo "=== 检测 D8D 服务端口 ===" +D8D_PORT=$(lsof -i -P -n | grep LISTEN | grep node | awk '{print $9}' | grep -oP '^\d+' | head -1) +echo "检测到端口: $D8D_PORT" + +# 如果没有检测到，使用默认值 +D8D_PORT=${D8D_PORT:-"23957"} +echo "使用端口: $D8D_PORT" +``` + +### 检查本地配置文件 + +```bash +# 检查当前 worktree 中是否存在本地配置文件 +echo "=== 检查本地配置文件 ===" + +# 按优先级检查配置文件 +if [ -f .env.local ]; then + echo "✅ 找到 .env.local" + cat .env.local | grep -E "(D8D|API|PORT|ADMIN)" || true +elif [ -f .env ]; then + echo "✅ 找到 .env" + cat .env | grep -E "(D8D|API|PORT|ADMIN)" || true +else + echo "ℹ️ 未找到本地配置文件，使用默认配置" +fi +``` + +### 从配置文件读取端点 + +```bash +# 1. 先检测实际运行的端口 +D8D_DETECTED_PORT=$(lsof -i -P -n 2>/dev/null | grep LISTEN | grep node | awk '{print $9}' | grep -oP '^\d+' | head -1) + +# 2. 读取本地配置（如果存在） +if [ -f .env.local ]; then + source .env.local +elif [ -f .env ]; then + source .env +fi + +# 3. 使用检测到的端口 > 配置文件端口 > 默认值 +D8D_PORT=${D8D_DETECTED_PORT:-${PORT:-"23957"}} +D8D_API_URL="http://localhost:$D8D_PORT" +D8D_PHONE=${D8D_PHONE:-"18617351030"} +D8D_CODE=${D8D_CODE:-"220290"} + +echo "使用配置：" +echo " API URL: $D8D_API_URL" +echo " 端口: $D8D_PORT" +echo " 测试账号: $D8D_PHONE" +echo " MCP 端点: $D8D_API_URL/mcp" +echo " Admin MCP 端点: $D8D_API_URL/mcp-admin" +``` + +### 配置文件示例 + +如果需要在 worktree 中创建本地配置，可以创建 `.env.local`： + +```bash +# .env.local - Worktree 本地配置 +PORT=43959 +D8D_PHONE=18617351030 +D8D_CODE=220290 +``` + +--- + +## 获取认证 Token + +### 方法 1：使用测试账号（推荐） + +D8D 提供固定验证码测试账号： + +| 项目 | 值 | +|------|-----| +| **手机号** | `18617351030` | +| **验证码** | `220290`（固定验证码） | + +### 方法 2：通过 API 获取 Token（使用本地配置） + +```bash +# 1. 先检测实际运行的端口 +D8D_DETECTED_PORT=$(lsof -i -P -n 2>/dev/null | grep LISTEN | grep node | awk '{print $9}' | grep -oP '^\d+' | head -1) + +# 2. 读取本地配置（如果存在） +if [ -f .env.local ]; then + source .env.local +elif [ -f .env ]; then + source .env +fi + +# 3. 使用检测到的端口 > 配置文件端口 > 默认值 +D8D_PORT=${D8D_DETECTED_PORT:-${PORT:-"23957"}} +D8D_API_URL="http://localhost:$D8D_PORT" +D8D_PHONE=${D8D_PHONE:-"18617351030"} +D8D_CODE=${D8D_CODE:-"220290"} + +echo "从 $D8D_API_URL 获取 Token..." +curl -X POST $D8D_API_URL/api/v1/auth/login/sms \ + -H "Content-Type: application/json" \ + -d "{\"phone\":\"$D8D_PHONE\",\"code\":\"$D8D_CODE\"}" +``` + +**响应示例：** +```json +{ + "code": 0, + "message": "success", + "data": { + "token": "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9...", + "user": {...} + } +} +``` + +复制返回的 `token` 值用于 MCP 配置。 + +--- + +## Claude MCP 配置 + +### 配置 Claude Desktop + +编辑 Claude Desktop 配置文件（`claude_desktop_config.json`）： + +```json +{ + "mcpServers": { + "d8d": { + "transport": { + "type": "streamable_http", + "url": "http://localhost:23957/mcp", + "headers": { + "Authorization": "Bearer YOUR_TOKEN_HERE" + } + } + }, + "d8d-admin": { + "transport": { + "type": "streamable_http", + "url": "http://localhost:23957/mcp-admin", + "headers": { + "Authorization": "Bearer YOUR_TOKEN_HERE" + } + } + } + } +} +``` + +### 使用 Claude Code CLI 配置（项目级别） + +**说明**： +- 使用 `--scope project` 会在项目目录下**自动生成** `.mcp.json` 配置文件 +- d8d 和 d8d-admin 使用**同一个端口**，仅端点路径不同 +- 此文件由 CLI 命令管理，**不要手动编辑** + +**配置两个 MCP 服务**： + +```bash +# 先检测端口（或使用默认端口 23957） +D8D_PORT=${PORT:-"23957"} + +# 配置 d8d MCP（主功能） +/root/.local/bin/claude mcp add --scope project --transport http d8d "http://localhost:$D8D_PORT/mcp" \ + --header "Authorization: Bearer YOUR_TOKEN_HERE" + +# 配置 d8d-admin MCP（管理功能） +/root/.local/bin/claude mcp add --scope project --transport http d8d-admin "http://localhost:$D8D_PORT/mcp-admin" \ + --header "Authorization: Bearer YOUR_TOKEN_HERE" +``` + +**⚠️ Cloud Claude 环境注意事项**： +- 在 Cloud Claude 中运行此命令时，输出会被吞掉 +- 命令会**成功执行并生成** `.mcp.json` 文件 +- 使用 `cat .mcp.json` 或 `Read .mcp.json` 验证文件是否生成 + +### 更新现有 MCP 配置 + +如果 D8D MCP 已配置，需要更新 token： + +```bash +# 删除旧配置（项目级别） +/root/.local/bin/claude mcp remove --scope project d8d + +# 重新添加新配置（项目级别） +/root/.local/bin/claude mcp add --scope project --transport http d8d "http://localhost:23957/mcp" \ + --header "Authorization: Bearer YOUR_NEW_TOKEN" +``` + +**⚠️ 重要说明**： +- `.mcp.json` 文件由 CLI 命令**自动生成和管理** +- **不要手动编辑**此文件 +- 如需更新配置，使用 `claude mcp remove` + `claude mcp add` 命令 +- **此文件已添加到 `.gitignore`，不会提交到仓库**（每个开发者/环境单独配置） + +--- + +## 验证连接 + +配置完成后，验证 MCP 连接： + +### ⚠️ Cloud Claude 环境特殊说明 + +**在 Cloud Claude 环境中运行 Claude CLI 命令时**，由于是在 Claude 命令环境中再次调用 Claude 命令，输出无法直接显示。**必须先输出到文件，再读取文件查看**。 + +**正确方式**： +```bash +# 将命令输出保存到文件，然后读取文件 +/root/.local/bin/claude mcp list > /tmp/mcp-list-output.txt 2>&1 +cat /tmp/mcp-list-output.txt +``` + +**错误方式**（输出不会显示）： +```bash +# ❌ 直接执行命令，输出会被吞掉 +/root/.local/bin/claude mcp list +``` + +### 验证命令 + +```bash +# 列出已配置的 MCP 服务器（输出到文件） +/root/.local/bin/claude mcp list > /tmp/mcp-list-output.txt 2>&1 + +# 查看输出 +cat /tmp/mcp-list-output.txt + +# 或使用 Read 工具读取 +Read /tmp/mcp-list-output.txt + +# 查看 D8D MCP 可用工具 +# 在 Claude Code 对话中询问："列出 D8D MCP 的所有工具" +``` + +--- + +## 可用工具 + +配置成功后，D8D MCP 提供以下工具类别： + +### 工作空间工具 +- `d8d_list_workspaces` - 列出工作空间 +- `d8d_get_workspace` - 获取工作空间详情 +- `d8d_create_workspace` - 创建工作空间 +- `d8d_delete_workspace` - 删除工作空间 + +### 模板工具 +- `d8d_list_templates` - 列出模板 +- `d8d_get_template` - 获取模板详情 + +### 容器工具 +- `d8d_list_containers` - 列出容器 +- `d8d_get_container` - 获取容器详情 +- `d8d_get_container_status` - 获取容器状态 +- `d8d_start_container` - 启动容器 +- `d8d_stop_container` - 停止容器 +- `d8d_restart_container` - 重启容器 + +### 容器组配置工具 +- `d8d_get_container_group_config` - 获取容器组配置 +- `d8d_list_container_group_configs` - 列出容器组配置 + +--- + +## 故障排查 + +### 问题 1：认证失败 + +**错误信息：** `Unauthorized: Missing Authorization header` 或 `Forbidden: Invalid token` + +**解决方案：** +1. 确认 token 未过期（token 有效期通常为 7 天） +2. 重新获取 token：`curl -X POST http://localhost:23957/api/v1/auth/login/sms -H "Content-Type: application/json" -d '{"phone":"18617351030","code":"220290"}'` +3. 更新 MCP 配置中的 token + +### 问题 2：连接超时 + +**错误信息：** 请求超时或无法连接 + +**解决方案：** +```bash +# 1. 检测实际运行的端口 +D8D_PORT=$(lsof -i -P -n 2>/dev/null | grep LISTEN | grep node | awk '{print $9}' | grep -oP '^\d+' | head -1) +echo "检测到端口: $D8D_PORT" + +# 2. 确认 D8D 服务正在运行 +curl http://localhost:$D8D_PORT/health + +# 3. 测试 MCP 端点（需要 token） +curl http://localhost:$D8D_PORT/mcp +``` + +### 问题 3：工具未找到 + +**错误信息：** `Tool not found` + +**解决方案：** +1. 确认工具名称格式：`d8d_{action}_{resource}` +2. 查看可用工具列表：在 Claude Code 中询问 "D8D MCP 有哪些工具？" + +### 问题 4：D8D 服务未启动 + +**检查服务状态：** +```bash +# 检查端口是否监听 +lsof -i :23957 + +# 或检查进程 +ps aux | grep d8d +``` + +**启动 D8D 服务：** +```bash +cd /mnt/code-fast/d8d-worktrees/feat-epic-32 +pnpm dev +``` + +--- + +## 测试连接 + +配置完成后，可以通过以下方式测试： + +### 在 Claude Code 中测试 + +``` +用户：使用 D8D MCP 列出所有工作空间 + +Claude 应该调用 d8d_list_workspaces 工具并返回工作空间列表。 +``` + +### 直接 API 测试 + +```bash +# 测试健康检查 +curl http://localhost:23957/health + +# 测试 MCP 端点 +curl -X POST http://localhost:23957/mcp \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer YOUR_TOKEN" \ + -d '{"jsonrpc":"2.0","id":1,"method":"ping"}' +``` + +--- + +## Token 刷新 + +Token 有效期为 7 天，过期后需要重新获取： + +```bash +# 1. 获取新 token +NEW_TOKEN=$(curl -s -X POST http://localhost:23957/api/v1/auth/login/sms \ + -H "Content-Type: application/json" \ + -d '{"phone":"18617351030","code":"220290"}' | jq -r '.data.token') + +# 2. 删除旧配置（项目级别） +/root/.local/bin/claude mcp remove --scope project d8d + +# 3. 重新添加新配置（项目级别） +/root/.local/bin/claude mcp add --scope project --transport http d8d "http://localhost:23957/mcp" \ + --header "Authorization: Bearer $NEW_TOKEN" +``` + +**⚠️ Cloud Claude 环境**：执行后使用 `cat .mcp.json` 验证配置已更新。 + +--- + +## 附录：完整配置示例 + +### Claude Desktop 配置文件位置 + +- **Linux/macOS**: `~/.config/claude/claude_desktop_config.json` +- **Windows**: `%APPDATA%\Claude\claude_desktop_config.json` + +### 完整配置示例 + +```json +{ + "mcpServers": { + "d8d": { + "transport": { + "type": "streamable_http", + "url": "http://localhost:23957/mcp", + "headers": { + "Authorization": "Bearer eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9..." + } + } + } + } +} +``` + +--- + +## 相关文档 + +- [D8D MCP 服务器文档](https://localhost:23957/doc) +- [MCP 协议规范](https://modelcontextprotocol.io/) diff --git a/.claude/skills/mcp-novel-platform-install.skill b/.claude/skills/mcp-novel-platform-install.skill new file mode 100644 index 0000000000000000000000000000000000000000..5658a7eebda880413a4f65171678022a601f9d4f GIT binary patch literal 2985 zcma);XEYm*0>xuhY_(@8te!o8>I0-2e000027#V%6GlY6KiKqYogdhOG|F`u(c!NE? z0-aD`Z4|$Fr!DQg@Y=M`XKV8PeBO9i1Qxfb+Vk{Q zyW#>S^nH{3<`PJD8)aHu_~8npn56exJI^Ao6VG+hR#R?pI-z-}i5)nYM#o2+_L5(? zen)}VE}6(Gw2@Qm-t9J@-ZL@X+JGVYK$ zBZ|22^-*idG`fm4dK6h9GwFL*LAFqB#Vqp5)>)K$u_A5NGPk|e<;(YfINp5nme$EO=)3(w>T0sbRu9K#tk&{($C12Y|qv3!m_*rRj7fc4_Kw3PZYObjQ(7>DiMO&h}N&%)B+&3c1LqWD?!$= ze##^JV$SV`+I^EuZ(xq&`sRwmBQj9oG9Xx|}jxgEvRoqaGKXc8VH7d7wZmFjd+JxU*L2q7L#B{Vl znU!u+d}IxRAVpmLzgn}3-Jw$I>v5p5tn@;;u{tD- z<<`zjS*NOLimhXU0Cr)1qloBNr}iq!23LO7s!x_dm(r5e$p(F8rdp6{s$7o7hffc9 zwD5>E@4;3xkI?&J_s)j2Fp7D%p3tZx(X|()CBpWHq@u?Ww~NjN%N7;SJ#V~z8L~bt z&$hU%$%rn`pKr$IF6g&*33~{C0m`>e=1&j@1{}?4heWmQ>D#Iqc~09_?}|_vd^_Ek z*esTnkTA6TKwhC-x6JB@fm@!*Wg;9ko@UXn{faq9Ap;QQBJQ>iv8l=JIo=l}d%F5TJ`lf<^`}{qOd&>ne=ArD`=9H9uREh@aT8_NySEy(Jr5 z;IuSCTRn^P_Ma)vt z#^h!Ew4s1aL?O`(kwO{#3Uxjy5k!G>Or+cBn!uUH(cD{fxLNFr4Ix*wA{%2Z`Uyjp)$ z3u)(c{T^qw#n>2|16kP@og@RZ!E6bt0b)RI7oHYLbLL`CPodPleaC+y?^)uq9UN)& znsaufan$%qa5&SNCc~Hh@IRXU)^oJda>-FxgxXAjs%S8$Opfhc&!$00EQ0tRdlrS6 zszad})SoHc!@_CcaF|S+c8c>T9%Ax6u@nTA@t6F^C4Q_@SxQ50?FSToa}W&l6l5Sw zH*|%@8Ri7wz{Pz2wr7!ZXdp+{Q?j}G@U|~-2MY|zx~6OuLzGA*Pe=KNXsQJ9D|qzc zBW)g z;-GP{Xb%brZ4t?FCc7#JU~8am#HS-Q7`dM82+0X9m z@0&GFMe2W)$vu>Rs>T^JRNDrB^lp;;9S0!k<4pO5b5YXeIu>-I-u?MEk(JIxSz`iT zu=%&Qq3aC#XHLVZT}!TtCHbXNr`gZaplp3NZXa4RPfn{D>Nk-wOA!sVN?B#`=6^VT z8m<``$0QBlt@Nzto=TOxFVJ<7adA3WW`d82dtHXp_W8+@>R;Ie-opAGqJ%FpYl;`d zi;1E8jK@1O`6bJ>xF*lxSIx6dl}H*IxmLB^rJg^12K%vjZa=!Vhy_w-k>fgZ&Wtg_ z4DRQnpcY(2oo~f(!#3TL&AGRQv3;7*>SLg4YcIWYB(K3L@|!Z$kqPBq*K^um9E6(!Gv5b z$nB!{@*@TF2id|>o+KI*^!OvlCwDIdZtsB=th@KF!mtCS7b+ZDlL(r}t;KcE9*$mT z&UHQ-^x5Oi!r&8jJ8pGKdJE8lcQbOQWDcFkp4`bQ_G2AMM7s(_m#&{E zs>7PFrkcqzO)>PRHpJ|`(b?Ywy%%KDbz}*-9-D;cgsQhC1z%H6m#erWf}x)|4@`YV zjwz5MKJ^eoW+H;+AhonjQj5)nO;&N@m$1{AZZOzo+C1l|GE`uMMSaAX zx=dj=h$lDKocxM9f6;zZv>3M*mk;QUAvOLDWWY TvRnU7iT>L7Z>s$Tasc2zjnSFR literal 0 HcmV?d00001 diff --git a/.claude/skills/mcp-novel-platform-install/SKILL.md b/.claude/skills/mcp-novel-platform-install/SKILL.md new file mode 100644 index 0000000..df8a936 --- /dev/null +++ b/.claude/skills/mcp-novel-platform-install/SKILL.md @@ -0,0 +1,309 @@ +--- +name: mcp-novel-platform-install +description: Configure and install Novel Platform MCP server connections for Claude Code. This skill handles TWO MCP servers - User MCP for reader features (13 tools) and Admin MCP for admin features (16 tools). Use this skill when user needs to set up Novel Platform MCP connections for the first time, MCP connection needs to be reconfigured after disconnection, user asks to connect/install Novel Platform MCP tools, user asks about MCP servers for novel platform/reader/admin features, or troubleshooting Novel Platform MCP connectivity issues. IMPORTANT - Both MCP servers require JWT authentication token obtained from platform login. +--- + +# MCP Novel Platform Install + +## Overview + +This skill configures Claude Code to connect to the **Novel Platform** MCP servers, enabling access to: + +- **User MCP** (13 tools): Reader features - browse novels, read chapters, manage bookshelf, purchase chapters, track reading progress +- **Admin MCP** (16 tools): Admin features - platform stats, user management, content moderation, system configuration + +## Quick Start + +### Step 1: Register or Login to Get JWT Token + +**NEW USER - Register first:** +```bash +# Register a new account +curl -X POST https://d8d-ai-vscode-8080-223-238-template-6-group.dev.d8d.fun/api/v1/auth/register \ + -H "Content-Type: application/json" \ + -d '{"email": "your@email.com", "password": "yourpassword", "username": "yourname"}' +``` + +**EXISTING USER - Login:** +```bash +# Login to get JWT token +curl -X POST https://d8d-ai-vscode-8080-223-238-template-6-group.dev.d8d.fun/api/v1/auth/login \ + -H "Content-Type: application/json" \ + -d '{"email": "your@email.com", "password": "yourpassword"}' + +# Response includes access_token - save it! +# {"access_token": "eyJhbGci...", "token_type": "bearer", "expires_in": 3600} +``` + +### Step 2: Add User MCP Connection + +```bash +/root/.local/bin/claude mcp add --scope project --transport http \ + novel-platform-user \ + https://d8d-ai-vscode-8080-223-238-template-6-group.dev.d8d.fun/mcp +``` + +### Step 3: Add Admin MCP Connection (Admin Only) + +```bash +/root/.local/bin/claude mcp add --scope project --transport http \ + novel-platform-admin \ + https://d8d-ai-vscode-8080-223-238-template-6-group.dev.d8d.fun/admin-mcp +``` + +### Step 4: Verify Connections + +```bash +/root/.local/bin/claude mcp list +``` + +Expected output: +``` +novel-platform-user (http) - https://.../mcp +novel-platform-admin (http) - https://.../admin-mcp +``` + +## MCP Server Information + +| Property | User MCP | Admin MCP | +|----------|----------|-----------| +| **Server Name** | `novel-platform-user` | `novel-platform-admin` | +| **External URL** | `https://d8d-ai-vscode-8080-223-238-template-6-group.dev.d8d.fun/mcp/` | `https://d8d-ai-vscode-8080-223-238-template-6-group.dev.d8d.fun/admin-mcp/` | +| **Transport** | HTTP (SSE) | HTTP (SSE) | +| **Authentication** | JWT Token | JWT Token | +| **Container** | D8D Template 238 (Workspace 223) | Same | +| **Internal Port** | 8080 | 8080 | +| **Tool Count** | 13 tools | 16 tools | + +## Available Tools + +### User MCP Tools (13) + +| Tool | Function | +|------|----------| +| `login` | Authenticate and get JWT token | +| `get_user_profile` | Get current user profile | +| `get_novels` | Browse novel list with filters | +| `get_novel_detail` | Get novel detail and metadata | +| `get_featured_novels` | Get recommended/featured novels | +| `get_chapter` | Get chapter content | +| `get_chapter_directory` | Get chapter list for a novel | +| `get_bookshelf` | Get user's bookshelf | +| `add_to_bookshelf` | Add novel to bookshelf | +| `remove_from_bookshelf` | Remove from bookshelf | +| `get_reading_progress` | Get reading progress for a novel | +| `update_reading_progress` | Update reading progress | +| `list_reading_progress` | List all reading progress | + +### Admin MCP Tools (16) + +| Tool | Function | +|------|----------| +| `login` | Authenticate as admin | +| `get_system_stats` | Get platform statistics | +| `get_platform_metrics` | Get detailed metrics | +| `get_top_content` | Get top-rated content | +| `get_users` | List users with filters | +| `get_user_detail` | Get user detail | +| `ban_user` | Ban a user | +| `unban_user` | Unban a user | +| `get_pending_novels` | Get pending approval novels | +| `approve_novel` | Approve a novel | +| `reject_novel` | Reject a novel | +| `delete_novel` | Delete a novel | +| `get_system_config` | Get system configuration | +| `update_system_config` | Update system configuration | +| `get_platform_health` | Get platform health status | + +## Installation Workflow + +### Step 1: Verify Backend Service is Running + +```bash +# Check if backend API is accessible +curl -s https://d8d-ai-vscode-8080-223-238-template-6-group.dev.d8d.fun/ | head -20 +``` + +Expected: `{"message":"NexusNovel Platform API"...}` + +### Step 2: Register or Login for JWT Token + +**NEW USER - Register First:** +```bash +curl -X POST https://d8d-ai-vscode-8080-223-238-template-6-group.dev.d8d.fun/api/v1/auth/register \ + -H "Content-Type: application/json" \ + -d '{ + "email": "your@email.com", + "password": "yourpassword", + "username": "yourname" + }' +``` + +**EXISTING USER - Login:** +```bash +curl -X POST https://d8d-ai-vscode-8080-223-238-template-6-group.dev.d8d.fun/api/v1/auth/login \ + -H "Content-Type: application/json" \ + -d '{ + "email": "your@email.com", + "password": "yourpassword" + }' +``` + +**Response (save the access_token):** +```json +{ + "access_token": "eyJhbGciOiJIUzI1NiIs...", + "token_type": "bearer", + "expires_in": 3600 +} +``` + +**Option B: Via Swagger UI** +1. Open: https://d8d-ai-vscode-8080-223-238-template-6-group.dev.d8d.fun/docs +2. Find `POST /api/v1/auth/register` or `POST /api/v1/auth/login` +3. Try it out → Execute +4. Copy the `access_token` from response + +### Step 3: Add MCP Connections + +```bash +# User MCP +/root/.local/bin/claude mcp add --scope project --transport http \ + novel-platform-user \ + https://d8d-ai-vscode-8080-223-238-template-6-group.dev.d8d.fun/mcp/ + +# Admin MCP (if you have admin privileges) +/root/.local/bin/claude mcp add --scope project --transport http \ + novel-platform-admin \ + https://d8d-ai-vscode-8080-223-238-template-6-group.dev.d8d.fun/admin-mcp/ +``` + +### Step 4: Verify Installation + +```bash +/root/.local/bin/claude mcp list +``` + +Expected output: +``` +novel-platform-user (http) - https://d8d-ai-vscode-8080-223-238-template-6-group.dev.d8d.fun/mcp/ +novel-platform-admin (http) - https://d8d-ai-vscode-8080-223-238-template-6-group.dev.d8d.fun/admin-mcp/ +``` + +### Step 5: Test Connection + +After installation, tools are available with prefix: +- `mcp__novel-platform-user__*` for user tools +- `mcp__novel-platform-admin__*` for admin tools + +## Authentication Details + +### JWT Token Format + +The JWT token is returned from login API: + +```json +{ + "access_token": "eyJhbGciOiJIUzI1NiIs...", + "token_type": "bearer", + "expires_in": 3600 +} +``` + +### Token Expiration + +- JWT tokens expire after **1 hour** (3600 seconds) +- Re-authentication required when token expires +- Use the `login` MCP tool to refresh token + +### Login via MCP + +Alternatively, use the `login` tool directly: + +```python +mcp__novel-platform-user__login(email="user@example.com", password="password") +``` + +## Troubleshooting + +### Connection Refused + +1. Verify backend is running: Check Template 238 container status +2. Verify external URL is accessible: `curl -I https://d8d-ai-vscode-8080-223-238-template-6-group.dev.d8d.fun/mcp/` +3. Check container port 8080 is accessible + +### Authentication Failed + +1. Verify JWT token is valid and not expired (1 hour TTL) +2. Re-login to get fresh token: + ```bash + curl -X POST https://d8d-ai-vscode-8080-223-238-template-6-group.dev.d8d.fun/api/v1/auth/login \ + -H "Content-Type: application/json" \ + -d '{"email": "your@email.com", "password": "yourpassword"}' + ``` +3. Check token is being passed correctly in headers + +### Tools Not Appearing + +1. Restart Claude Code +2. Re-run `/root/.local/bin/claude mcp list` +3. Remove and re-add MCP connections: + ```bash + /root/.local/bin/claude mcp remove novel-platform-user + /root/.local/bin/claude mcp remove novel-platform-admin + ``` + +### URL Changes (New Container) + +When container is recreated, the URL may change. Verify current URL: +```bash +# Check if backend is responding +curl -s https://d8d-ai-vscode-8080-223-238-template-6-group.dev.d8d.fun/ | head -5 +``` + +If URL changed, update connections with new URL. + +## Example Usage After Installation + +### User Features + +```python +# Browse novels +mcp__novel-platform-user__get_novels(page=1, limit=10) + +# Get novel detail +mcp__novel-platform-user__get_novel_detail(novel_id=1) + +# Read chapter +mcp__novel-platform-user__get_chapter(chapter_id=123) + +# Add to bookshelf +mcp__novel-platform-user__add_to_bookshelf(novel_id=1, category="reading") + +# Update reading progress +mcp__novel-platform-user__update_reading_progress(novel_id=1, chapter_id=123) +``` + +### Admin Features + +```python +# Get system stats +mcp__novel-platform-admin__get_system_stats() + +# List users +mcp__novel-platform-admin__get_users(page=1, limit=20) + +# Approve novel +mcp__novel-platform-admin__approve_novel(novel_id=45) + +# Get platform health +mcp__novel-platform-admin__get_platform_health() +``` + +## Project Context + +- **Product**: NexusNovel Platform +- **Purpose**: Web-based novel reading and publishing platform +- **Features**: Novel browsing, chapter reading, bookshelf management, purchase chapters, author dashboard, admin panel +- **Status**: Backend 100% complete (8 Epics, 48/56 Stories) +- **Template**: D8D Template 238 (Workspace 223) diff --git a/.claude/skills/mcp-novel-translator-install/SKILL.md b/.claude/skills/mcp-novel-translator-install/SKILL.md new file mode 100644 index 0000000..1169598 --- /dev/null +++ b/.claude/skills/mcp-novel-translator-install/SKILL.md @@ -0,0 +1,142 @@ +--- +name: mcp-novel-translator-install +description: Configure and install Novel Translator MCP server connection for Claude Code. Use this skill when: (1) User needs to set up Novel Translator MCP connection for the first time, (2) MCP connection needs to be reconfigured after disconnection, (3) User asks to connect/install Novel Translator MCP tools, (4) User asks about MCP servers for novel translation, (5) Troubleshooting Novel Translator MCP connectivity issues. +--- + +# MCP Novel Translator Install + +## Overview + +This skill configures Claude Code to connect to the Novel Translator MCP server, enabling access to 10 translation tools (translate_text, translate_batch, translate_file, clean_file, split_chapters, glossary_add, glossary_list, glossary_clear, check_duplicate, get_fingerprint). + +## Quick Start + +Run the installation workflow: + +```bash +# Step 1: Check MCP server status in container +/root/.local/bin/claude mcp list + +# Step 2: Add Novel Translator MCP connection +/root/.local/bin/claude mcp add --scope project --transport http novel-translator https://d8d-ai-vscode-8080-223-236-template-6-group.dev.d8d.fun/sse + +# Step 3: Verify connection +/root/.local/bin/claude mcp list + +# Step 4: Test tools (should show 10 tools available) +``` + +## MCP Server Information + +| Property | Value | +|----------|-------| +| **Server Name** | `novel-translator` | +| **External URL** | `https://d8d-ai-vscode-8080-223-236-template-6-group.dev.d8d.fun/sse` | +| **Transport** | HTTP (SSE) | +| **Internal Port** | 8080 | +| **Container** | D8D Template 236 (Workspace 223) | + +## Available Tools (10) + +After installation, these tools become available: + +| Tool | Function | Category | +|------|----------|----------| +| `translate_text` | Translate single text segment with glossary support | Translation | +| `translate_batch` | Batch translate multiple text segments | Translation | +| `translate_file` | Complete translation pipeline (fingerprint→clean→glossary→translate) | Translation | +| `clean_file` | Clean and normalize TXT files | Cleaning | +| `split_chapters` | Intelligent chapter splitting | Cleaning | +| `glossary_add` | Add term to glossary | Glossary | +| `glossary_list` | List all glossary terms | Glossary | +| `glossary_clear` | Clear glossary | Glossary | +| `check_duplicate` | MD5 file duplicate check | Fingerprint | +| `get_fingerprint` | Get file fingerprint and metadata | Fingerprint | + +## Installation Workflow + +### Step 1: Verify Prerequisites + +Ensure the MCP server is running in the container: + +```bash +# Check if server is accessible +curl -s https://d8d-ai-vscode-8080-223-236-template-6-group.dev.d8d.fun/sse | head -20 +``` + +Expected: Server response (not connection error). + +### Step 2: Add MCP Connection + +Add the MCP server to Claude Code: + +```bash +/root/.local/bin/claude mcp add --scope project --transport http novel-translator https://d8d-ai-vscode-8080-223-236-template-6-group.dev.d8d.fun/sse +``` + +**Parameters:** +- `--scope project`: Project-level configuration +- `--transport http`: Use HTTP SSE transport +- `novel-translator`: Server name/identifier +- URL: External endpoint + +### Step 3: Verify Installation + +Check that the MCP server is listed: + +```bash +/root/.local/bin/claude mcp list +``` + +Expected output includes: +``` +novel-translator (http) - https://d8d-ai-vscode-8080-223-236-template-6-group.dev.d8d.fun/sse +``` + +### Step 4: Test Connection + +Verify tools are available. The MCP tools should now be accessible in Claude Code with the prefix `mcp__novel-translator__`. + +## Troubleshooting + +### Connection Refused + +If connection fails: +1. Verify container is running: Check D8D Template 236 status +2. Verify MCP server is running inside container: `python -m src.mcp_server.server` +3. Check external URL is accessible: `curl -I https://d8d-ai-vscode-8080-223-236-template-6-group.dev.d8d.fun/sse` + +### Tools Not Appearing + +If tools don't appear after installation: +1. Restart Claude Code +2. Re-run `/root/.local/bin/claude mcp list` +3. Remove and re-add: `/root/.local/bin/claude mcp remove novel-translator` + +### URL Changes + +If the external URL changes (e.g., new container): +1. Remove old connection: `/root/.local/bin/claude mcp remove novel-translator` +2. Add with new URL (update the URL in Step 2) + +## Example Usage After Installation + +Once installed, use the tools directly: + +```python +# Example: Translate text +mcp__novel-translator__translate_text(text="林风是一名修仙者", src_lang="zh", tgt_lang="en") + +# Example: Check file duplicate +mcp__novel-translator__check_duplicate(file_path="/path/to/novel.txt") + +# Example: List glossary +mcp__novel-translator__glossary_list() +``` + +## Project Context + +- **Product**: 序灵 Matrix 助手 (Novel Translator) +- **Purpose**: AI-powered Chinese novel translation pipeline +- **Features**: Fingerprint deduplication, text cleaning, glossary management, m2m100 translation, chapter upload +- **Status**: 100% complete (8 Epics, 318 Story Points) diff --git a/.claude/skills/pdf/LICENSE.txt b/.claude/skills/pdf/LICENSE.txt new file mode 100644 index 0000000..c55ab42 --- /dev/null +++ b/.claude/skills/pdf/LICENSE.txt @@ -0,0 +1,30 @@ +© 2025 Anthropic, PBC. All rights reserved. + +LICENSE: Use of these materials (including all code, prompts, assets, files, +and other components of this Skill) is governed by your agreement with +Anthropic regarding use of Anthropic's services. If no separate agreement +exists, use is governed by Anthropic's Consumer Terms of Service or +Commercial Terms of Service, as applicable: +https://www.anthropic.com/legal/consumer-terms +https://www.anthropic.com/legal/commercial-terms +Your applicable agreement is referred to as the "Agreement." "Services" are +as defined in the Agreement. + +ADDITIONAL RESTRICTIONS: Notwithstanding anything in the Agreement to the +contrary, users may not: + +- Extract these materials from the Services or retain copies of these + materials outside the Services +- Reproduce or copy these materials, except for temporary copies created + automatically during authorized use of the Services +- Create derivative works based on these materials +- Distribute, sublicense, or transfer these materials to any third party +- Make, offer to sell, sell, or import any inventions embodied in these + materials +- Reverse engineer, decompile, or disassemble these materials + +The receipt, viewing, or possession of these materials does not convey or +imply any license or right beyond those expressly granted above. + +Anthropic retains all right, title, and interest in these materials, +including all copyrights, patents, and other intellectual property rights. diff --git a/.claude/skills/pdf/SKILL.md b/.claude/skills/pdf/SKILL.md new file mode 100644 index 0000000..d3e046a --- /dev/null +++ b/.claude/skills/pdf/SKILL.md @@ -0,0 +1,314 @@ +--- +name: pdf +description: Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. +license: Proprietary. LICENSE.txt has complete terms +--- + +# PDF Processing Guide + +## Overview + +This guide covers essential PDF processing operations using Python libraries and command-line tools. For advanced features, JavaScript libraries, and detailed examples, see REFERENCE.md. If you need to fill out a PDF form, read FORMS.md and follow its instructions. + +## Quick Start + +```python +from pypdf import PdfReader, PdfWriter + +# Read a PDF +reader = PdfReader("document.pdf") +print(f"Pages: {len(reader.pages)}") + +# Extract text +text = "" +for page in reader.pages: + text += page.extract_text() +``` + +## Python Libraries + +### pypdf - Basic Operations + +#### Merge PDFs +```python +from pypdf import PdfWriter, PdfReader + +writer = PdfWriter() +for pdf_file in ["doc1.pdf", "doc2.pdf", "doc3.pdf"]: + reader = PdfReader(pdf_file) + for page in reader.pages: + writer.add_page(page) + +with open("merged.pdf", "wb") as output: + writer.write(output) +``` + +#### Split PDF +```python +reader = PdfReader("input.pdf") +for i, page in enumerate(reader.pages): + writer = PdfWriter() + writer.add_page(page) + with open(f"page_{i+1}.pdf", "wb") as output: + writer.write(output) +``` + +#### Extract Metadata +```python +reader = PdfReader("document.pdf") +meta = reader.metadata +print(f"Title: {meta.title}") +print(f"Author: {meta.author}") +print(f"Subject: {meta.subject}") +print(f"Creator: {meta.creator}") +``` + +#### Rotate Pages +```python +reader = PdfReader("input.pdf") +writer = PdfWriter() + +page = reader.pages[0] +page.rotate(90) # Rotate 90 degrees clockwise +writer.add_page(page) + +with open("rotated.pdf", "wb") as output: + writer.write(output) +``` + +### pdfplumber - Text and Table Extraction + +#### Extract Text with Layout +```python +import pdfplumber + +with pdfplumber.open("document.pdf") as pdf: + for page in pdf.pages: + text = page.extract_text() + print(text) +``` + +#### Extract Tables +```python +with pdfplumber.open("document.pdf") as pdf: + for i, page in enumerate(pdf.pages): + tables = page.extract_tables() + for j, table in enumerate(tables): + print(f"Table {j+1} on page {i+1}:") + for row in table: + print(row) +``` + +#### Advanced Table Extraction +```python +import pandas as pd + +with pdfplumber.open("document.pdf") as pdf: + all_tables = [] + for page in pdf.pages: + tables = page.extract_tables() + for table in tables: + if table: # Check if table is not empty + df = pd.DataFrame(table[1:], columns=table[0]) + all_tables.append(df) + +# Combine all tables +if all_tables: + combined_df = pd.concat(all_tables, ignore_index=True) + combined_df.to_excel("extracted_tables.xlsx", index=False) +``` + +### reportlab - Create PDFs + +#### Basic PDF Creation +```python +from reportlab.lib.pagesizes import letter +from reportlab.pdfgen import canvas + +c = canvas.Canvas("hello.pdf", pagesize=letter) +width, height = letter + +# Add text +c.drawString(100, height - 100, "Hello World!") +c.drawString(100, height - 120, "This is a PDF created with reportlab") + +# Add a line +c.line(100, height - 140, 400, height - 140) + +# Save +c.save() +``` + +#### Create PDF with Multiple Pages +```python +from reportlab.lib.pagesizes import letter +from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, PageBreak +from reportlab.lib.styles import getSampleStyleSheet + +doc = SimpleDocTemplate("report.pdf", pagesize=letter) +styles = getSampleStyleSheet() +story = [] + +# Add content +title = Paragraph("Report Title", styles['Title']) +story.append(title) +story.append(Spacer(1, 12)) + +body = Paragraph("This is the body of the report. " * 20, styles['Normal']) +story.append(body) +story.append(PageBreak()) + +# Page 2 +story.append(Paragraph("Page 2", styles['Heading1'])) +story.append(Paragraph("Content for page 2", styles['Normal'])) + +# Build PDF +doc.build(story) +``` + +#### Subscripts and Superscripts + +**IMPORTANT**: Never use Unicode subscript/superscript characters (₀₁₂₃₄₅₆₇₈₉, ⁰¹²³⁴⁵⁶⁷⁸⁹) in ReportLab PDFs. The built-in fonts do not include these glyphs, causing them to render as solid black boxes. + +Instead, use ReportLab's XML markup tags in Paragraph objects: +```python +from reportlab.platypus import Paragraph +from reportlab.lib.styles import getSampleStyleSheet + +styles = getSampleStyleSheet() + +# Subscripts: use tag +chemical = Paragraph("H2O", styles['Normal']) + +# Superscripts: use tag +squared = Paragraph("x2 + y2", styles['Normal']) +``` + +For canvas-drawn text (not Paragraph objects), manually adjust font the size and position rather than using Unicode subscripts/superscripts. + +## Command-Line Tools + +### pdftotext (poppler-utils) +```bash +# Extract text +pdftotext input.pdf output.txt + +# Extract text preserving layout +pdftotext -layout input.pdf output.txt + +# Extract specific pages +pdftotext -f 1 -l 5 input.pdf output.txt # Pages 1-5 +``` + +### qpdf +```bash +# Merge PDFs +qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf + +# Split pages +qpdf input.pdf --pages . 1-5 -- pages1-5.pdf +qpdf input.pdf --pages . 6-10 -- pages6-10.pdf + +# Rotate pages +qpdf input.pdf output.pdf --rotate=+90:1 # Rotate page 1 by 90 degrees + +# Remove password +qpdf --password=mypassword --decrypt encrypted.pdf decrypted.pdf +``` + +### pdftk (if available) +```bash +# Merge +pdftk file1.pdf file2.pdf cat output merged.pdf + +# Split +pdftk input.pdf burst + +# Rotate +pdftk input.pdf rotate 1east output rotated.pdf +``` + +## Common Tasks + +### Extract Text from Scanned PDFs +```python +# Requires: pip install pytesseract pdf2image +import pytesseract +from pdf2image import convert_from_path + +# Convert PDF to images +images = convert_from_path('scanned.pdf') + +# OCR each page +text = "" +for i, image in enumerate(images): + text += f"Page {i+1}:\n" + text += pytesseract.image_to_string(image) + text += "\n\n" + +print(text) +``` + +### Add Watermark +```python +from pypdf import PdfReader, PdfWriter + +# Create watermark (or load existing) +watermark = PdfReader("watermark.pdf").pages[0] + +# Apply to all pages +reader = PdfReader("document.pdf") +writer = PdfWriter() + +for page in reader.pages: + page.merge_page(watermark) + writer.add_page(page) + +with open("watermarked.pdf", "wb") as output: + writer.write(output) +``` + +### Extract Images +```bash +# Using pdfimages (poppler-utils) +pdfimages -j input.pdf output_prefix + +# This extracts all images as output_prefix-000.jpg, output_prefix-001.jpg, etc. +``` + +### Password Protection +```python +from pypdf import PdfReader, PdfWriter + +reader = PdfReader("input.pdf") +writer = PdfWriter() + +for page in reader.pages: + writer.add_page(page) + +# Add password +writer.encrypt("userpassword", "ownerpassword") + +with open("encrypted.pdf", "wb") as output: + writer.write(output) +``` + +## Quick Reference + +| Task | Best Tool | Command/Code | +|------|-----------|--------------| +| Merge PDFs | pypdf | `writer.add_page(page)` | +| Split PDFs | pypdf | One page per file | +| Extract text | pdfplumber | `page.extract_text()` | +| Extract tables | pdfplumber | `page.extract_tables()` | +| Create PDFs | reportlab | Canvas or Platypus | +| Command line merge | qpdf | `qpdf --empty --pages ...` | +| OCR scanned PDFs | pytesseract | Convert to image first | +| Fill PDF forms | pdf-lib or pypdf (see FORMS.md) | See FORMS.md | + +## Next Steps + +- For advanced pypdfium2 usage, see REFERENCE.md +- For JavaScript libraries (pdf-lib), see REFERENCE.md +- If you need to fill out a PDF form, follow the instructions in FORMS.md +- For troubleshooting guides, see REFERENCE.md diff --git a/.claude/skills/pdf/forms.md b/.claude/skills/pdf/forms.md new file mode 100644 index 0000000..6e7e1e0 --- /dev/null +++ b/.claude/skills/pdf/forms.md @@ -0,0 +1,294 @@ +**CRITICAL: You MUST complete these steps in order. Do not skip ahead to writing code.** + +If you need to fill out a PDF form, first check to see if the PDF has fillable form fields. Run this script from this file's directory: + `python scripts/check_fillable_fields `, and depending on the result go to either the "Fillable fields" or "Non-fillable fields" and follow those instructions. + +# Fillable fields +If the PDF has fillable form fields: +- Run this script from this file's directory: `python scripts/extract_form_field_info.py `. It will create a JSON file with a list of fields in this format: +``` +[ + { + "field_id": (unique ID for the field), + "page": (page number, 1-based), + "rect": ([left, bottom, right, top] bounding box in PDF coordinates, y=0 is the bottom of the page), + "type": ("text", "checkbox", "radio_group", or "choice"), + }, + // Checkboxes have "checked_value" and "unchecked_value" properties: + { + "field_id": (unique ID for the field), + "page": (page number, 1-based), + "type": "checkbox", + "checked_value": (Set the field to this value to check the checkbox), + "unchecked_value": (Set the field to this value to uncheck the checkbox), + }, + // Radio groups have a "radio_options" list with the possible choices. + { + "field_id": (unique ID for the field), + "page": (page number, 1-based), + "type": "radio_group", + "radio_options": [ + { + "value": (set the field to this value to select this radio option), + "rect": (bounding box for the radio button for this option) + }, + // Other radio options + ] + }, + // Multiple choice fields have a "choice_options" list with the possible choices: + { + "field_id": (unique ID for the field), + "page": (page number, 1-based), + "type": "choice", + "choice_options": [ + { + "value": (set the field to this value to select this option), + "text": (display text of the option) + }, + // Other choice options + ], + } +] +``` +- Convert the PDF to PNGs (one image for each page) with this script (run from this file's directory): +`python scripts/convert_pdf_to_images.py ` +Then analyze the images to determine the purpose of each form field (make sure to convert the bounding box PDF coordinates to image coordinates). +- Create a `field_values.json` file in this format with the values to be entered for each field: +``` +[ + { + "field_id": "last_name", // Must match the field_id from `extract_form_field_info.py` + "description": "The user's last name", + "page": 1, // Must match the "page" value in field_info.json + "value": "Simpson" + }, + { + "field_id": "Checkbox12", + "description": "Checkbox to be checked if the user is 18 or over", + "page": 1, + "value": "/On" // If this is a checkbox, use its "checked_value" value to check it. If it's a radio button group, use one of the "value" values in "radio_options". + }, + // more fields +] +``` +- Run the `fill_fillable_fields.py` script from this file's directory to create a filled-in PDF: +`python scripts/fill_fillable_fields.py ` +This script will verify that the field IDs and values you provide are valid; if it prints error messages, correct the appropriate fields and try again. + +# Non-fillable fields +If the PDF doesn't have fillable form fields, you'll add text annotations. First try to extract coordinates from the PDF structure (more accurate), then fall back to visual estimation if needed. + +## Step 1: Try Structure Extraction First + +Run this script to extract text labels, lines, and checkboxes with their exact PDF coordinates: +`python scripts/extract_form_structure.py form_structure.json` + +This creates a JSON file containing: +- **labels**: Every text element with exact coordinates (x0, top, x1, bottom in PDF points) +- **lines**: Horizontal lines that define row boundaries +- **checkboxes**: Small square rectangles that are checkboxes (with center coordinates) +- **row_boundaries**: Row top/bottom positions calculated from horizontal lines + +**Check the results**: If `form_structure.json` has meaningful labels (text elements that correspond to form fields), use **Approach A: Structure-Based Coordinates**. If the PDF is scanned/image-based and has few or no labels, use **Approach B: Visual Estimation**. + +--- + +## Approach A: Structure-Based Coordinates (Preferred) + +Use this when `extract_form_structure.py` found text labels in the PDF. + +### A.1: Analyze the Structure + +Read form_structure.json and identify: + +1. **Label groups**: Adjacent text elements that form a single label (e.g., "Last" + "Name") +2. **Row structure**: Labels with similar `top` values are in the same row +3. **Field columns**: Entry areas start after label ends (x0 = label.x1 + gap) +4. **Checkboxes**: Use the checkbox coordinates directly from the structure + +**Coordinate system**: PDF coordinates where y=0 is at TOP of page, y increases downward. + +### A.2: Check for Missing Elements + +The structure extraction may not detect all form elements. Common cases: +- **Circular checkboxes**: Only square rectangles are detected as checkboxes +- **Complex graphics**: Decorative elements or non-standard form controls +- **Faded or light-colored elements**: May not be extracted + +If you see form fields in the PDF images that aren't in form_structure.json, you'll need to use **visual analysis** for those specific fields (see "Hybrid Approach" below). + +### A.3: Create fields.json with PDF Coordinates + +For each field, calculate entry coordinates from the extracted structure: + +**Text fields:** +- entry x0 = label x1 + 5 (small gap after label) +- entry x1 = next label's x0, or row boundary +- entry top = same as label top +- entry bottom = row boundary line below, or label bottom + row_height + +**Checkboxes:** +- Use the checkbox rectangle coordinates directly from form_structure.json +- entry_bounding_box = [checkbox.x0, checkbox.top, checkbox.x1, checkbox.bottom] + +Create fields.json using `pdf_width` and `pdf_height` (signals PDF coordinates): +```json +{ + "pages": [ + {"page_number": 1, "pdf_width": 612, "pdf_height": 792} + ], + "form_fields": [ + { + "page_number": 1, + "description": "Last name entry field", + "field_label": "Last Name", + "label_bounding_box": [43, 63, 87, 73], + "entry_bounding_box": [92, 63, 260, 79], + "entry_text": {"text": "Smith", "font_size": 10} + }, + { + "page_number": 1, + "description": "US Citizen Yes checkbox", + "field_label": "Yes", + "label_bounding_box": [260, 200, 280, 210], + "entry_bounding_box": [285, 197, 292, 205], + "entry_text": {"text": "X"} + } + ] +} +``` + +**Important**: Use `pdf_width`/`pdf_height` and coordinates directly from form_structure.json. + +### A.4: Validate Bounding Boxes + +Before filling, check your bounding boxes for errors: +`python scripts/check_bounding_boxes.py fields.json` + +This checks for intersecting bounding boxes and entry boxes that are too small for the font size. Fix any reported errors before filling. + +--- + +## Approach B: Visual Estimation (Fallback) + +Use this when the PDF is scanned/image-based and structure extraction found no usable text labels (e.g., all text shows as "(cid:X)" patterns). + +### B.1: Convert PDF to Images + +`python scripts/convert_pdf_to_images.py ` + +### B.2: Initial Field Identification + +Examine each page image to identify form sections and get **rough estimates** of field locations: +- Form field labels and their approximate positions +- Entry areas (lines, boxes, or blank spaces for text input) +- Checkboxes and their approximate locations + +For each field, note approximate pixel coordinates (they don't need to be precise yet). + +### B.3: Zoom Refinement (CRITICAL for accuracy) + +For each field, crop a region around the estimated position to refine coordinates precisely. + +**Create a zoomed crop using ImageMagick:** +```bash +magick -crop x++ +repage +``` + +Where: +- `, ` = top-left corner of crop region (use your rough estimate minus padding) +- `, ` = size of crop region (field area plus ~50px padding on each side) + +**Example:** To refine a "Name" field estimated around (100, 150): +```bash +magick images_dir/page_1.png -crop 300x80+50+120 +repage crops/name_field.png +``` + +(Note: if the `magick` command isn't available, try `convert` with the same arguments). + +**Examine the cropped image** to determine precise coordinates: +1. Identify the exact pixel where the entry area begins (after the label) +2. Identify where the entry area ends (before next field or edge) +3. Identify the top and bottom of the entry line/box + +**Convert crop coordinates back to full image coordinates:** +- full_x = crop_x + crop_offset_x +- full_y = crop_y + crop_offset_y + +Example: If the crop started at (50, 120) and the entry box starts at (52, 18) within the crop: +- entry_x0 = 52 + 50 = 102 +- entry_top = 18 + 120 = 138 + +**Repeat for each field**, grouping nearby fields into single crops when possible. + +### B.4: Create fields.json with Refined Coordinates + +Create fields.json using `image_width` and `image_height` (signals image coordinates): +```json +{ + "pages": [ + {"page_number": 1, "image_width": 1700, "image_height": 2200} + ], + "form_fields": [ + { + "page_number": 1, + "description": "Last name entry field", + "field_label": "Last Name", + "label_bounding_box": [120, 175, 242, 198], + "entry_bounding_box": [255, 175, 720, 218], + "entry_text": {"text": "Smith", "font_size": 10} + } + ] +} +``` + +**Important**: Use `image_width`/`image_height` and the refined pixel coordinates from the zoom analysis. + +### B.5: Validate Bounding Boxes + +Before filling, check your bounding boxes for errors: +`python scripts/check_bounding_boxes.py fields.json` + +This checks for intersecting bounding boxes and entry boxes that are too small for the font size. Fix any reported errors before filling. + +--- + +## Hybrid Approach: Structure + Visual + +Use this when structure extraction works for most fields but misses some elements (e.g., circular checkboxes, unusual form controls). + +1. **Use Approach A** for fields that were detected in form_structure.json +2. **Convert PDF to images** for visual analysis of missing fields +3. **Use zoom refinement** (from Approach B) for the missing fields +4. **Combine coordinates**: For fields from structure extraction, use `pdf_width`/`pdf_height`. For visually-estimated fields, you must convert image coordinates to PDF coordinates: + - pdf_x = image_x * (pdf_width / image_width) + - pdf_y = image_y * (pdf_height / image_height) +5. **Use a single coordinate system** in fields.json - convert all to PDF coordinates with `pdf_width`/`pdf_height` + +--- + +## Step 2: Validate Before Filling + +**Always validate bounding boxes before filling:** +`python scripts/check_bounding_boxes.py fields.json` + +This checks for: +- Intersecting bounding boxes (which would cause overlapping text) +- Entry boxes that are too small for the specified font size + +Fix any reported errors in fields.json before proceeding. + +## Step 3: Fill the Form + +The fill script auto-detects the coordinate system and handles conversion: +`python scripts/fill_pdf_form_with_annotations.py fields.json ` + +## Step 4: Verify Output + +Convert the filled PDF to images and verify text placement: +`python scripts/convert_pdf_to_images.py ` + +If text is mispositioned: +- **Approach A**: Check that you're using PDF coordinates from form_structure.json with `pdf_width`/`pdf_height` +- **Approach B**: Check that image dimensions match and coordinates are accurate pixels +- **Hybrid**: Ensure coordinate conversions are correct for visually-estimated fields diff --git a/.claude/skills/pdf/reference.md b/.claude/skills/pdf/reference.md new file mode 100644 index 0000000..41400bf --- /dev/null +++ b/.claude/skills/pdf/reference.md @@ -0,0 +1,612 @@ +# PDF Processing Advanced Reference + +This document contains advanced PDF processing features, detailed examples, and additional libraries not covered in the main skill instructions. + +## pypdfium2 Library (Apache/BSD License) + +### Overview +pypdfium2 is a Python binding for PDFium (Chromium's PDF library). It's excellent for fast PDF rendering, image generation, and serves as a PyMuPDF replacement. + +### Render PDF to Images +```python +import pypdfium2 as pdfium +from PIL import Image + +# Load PDF +pdf = pdfium.PdfDocument("document.pdf") + +# Render page to image +page = pdf[0] # First page +bitmap = page.render( + scale=2.0, # Higher resolution + rotation=0 # No rotation +) + +# Convert to PIL Image +img = bitmap.to_pil() +img.save("page_1.png", "PNG") + +# Process multiple pages +for i, page in enumerate(pdf): + bitmap = page.render(scale=1.5) + img = bitmap.to_pil() + img.save(f"page_{i+1}.jpg", "JPEG", quality=90) +``` + +### Extract Text with pypdfium2 +```python +import pypdfium2 as pdfium + +pdf = pdfium.PdfDocument("document.pdf") +for i, page in enumerate(pdf): + text = page.get_text() + print(f"Page {i+1} text length: {len(text)} chars") +``` + +## JavaScript Libraries + +### pdf-lib (MIT License) + +pdf-lib is a powerful JavaScript library for creating and modifying PDF documents in any JavaScript environment. + +#### Load and Manipulate Existing PDF +```javascript +import { PDFDocument } from 'pdf-lib'; +import fs from 'fs'; + +async function manipulatePDF() { + // Load existing PDF + const existingPdfBytes = fs.readFileSync('input.pdf'); + const pdfDoc = await PDFDocument.load(existingPdfBytes); + + // Get page count + const pageCount = pdfDoc.getPageCount(); + console.log(`Document has ${pageCount} pages`); + + // Add new page + const newPage = pdfDoc.addPage([600, 400]); + newPage.drawText('Added by pdf-lib', { + x: 100, + y: 300, + size: 16 + }); + + // Save modified PDF + const pdfBytes = await pdfDoc.save(); + fs.writeFileSync('modified.pdf', pdfBytes); +} +``` + +#### Create Complex PDFs from Scratch +```javascript +import { PDFDocument, rgb, StandardFonts } from 'pdf-lib'; +import fs from 'fs'; + +async function createPDF() { + const pdfDoc = await PDFDocument.create(); + + // Add fonts + const helveticaFont = await pdfDoc.embedFont(StandardFonts.Helvetica); + const helveticaBold = await pdfDoc.embedFont(StandardFonts.HelveticaBold); + + // Add page + const page = pdfDoc.addPage([595, 842]); // A4 size + const { width, height } = page.getSize(); + + // Add text with styling + page.drawText('Invoice #12345', { + x: 50, + y: height - 50, + size: 18, + font: helveticaBold, + color: rgb(0.2, 0.2, 0.8) + }); + + // Add rectangle (header background) + page.drawRectangle({ + x: 40, + y: height - 100, + width: width - 80, + height: 30, + color: rgb(0.9, 0.9, 0.9) + }); + + // Add table-like content + const items = [ + ['Item', 'Qty', 'Price', 'Total'], + ['Widget', '2', '$50', '$100'], + ['Gadget', '1', '$75', '$75'] + ]; + + let yPos = height - 150; + items.forEach(row => { + let xPos = 50; + row.forEach(cell => { + page.drawText(cell, { + x: xPos, + y: yPos, + size: 12, + font: helveticaFont + }); + xPos += 120; + }); + yPos -= 25; + }); + + const pdfBytes = await pdfDoc.save(); + fs.writeFileSync('created.pdf', pdfBytes); +} +``` + +#### Advanced Merge and Split Operations +```javascript +import { PDFDocument } from 'pdf-lib'; +import fs from 'fs'; + +async function mergePDFs() { + // Create new document + const mergedPdf = await PDFDocument.create(); + + // Load source PDFs + const pdf1Bytes = fs.readFileSync('doc1.pdf'); + const pdf2Bytes = fs.readFileSync('doc2.pdf'); + + const pdf1 = await PDFDocument.load(pdf1Bytes); + const pdf2 = await PDFDocument.load(pdf2Bytes); + + // Copy pages from first PDF + const pdf1Pages = await mergedPdf.copyPages(pdf1, pdf1.getPageIndices()); + pdf1Pages.forEach(page => mergedPdf.addPage(page)); + + // Copy specific pages from second PDF (pages 0, 2, 4) + const pdf2Pages = await mergedPdf.copyPages(pdf2, [0, 2, 4]); + pdf2Pages.forEach(page => mergedPdf.addPage(page)); + + const mergedPdfBytes = await mergedPdf.save(); + fs.writeFileSync('merged.pdf', mergedPdfBytes); +} +``` + +### pdfjs-dist (Apache License) + +PDF.js is Mozilla's JavaScript library for rendering PDFs in the browser. + +#### Basic PDF Loading and Rendering +```javascript +import * as pdfjsLib from 'pdfjs-dist'; + +// Configure worker (important for performance) +pdfjsLib.GlobalWorkerOptions.workerSrc = './pdf.worker.js'; + +async function renderPDF() { + // Load PDF + const loadingTask = pdfjsLib.getDocument('document.pdf'); + const pdf = await loadingTask.promise; + + console.log(`Loaded PDF with ${pdf.numPages} pages`); + + // Get first page + const page = await pdf.getPage(1); + const viewport = page.getViewport({ scale: 1.5 }); + + // Render to canvas + const canvas = document.createElement('canvas'); + const context = canvas.getContext('2d'); + canvas.height = viewport.height; + canvas.width = viewport.width; + + const renderContext = { + canvasContext: context, + viewport: viewport + }; + + await page.render(renderContext).promise; + document.body.appendChild(canvas); +} +``` + +#### Extract Text with Coordinates +```javascript +import * as pdfjsLib from 'pdfjs-dist'; + +async function extractText() { + const loadingTask = pdfjsLib.getDocument('document.pdf'); + const pdf = await loadingTask.promise; + + let fullText = ''; + + // Extract text from all pages + for (let i = 1; i <= pdf.numPages; i++) { + const page = await pdf.getPage(i); + const textContent = await page.getTextContent(); + + const pageText = textContent.items + .map(item => item.str) + .join(' '); + + fullText += `\n--- Page ${i} ---\n${pageText}`; + + // Get text with coordinates for advanced processing + const textWithCoords = textContent.items.map(item => ({ + text: item.str, + x: item.transform[4], + y: item.transform[5], + width: item.width, + height: item.height + })); + } + + console.log(fullText); + return fullText; +} +``` + +#### Extract Annotations and Forms +```javascript +import * as pdfjsLib from 'pdfjs-dist'; + +async function extractAnnotations() { + const loadingTask = pdfjsLib.getDocument('annotated.pdf'); + const pdf = await loadingTask.promise; + + for (let i = 1; i <= pdf.numPages; i++) { + const page = await pdf.getPage(i); + const annotations = await page.getAnnotations(); + + annotations.forEach(annotation => { + console.log(`Annotation type: ${annotation.subtype}`); + console.log(`Content: ${annotation.contents}`); + console.log(`Coordinates: ${JSON.stringify(annotation.rect)}`); + }); + } +} +``` + +## Advanced Command-Line Operations + +### poppler-utils Advanced Features + +#### Extract Text with Bounding Box Coordinates +```bash +# Extract text with bounding box coordinates (essential for structured data) +pdftotext -bbox-layout document.pdf output.xml + +# The XML output contains precise coordinates for each text element +``` + +#### Advanced Image Conversion +```bash +# Convert to PNG images with specific resolution +pdftoppm -png -r 300 document.pdf output_prefix + +# Convert specific page range with high resolution +pdftoppm -png -r 600 -f 1 -l 3 document.pdf high_res_pages + +# Convert to JPEG with quality setting +pdftoppm -jpeg -jpegopt quality=85 -r 200 document.pdf jpeg_output +``` + +#### Extract Embedded Images +```bash +# Extract all embedded images with metadata +pdfimages -j -p document.pdf page_images + +# List image info without extracting +pdfimages -list document.pdf + +# Extract images in their original format +pdfimages -all document.pdf images/img +``` + +### qpdf Advanced Features + +#### Complex Page Manipulation +```bash +# Split PDF into groups of pages +qpdf --split-pages=3 input.pdf output_group_%02d.pdf + +# Extract specific pages with complex ranges +qpdf input.pdf --pages input.pdf 1,3-5,8,10-end -- extracted.pdf + +# Merge specific pages from multiple PDFs +qpdf --empty --pages doc1.pdf 1-3 doc2.pdf 5-7 doc3.pdf 2,4 -- combined.pdf +``` + +#### PDF Optimization and Repair +```bash +# Optimize PDF for web (linearize for streaming) +qpdf --linearize input.pdf optimized.pdf + +# Remove unused objects and compress +qpdf --optimize-level=all input.pdf compressed.pdf + +# Attempt to repair corrupted PDF structure +qpdf --check input.pdf +qpdf --fix-qdf damaged.pdf repaired.pdf + +# Show detailed PDF structure for debugging +qpdf --show-all-pages input.pdf > structure.txt +``` + +#### Advanced Encryption +```bash +# Add password protection with specific permissions +qpdf --encrypt user_pass owner_pass 256 --print=none --modify=none -- input.pdf encrypted.pdf + +# Check encryption status +qpdf --show-encryption encrypted.pdf + +# Remove password protection (requires password) +qpdf --password=secret123 --decrypt encrypted.pdf decrypted.pdf +``` + +## Advanced Python Techniques + +### pdfplumber Advanced Features + +#### Extract Text with Precise Coordinates +```python +import pdfplumber + +with pdfplumber.open("document.pdf") as pdf: + page = pdf.pages[0] + + # Extract all text with coordinates + chars = page.chars + for char in chars[:10]: # First 10 characters + print(f"Char: '{char['text']}' at x:{char['x0']:.1f} y:{char['y0']:.1f}") + + # Extract text by bounding box (left, top, right, bottom) + bbox_text = page.within_bbox((100, 100, 400, 200)).extract_text() +``` + +#### Advanced Table Extraction with Custom Settings +```python +import pdfplumber +import pandas as pd + +with pdfplumber.open("complex_table.pdf") as pdf: + page = pdf.pages[0] + + # Extract tables with custom settings for complex layouts + table_settings = { + "vertical_strategy": "lines", + "horizontal_strategy": "lines", + "snap_tolerance": 3, + "intersection_tolerance": 15 + } + tables = page.extract_tables(table_settings) + + # Visual debugging for table extraction + img = page.to_image(resolution=150) + img.save("debug_layout.png") +``` + +### reportlab Advanced Features + +#### Create Professional Reports with Tables +```python +from reportlab.platypus import SimpleDocTemplate, Table, TableStyle, Paragraph +from reportlab.lib.styles import getSampleStyleSheet +from reportlab.lib import colors + +# Sample data +data = [ + ['Product', 'Q1', 'Q2', 'Q3', 'Q4'], + ['Widgets', '120', '135', '142', '158'], + ['Gadgets', '85', '92', '98', '105'] +] + +# Create PDF with table +doc = SimpleDocTemplate("report.pdf") +elements = [] + +# Add title +styles = getSampleStyleSheet() +title = Paragraph("Quarterly Sales Report", styles['Title']) +elements.append(title) + +# Add table with advanced styling +table = Table(data) +table.setStyle(TableStyle([ + ('BACKGROUND', (0, 0), (-1, 0), colors.grey), + ('TEXTCOLOR', (0, 0), (-1, 0), colors.whitesmoke), + ('ALIGN', (0, 0), (-1, -1), 'CENTER'), + ('FONTNAME', (0, 0), (-1, 0), 'Helvetica-Bold'), + ('FONTSIZE', (0, 0), (-1, 0), 14), + ('BOTTOMPADDING', (0, 0), (-1, 0), 12), + ('BACKGROUND', (0, 1), (-1, -1), colors.beige), + ('GRID', (0, 0), (-1, -1), 1, colors.black) +])) +elements.append(table) + +doc.build(elements) +``` + +## Complex Workflows + +### Extract Figures/Images from PDF + +#### Method 1: Using pdfimages (fastest) +```bash +# Extract all images with original quality +pdfimages -all document.pdf images/img +``` + +#### Method 2: Using pypdfium2 + Image Processing +```python +import pypdfium2 as pdfium +from PIL import Image +import numpy as np + +def extract_figures(pdf_path, output_dir): + pdf = pdfium.PdfDocument(pdf_path) + + for page_num, page in enumerate(pdf): + # Render high-resolution page + bitmap = page.render(scale=3.0) + img = bitmap.to_pil() + + # Convert to numpy for processing + img_array = np.array(img) + + # Simple figure detection (non-white regions) + mask = np.any(img_array != [255, 255, 255], axis=2) + + # Find contours and extract bounding boxes + # (This is simplified - real implementation would need more sophisticated detection) + + # Save detected figures + # ... implementation depends on specific needs +``` + +### Batch PDF Processing with Error Handling +```python +import os +import glob +from pypdf import PdfReader, PdfWriter +import logging + +logging.basicConfig(level=logging.INFO) +logger = logging.getLogger(__name__) + +def batch_process_pdfs(input_dir, operation='merge'): + pdf_files = glob.glob(os.path.join(input_dir, "*.pdf")) + + if operation == 'merge': + writer = PdfWriter() + for pdf_file in pdf_files: + try: + reader = PdfReader(pdf_file) + for page in reader.pages: + writer.add_page(page) + logger.info(f"Processed: {pdf_file}") + except Exception as e: + logger.error(f"Failed to process {pdf_file}: {e}") + continue + + with open("batch_merged.pdf", "wb") as output: + writer.write(output) + + elif operation == 'extract_text': + for pdf_file in pdf_files: + try: + reader = PdfReader(pdf_file) + text = "" + for page in reader.pages: + text += page.extract_text() + + output_file = pdf_file.replace('.pdf', '.txt') + with open(output_file, 'w', encoding='utf-8') as f: + f.write(text) + logger.info(f"Extracted text from: {pdf_file}") + + except Exception as e: + logger.error(f"Failed to extract text from {pdf_file}: {e}") + continue +``` + +### Advanced PDF Cropping +```python +from pypdf import PdfWriter, PdfReader + +reader = PdfReader("input.pdf") +writer = PdfWriter() + +# Crop page (left, bottom, right, top in points) +page = reader.pages[0] +page.mediabox.left = 50 +page.mediabox.bottom = 50 +page.mediabox.right = 550 +page.mediabox.top = 750 + +writer.add_page(page) +with open("cropped.pdf", "wb") as output: + writer.write(output) +``` + +## Performance Optimization Tips + +### 1. For Large PDFs +- Use streaming approaches instead of loading entire PDF in memory +- Use `qpdf --split-pages` for splitting large files +- Process pages individually with pypdfium2 + +### 2. For Text Extraction +- `pdftotext -bbox-layout` is fastest for plain text extraction +- Use pdfplumber for structured data and tables +- Avoid `pypdf.extract_text()` for very large documents + +### 3. For Image Extraction +- `pdfimages` is much faster than rendering pages +- Use low resolution for previews, high resolution for final output + +### 4. For Form Filling +- pdf-lib maintains form structure better than most alternatives +- Pre-validate form fields before processing + +### 5. Memory Management +```python +# Process PDFs in chunks +def process_large_pdf(pdf_path, chunk_size=10): + reader = PdfReader(pdf_path) + total_pages = len(reader.pages) + + for start_idx in range(0, total_pages, chunk_size): + end_idx = min(start_idx + chunk_size, total_pages) + writer = PdfWriter() + + for i in range(start_idx, end_idx): + writer.add_page(reader.pages[i]) + + # Process chunk + with open(f"chunk_{start_idx//chunk_size}.pdf", "wb") as output: + writer.write(output) +``` + +## Troubleshooting Common Issues + +### Encrypted PDFs +```python +# Handle password-protected PDFs +from pypdf import PdfReader + +try: + reader = PdfReader("encrypted.pdf") + if reader.is_encrypted: + reader.decrypt("password") +except Exception as e: + print(f"Failed to decrypt: {e}") +``` + +### Corrupted PDFs +```bash +# Use qpdf to repair +qpdf --check corrupted.pdf +qpdf --replace-input corrupted.pdf +``` + +### Text Extraction Issues +```python +# Fallback to OCR for scanned PDFs +import pytesseract +from pdf2image import convert_from_path + +def extract_text_with_ocr(pdf_path): + images = convert_from_path(pdf_path) + text = "" + for i, image in enumerate(images): + text += pytesseract.image_to_string(image) + return text +``` + +## License Information + +- **pypdf**: BSD License +- **pdfplumber**: MIT License +- **pypdfium2**: Apache/BSD License +- **reportlab**: BSD License +- **poppler-utils**: GPL-2 License +- **qpdf**: Apache License +- **pdf-lib**: MIT License +- **pdfjs-dist**: Apache License \ No newline at end of file diff --git a/.claude/skills/pdf/scripts/check_bounding_boxes.py b/.claude/skills/pdf/scripts/check_bounding_boxes.py new file mode 100644 index 0000000..2cc5e34 --- /dev/null +++ b/.claude/skills/pdf/scripts/check_bounding_boxes.py @@ -0,0 +1,65 @@ +from dataclasses import dataclass +import json +import sys + + + + +@dataclass +class RectAndField: + rect: list[float] + rect_type: str + field: dict + + +def get_bounding_box_messages(fields_json_stream) -> list[str]: + messages = [] + fields = json.load(fields_json_stream) + messages.append(f"Read {len(fields['form_fields'])} fields") + + def rects_intersect(r1, r2): + disjoint_horizontal = r1[0] >= r2[2] or r1[2] <= r2[0] + disjoint_vertical = r1[1] >= r2[3] or r1[3] <= r2[1] + return not (disjoint_horizontal or disjoint_vertical) + + rects_and_fields = [] + for f in fields["form_fields"]: + rects_and_fields.append(RectAndField(f["label_bounding_box"], "label", f)) + rects_and_fields.append(RectAndField(f["entry_bounding_box"], "entry", f)) + + has_error = False + for i, ri in enumerate(rects_and_fields): + for j in range(i + 1, len(rects_and_fields)): + rj = rects_and_fields[j] + if ri.field["page_number"] == rj.field["page_number"] and rects_intersect(ri.rect, rj.rect): + has_error = True + if ri.field is rj.field: + messages.append(f"FAILURE: intersection between label and entry bounding boxes for `{ri.field['description']}` ({ri.rect}, {rj.rect})") + else: + messages.append(f"FAILURE: intersection between {ri.rect_type} bounding box for `{ri.field['description']}` ({ri.rect}) and {rj.rect_type} bounding box for `{rj.field['description']}` ({rj.rect})") + if len(messages) >= 20: + messages.append("Aborting further checks; fix bounding boxes and try again") + return messages + if ri.rect_type == "entry": + if "entry_text" in ri.field: + font_size = ri.field["entry_text"].get("font_size", 14) + entry_height = ri.rect[3] - ri.rect[1] + if entry_height < font_size: + has_error = True + messages.append(f"FAILURE: entry bounding box height ({entry_height}) for `{ri.field['description']}` is too short for the text content (font size: {font_size}). Increase the box height or decrease the font size.") + if len(messages) >= 20: + messages.append("Aborting further checks; fix bounding boxes and try again") + return messages + + if not has_error: + messages.append("SUCCESS: All bounding boxes are valid") + return messages + +if __name__ == "__main__": + if len(sys.argv) != 2: + print("Usage: check_bounding_boxes.py [fields.json]") + sys.exit(1) + with open(sys.argv[1]) as f: + messages = get_bounding_box_messages(f) + for msg in messages: + print(msg) diff --git a/.claude/skills/pdf/scripts/check_fillable_fields.py b/.claude/skills/pdf/scripts/check_fillable_fields.py new file mode 100644 index 0000000..36dfb95 --- /dev/null +++ b/.claude/skills/pdf/scripts/check_fillable_fields.py @@ -0,0 +1,11 @@ +import sys +from pypdf import PdfReader + + + + +reader = PdfReader(sys.argv[1]) +if (reader.get_fields()): + print("This PDF has fillable form fields") +else: + print("This PDF does not have fillable form fields; you will need to visually determine where to enter data") diff --git a/.claude/skills/pdf/scripts/convert_pdf_to_images.py b/.claude/skills/pdf/scripts/convert_pdf_to_images.py new file mode 100644 index 0000000..7939cef --- /dev/null +++ b/.claude/skills/pdf/scripts/convert_pdf_to_images.py @@ -0,0 +1,33 @@ +import os +import sys + +from pdf2image import convert_from_path + + + + +def convert(pdf_path, output_dir, max_dim=1000): + images = convert_from_path(pdf_path, dpi=200) + + for i, image in enumerate(images): + width, height = image.size + if width > max_dim or height > max_dim: + scale_factor = min(max_dim / width, max_dim / height) + new_width = int(width * scale_factor) + new_height = int(height * scale_factor) + image = image.resize((new_width, new_height)) + + image_path = os.path.join(output_dir, f"page_{i+1}.png") + image.save(image_path) + print(f"Saved page {i+1} as {image_path} (size: {image.size})") + + print(f"Converted {len(images)} pages to PNG images") + + +if __name__ == "__main__": + if len(sys.argv) != 3: + print("Usage: convert_pdf_to_images.py [input pdf] [output directory]") + sys.exit(1) + pdf_path = sys.argv[1] + output_directory = sys.argv[2] + convert(pdf_path, output_directory) diff --git a/.claude/skills/pdf/scripts/create_validation_image.py b/.claude/skills/pdf/scripts/create_validation_image.py new file mode 100644 index 0000000..10eadd8 --- /dev/null +++ b/.claude/skills/pdf/scripts/create_validation_image.py @@ -0,0 +1,37 @@ +import json +import sys + +from PIL import Image, ImageDraw + + + + +def create_validation_image(page_number, fields_json_path, input_path, output_path): + with open(fields_json_path, 'r') as f: + data = json.load(f) + + img = Image.open(input_path) + draw = ImageDraw.Draw(img) + num_boxes = 0 + + for field in data["form_fields"]: + if field["page_number"] == page_number: + entry_box = field['entry_bounding_box'] + label_box = field['label_bounding_box'] + draw.rectangle(entry_box, outline='red', width=2) + draw.rectangle(label_box, outline='blue', width=2) + num_boxes += 2 + + img.save(output_path) + print(f"Created validation image at {output_path} with {num_boxes} bounding boxes") + + +if __name__ == "__main__": + if len(sys.argv) != 5: + print("Usage: create_validation_image.py [page number] [fields.json file] [input image path] [output image path]") + sys.exit(1) + page_number = int(sys.argv[1]) + fields_json_path = sys.argv[2] + input_image_path = sys.argv[3] + output_image_path = sys.argv[4] + create_validation_image(page_number, fields_json_path, input_image_path, output_image_path) diff --git a/.claude/skills/pdf/scripts/extract_form_field_info.py b/.claude/skills/pdf/scripts/extract_form_field_info.py new file mode 100644 index 0000000..64cd470 --- /dev/null +++ b/.claude/skills/pdf/scripts/extract_form_field_info.py @@ -0,0 +1,122 @@ +import json +import sys + +from pypdf import PdfReader + + + + +def get_full_annotation_field_id(annotation): + components = [] + while annotation: + field_name = annotation.get('/T') + if field_name: + components.append(field_name) + annotation = annotation.get('/Parent') + return ".".join(reversed(components)) if components else None + + +def make_field_dict(field, field_id): + field_dict = {"field_id": field_id} + ft = field.get('/FT') + if ft == "/Tx": + field_dict["type"] = "text" + elif ft == "/Btn": + field_dict["type"] = "checkbox" + states = field.get("/_States_", []) + if len(states) == 2: + if "/Off" in states: + field_dict["checked_value"] = states[0] if states[0] != "/Off" else states[1] + field_dict["unchecked_value"] = "/Off" + else: + print(f"Unexpected state values for checkbox `${field_id}`. Its checked and unchecked values may not be correct; if you're trying to check it, visually verify the results.") + field_dict["checked_value"] = states[0] + field_dict["unchecked_value"] = states[1] + elif ft == "/Ch": + field_dict["type"] = "choice" + states = field.get("/_States_", []) + field_dict["choice_options"] = [{ + "value": state[0], + "text": state[1], + } for state in states] + else: + field_dict["type"] = f"unknown ({ft})" + return field_dict + + +def get_field_info(reader: PdfReader): + fields = reader.get_fields() + + field_info_by_id = {} + possible_radio_names = set() + + for field_id, field in fields.items(): + if field.get("/Kids"): + if field.get("/FT") == "/Btn": + possible_radio_names.add(field_id) + continue + field_info_by_id[field_id] = make_field_dict(field, field_id) + + + radio_fields_by_id = {} + + for page_index, page in enumerate(reader.pages): + annotations = page.get('/Annots', []) + for ann in annotations: + field_id = get_full_annotation_field_id(ann) + if field_id in field_info_by_id: + field_info_by_id[field_id]["page"] = page_index + 1 + field_info_by_id[field_id]["rect"] = ann.get('/Rect') + elif field_id in possible_radio_names: + try: + on_values = [v for v in ann["/AP"]["/N"] if v != "/Off"] + except KeyError: + continue + if len(on_values) == 1: + rect = ann.get("/Rect") + if field_id not in radio_fields_by_id: + radio_fields_by_id[field_id] = { + "field_id": field_id, + "type": "radio_group", + "page": page_index + 1, + "radio_options": [], + } + radio_fields_by_id[field_id]["radio_options"].append({ + "value": on_values[0], + "rect": rect, + }) + + fields_with_location = [] + for field_info in field_info_by_id.values(): + if "page" in field_info: + fields_with_location.append(field_info) + else: + print(f"Unable to determine location for field id: {field_info.get('field_id')}, ignoring") + + def sort_key(f): + if "radio_options" in f: + rect = f["radio_options"][0]["rect"] or [0, 0, 0, 0] + else: + rect = f.get("rect") or [0, 0, 0, 0] + adjusted_position = [-rect[1], rect[0]] + return [f.get("page"), adjusted_position] + + sorted_fields = fields_with_location + list(radio_fields_by_id.values()) + sorted_fields.sort(key=sort_key) + + return sorted_fields + + +def write_field_info(pdf_path: str, json_output_path: str): + reader = PdfReader(pdf_path) + field_info = get_field_info(reader) + with open(json_output_path, "w") as f: + json.dump(field_info, f, indent=2) + print(f"Wrote {len(field_info)} fields to {json_output_path}") + + +if __name__ == "__main__": + if len(sys.argv) != 3: + print("Usage: extract_form_field_info.py [input pdf] [output json]") + sys.exit(1) + write_field_info(sys.argv[1], sys.argv[2]) diff --git a/.claude/skills/pdf/scripts/extract_form_structure.py b/.claude/skills/pdf/scripts/extract_form_structure.py new file mode 100644 index 0000000..f219e7d --- /dev/null +++ b/.claude/skills/pdf/scripts/extract_form_structure.py @@ -0,0 +1,115 @@ +""" +Extract form structure from a non-fillable PDF. + +This script analyzes the PDF to find: +- Text labels with their exact coordinates +- Horizontal lines (row boundaries) +- Checkboxes (small rectangles) + +Output: A JSON file with the form structure that can be used to generate +accurate field coordinates for filling. + +Usage: python extract_form_structure.py +""" + +import json +import sys +import pdfplumber + + +def extract_form_structure(pdf_path): + structure = { + "pages": [], + "labels": [], + "lines": [], + "checkboxes": [], + "row_boundaries": [] + } + + with pdfplumber.open(pdf_path) as pdf: + for page_num, page in enumerate(pdf.pages, 1): + structure["pages"].append({ + "page_number": page_num, + "width": float(page.width), + "height": float(page.height) + }) + + words = page.extract_words() + for word in words: + structure["labels"].append({ + "page": page_num, + "text": word["text"], + "x0": round(float(word["x0"]), 1), + "top": round(float(word["top"]), 1), + "x1": round(float(word["x1"]), 1), + "bottom": round(float(word["bottom"]), 1) + }) + + for line in page.lines: + if abs(float(line["x1"]) - float(line["x0"])) > page.width * 0.5: + structure["lines"].append({ + "page": page_num, + "y": round(float(line["top"]), 1), + "x0": round(float(line["x0"]), 1), + "x1": round(float(line["x1"]), 1) + }) + + for rect in page.rects: + width = float(rect["x1"]) - float(rect["x0"]) + height = float(rect["bottom"]) - float(rect["top"]) + if 5 <= width <= 15 and 5 <= height <= 15 and abs(width - height) < 2: + structure["checkboxes"].append({ + "page": page_num, + "x0": round(float(rect["x0"]), 1), + "top": round(float(rect["top"]), 1), + "x1": round(float(rect["x1"]), 1), + "bottom": round(float(rect["bottom"]), 1), + "center_x": round((float(rect["x0"]) + float(rect["x1"])) / 2, 1), + "center_y": round((float(rect["top"]) + float(rect["bottom"])) / 2, 1) + }) + + lines_by_page = {} + for line in structure["lines"]: + page = line["page"] + if page not in lines_by_page: + lines_by_page[page] = [] + lines_by_page[page].append(line["y"]) + + for page, y_coords in lines_by_page.items(): + y_coords = sorted(set(y_coords)) + for i in range(len(y_coords) - 1): + structure["row_boundaries"].append({ + "page": page, + "row_top": y_coords[i], + "row_bottom": y_coords[i + 1], + "row_height": round(y_coords[i + 1] - y_coords[i], 1) + }) + + return structure + + +def main(): + if len(sys.argv) != 3: + print("Usage: extract_form_structure.py ") + sys.exit(1) + + pdf_path = sys.argv[1] + output_path = sys.argv[2] + + print(f"Extracting structure from {pdf_path}...") + structure = extract_form_structure(pdf_path) + + with open(output_path, "w") as f: + json.dump(structure, f, indent=2) + + print(f"Found:") + print(f" - {len(structure['pages'])} pages") + print(f" - {len(structure['labels'])} text labels") + print(f" - {len(structure['lines'])} horizontal lines") + print(f" - {len(structure['checkboxes'])} checkboxes") + print(f" - {len(structure['row_boundaries'])} row boundaries") + print(f"Saved to {output_path}") + + +if __name__ == "__main__": + main() diff --git a/.claude/skills/pdf/scripts/fill_fillable_fields.py b/.claude/skills/pdf/scripts/fill_fillable_fields.py new file mode 100644 index 0000000..51c2600 --- /dev/null +++ b/.claude/skills/pdf/scripts/fill_fillable_fields.py @@ -0,0 +1,98 @@ +import json +import sys + +from pypdf import PdfReader, PdfWriter + +from extract_form_field_info import get_field_info + + + + +def fill_pdf_fields(input_pdf_path: str, fields_json_path: str, output_pdf_path: str): + with open(fields_json_path) as f: + fields = json.load(f) + fields_by_page = {} + for field in fields: + if "value" in field: + field_id = field["field_id"] + page = field["page"] + if page not in fields_by_page: + fields_by_page[page] = {} + fields_by_page[page][field_id] = field["value"] + + reader = PdfReader(input_pdf_path) + + has_error = False + field_info = get_field_info(reader) + fields_by_ids = {f["field_id"]: f for f in field_info} + for field in fields: + existing_field = fields_by_ids.get(field["field_id"]) + if not existing_field: + has_error = True + print(f"ERROR: `{field['field_id']}` is not a valid field ID") + elif field["page"] != existing_field["page"]: + has_error = True + print(f"ERROR: Incorrect page number for `{field['field_id']}` (got {field['page']}, expected {existing_field['page']})") + else: + if "value" in field: + err = validation_error_for_field_value(existing_field, field["value"]) + if err: + print(err) + has_error = True + if has_error: + sys.exit(1) + + writer = PdfWriter(clone_from=reader) + for page, field_values in fields_by_page.items(): + writer.update_page_form_field_values(writer.pages[page - 1], field_values, auto_regenerate=False) + + writer.set_need_appearances_writer(True) + + with open(output_pdf_path, "wb") as f: + writer.write(f) + + +def validation_error_for_field_value(field_info, field_value): + field_type = field_info["type"] + field_id = field_info["field_id"] + if field_type == "checkbox": + checked_val = field_info["checked_value"] + unchecked_val = field_info["unchecked_value"] + if field_value != checked_val and field_value != unchecked_val: + return f'ERROR: Invalid value "{field_value}" for checkbox field "{field_id}". The checked value is "{checked_val}" and the unchecked value is "{unchecked_val}"' + elif field_type == "radio_group": + option_values = [opt["value"] for opt in field_info["radio_options"]] + if field_value not in option_values: + return f'ERROR: Invalid value "{field_value}" for radio group field "{field_id}". Valid values are: {option_values}' + elif field_type == "choice": + choice_values = [opt["value"] for opt in field_info["choice_options"]] + if field_value not in choice_values: + return f'ERROR: Invalid value "{field_value}" for choice field "{field_id}". Valid values are: {choice_values}' + return None + + +def monkeypatch_pydpf_method(): + from pypdf.generic import DictionaryObject + from pypdf.constants import FieldDictionaryAttributes + + original_get_inherited = DictionaryObject.get_inherited + + def patched_get_inherited(self, key: str, default = None): + result = original_get_inherited(self, key, default) + if key == FieldDictionaryAttributes.Opt: + if isinstance(result, list) and all(isinstance(v, list) and len(v) == 2 for v in result): + result = [r[0] for r in result] + return result + + DictionaryObject.get_inherited = patched_get_inherited + + +if __name__ == "__main__": + if len(sys.argv) != 4: + print("Usage: fill_fillable_fields.py [input pdf] [field_values.json] [output pdf]") + sys.exit(1) + monkeypatch_pydpf_method() + input_pdf = sys.argv[1] + fields_json = sys.argv[2] + output_pdf = sys.argv[3] + fill_pdf_fields(input_pdf, fields_json, output_pdf) diff --git a/.claude/skills/pdf/scripts/fill_pdf_form_with_annotations.py b/.claude/skills/pdf/scripts/fill_pdf_form_with_annotations.py new file mode 100644 index 0000000..b430069 --- /dev/null +++ b/.claude/skills/pdf/scripts/fill_pdf_form_with_annotations.py @@ -0,0 +1,107 @@ +import json +import sys + +from pypdf import PdfReader, PdfWriter +from pypdf.annotations import FreeText + + + + +def transform_from_image_coords(bbox, image_width, image_height, pdf_width, pdf_height): + x_scale = pdf_width / image_width + y_scale = pdf_height / image_height + + left = bbox[0] * x_scale + right = bbox[2] * x_scale + + top = pdf_height - (bbox[1] * y_scale) + bottom = pdf_height - (bbox[3] * y_scale) + + return left, bottom, right, top + + +def transform_from_pdf_coords(bbox, pdf_height): + left = bbox[0] + right = bbox[2] + + pypdf_top = pdf_height - bbox[1] + pypdf_bottom = pdf_height - bbox[3] + + return left, pypdf_bottom, right, pypdf_top + + +def fill_pdf_form(input_pdf_path, fields_json_path, output_pdf_path): + + with open(fields_json_path, "r") as f: + fields_data = json.load(f) + + reader = PdfReader(input_pdf_path) + writer = PdfWriter() + + writer.append(reader) + + pdf_dimensions = {} + for i, page in enumerate(reader.pages): + mediabox = page.mediabox + pdf_dimensions[i + 1] = [mediabox.width, mediabox.height] + + annotations = [] + for field in fields_data["form_fields"]: + page_num = field["page_number"] + + page_info = next(p for p in fields_data["pages"] if p["page_number"] == page_num) + pdf_width, pdf_height = pdf_dimensions[page_num] + + if "pdf_width" in page_info: + transformed_entry_box = transform_from_pdf_coords( + field["entry_bounding_box"], + float(pdf_height) + ) + else: + image_width = page_info["image_width"] + image_height = page_info["image_height"] + transformed_entry_box = transform_from_image_coords( + field["entry_bounding_box"], + image_width, image_height, + float(pdf_width), float(pdf_height) + ) + + if "entry_text" not in field or "text" not in field["entry_text"]: + continue + entry_text = field["entry_text"] + text = entry_text["text"] + if not text: + continue + + font_name = entry_text.get("font", "Arial") + font_size = str(entry_text.get("font_size", 14)) + "pt" + font_color = entry_text.get("font_color", "000000") + + annotation = FreeText( + text=text, + rect=transformed_entry_box, + font=font_name, + font_size=font_size, + font_color=font_color, + border_color=None, + background_color=None, + ) + annotations.append(annotation) + writer.add_annotation(page_number=page_num - 1, annotation=annotation) + + with open(output_pdf_path, "wb") as output: + writer.write(output) + + print(f"Successfully filled PDF form and saved to {output_pdf_path}") + print(f"Added {len(annotations)} text annotations") + + +if __name__ == "__main__": + if len(sys.argv) != 4: + print("Usage: fill_pdf_form_with_annotations.py [input pdf] [fields.json] [output pdf]") + sys.exit(1) + input_pdf = sys.argv[1] + fields_json = sys.argv[2] + output_pdf = sys.argv[3] + + fill_pdf_form(input_pdf, fields_json, output_pdf) diff --git a/.claude/skills/pptx/LICENSE.txt b/.claude/skills/pptx/LICENSE.txt new file mode 100644 index 0000000..c55ab42 --- /dev/null +++ b/.claude/skills/pptx/LICENSE.txt @@ -0,0 +1,30 @@ +© 2025 Anthropic, PBC. All rights reserved. + +LICENSE: Use of these materials (including all code, prompts, assets, files, +and other components of this Skill) is governed by your agreement with +Anthropic regarding use of Anthropic's services. If no separate agreement +exists, use is governed by Anthropic's Consumer Terms of Service or +Commercial Terms of Service, as applicable: +https://www.anthropic.com/legal/consumer-terms +https://www.anthropic.com/legal/commercial-terms +Your applicable agreement is referred to as the "Agreement." "Services" are +as defined in the Agreement. + +ADDITIONAL RESTRICTIONS: Notwithstanding anything in the Agreement to the +contrary, users may not: + +- Extract these materials from the Services or retain copies of these + materials outside the Services +- Reproduce or copy these materials, except for temporary copies created + automatically during authorized use of the Services +- Create derivative works based on these materials +- Distribute, sublicense, or transfer these materials to any third party +- Make, offer to sell, sell, or import any inventions embodied in these + materials +- Reverse engineer, decompile, or disassemble these materials + +The receipt, viewing, or possession of these materials does not convey or +imply any license or right beyond those expressly granted above. + +Anthropic retains all right, title, and interest in these materials, +including all copyrights, patents, and other intellectual property rights. diff --git a/.claude/skills/pptx/SKILL.md b/.claude/skills/pptx/SKILL.md new file mode 100644 index 0000000..df5000e --- /dev/null +++ b/.claude/skills/pptx/SKILL.md @@ -0,0 +1,232 @@ +--- +name: pptx +description: "Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill." +license: Proprietary. LICENSE.txt has complete terms +--- + +# PPTX Skill + +## Quick Reference + +| Task | Guide | +|------|-------| +| Read/analyze content | `python -m markitdown presentation.pptx` | +| Edit or create from template | Read [editing.md](editing.md) | +| Create from scratch | Read [pptxgenjs.md](pptxgenjs.md) | + +--- + +## Reading Content + +```bash +# Text extraction +python -m markitdown presentation.pptx + +# Visual overview +python scripts/thumbnail.py presentation.pptx + +# Raw XML +python scripts/office/unpack.py presentation.pptx unpacked/ +``` + +--- + +## Editing Workflow + +**Read [editing.md](editing.md) for full details.** + +1. Analyze template with `thumbnail.py` +2. Unpack → manipulate slides → edit content → clean → pack + +--- + +## Creating from Scratch + +**Read [pptxgenjs.md](pptxgenjs.md) for full details.** + +Use when no template or reference presentation is available. + +--- + +## Design Ideas + +**Don't create boring slides.** Plain bullets on a white background won't impress anyone. Consider ideas from this list for each slide. + +### Before Starting + +- **Pick a bold, content-informed color palette**: The palette should feel designed for THIS topic. If swapping your colors into a completely different presentation would still "work," you haven't made specific enough choices. +- **Dominance over equality**: One color should dominate (60-70% visual weight), with 1-2 supporting tones and one sharp accent. Never give all colors equal weight. +- **Dark/light contrast**: Dark backgrounds for title + conclusion slides, light for content ("sandwich" structure). Or commit to dark throughout for a premium feel. +- **Commit to a visual motif**: Pick ONE distinctive element and repeat it — rounded image frames, icons in colored circles, thick single-side borders. Carry it across every slide. + +### Color Palettes + +Choose colors that match your topic — don't default to generic blue. Use these palettes as inspiration: + +| Theme | Primary | Secondary | Accent | +|-------|---------|-----------|--------| +| **Midnight Executive** | `1E2761` (navy) | `CADCFC` (ice blue) | `FFFFFF` (white) | +| **Forest & Moss** | `2C5F2D` (forest) | `97BC62` (moss) | `F5F5F5` (cream) | +| **Coral Energy** | `F96167` (coral) | `F9E795` (gold) | `2F3C7E` (navy) | +| **Warm Terracotta** | `B85042` (terracotta) | `E7E8D1` (sand) | `A7BEAE` (sage) | +| **Ocean Gradient** | `065A82` (deep blue) | `1C7293` (teal) | `21295C` (midnight) | +| **Charcoal Minimal** | `36454F` (charcoal) | `F2F2F2` (off-white) | `212121` (black) | +| **Teal Trust** | `028090` (teal) | `00A896` (seafoam) | `02C39A` (mint) | +| **Berry & Cream** | `6D2E46` (berry) | `A26769` (dusty rose) | `ECE2D0` (cream) | +| **Sage Calm** | `84B59F` (sage) | `69A297` (eucalyptus) | `50808E` (slate) | +| **Cherry Bold** | `990011` (cherry) | `FCF6F5` (off-white) | `2F3C7E` (navy) | + +### For Each Slide + +**Every slide needs a visual element** — image, chart, icon, or shape. Text-only slides are forgettable. + +**Layout options:** +- Two-column (text left, illustration on right) +- Icon + text rows (icon in colored circle, bold header, description below) +- 2x2 or 2x3 grid (image on one side, grid of content blocks on other) +- Half-bleed image (full left or right side) with content overlay + +**Data display:** +- Large stat callouts (big numbers 60-72pt with small labels below) +- Comparison columns (before/after, pros/cons, side-by-side options) +- Timeline or process flow (numbered steps, arrows) + +**Visual polish:** +- Icons in small colored circles next to section headers +- Italic accent text for key stats or taglines + +### Typography + +**Choose an interesting font pairing** — don't default to Arial. Pick a header font with personality and pair it with a clean body font. + +| Header Font | Body Font | +|-------------|-----------| +| Georgia | Calibri | +| Arial Black | Arial | +| Calibri | Calibri Light | +| Cambria | Calibri | +| Trebuchet MS | Calibri | +| Impact | Arial | +| Palatino | Garamond | +| Consolas | Calibri | + +| Element | Size | +|---------|------| +| Slide title | 36-44pt bold | +| Section header | 20-24pt bold | +| Body text | 14-16pt | +| Captions | 10-12pt muted | + +### Spacing + +- 0.5" minimum margins +- 0.3-0.5" between content blocks +- Leave breathing room—don't fill every inch + +### Avoid (Common Mistakes) + +- **Don't repeat the same layout** — vary columns, cards, and callouts across slides +- **Don't center body text** — left-align paragraphs and lists; center only titles +- **Don't skimp on size contrast** — titles need 36pt+ to stand out from 14-16pt body +- **Don't default to blue** — pick colors that reflect the specific topic +- **Don't mix spacing randomly** — choose 0.3" or 0.5" gaps and use consistently +- **Don't style one slide and leave the rest plain** — commit fully or keep it simple throughout +- **Don't create text-only slides** — add images, icons, charts, or visual elements; avoid plain title + bullets +- **Don't forget text box padding** — when aligning lines or shapes with text edges, set `margin: 0` on the text box or offset the shape to account for padding +- **Don't use low-contrast elements** — icons AND text need strong contrast against the background; avoid light text on light backgrounds or dark text on dark backgrounds +- **NEVER use accent lines under titles** — these are a hallmark of AI-generated slides; use whitespace or background color instead + +--- + +## QA (Required) + +**Assume there are problems. Your job is to find them.** + +Your first render is almost never correct. Approach QA as a bug hunt, not a confirmation step. If you found zero issues on first inspection, you weren't looking hard enough. + +### Content QA + +```bash +python -m markitdown output.pptx +``` + +Check for missing content, typos, wrong order. + +**When using templates, check for leftover placeholder text:** + +```bash +python -m markitdown output.pptx | grep -iE "xxxx|lorem|ipsum|this.*(page|slide).*layout" +``` + +If grep returns results, fix them before declaring success. + +### Visual QA + +**⚠️ USE SUBAGENTS** — even for 2-3 slides. You've been staring at the code and will see what you expect, not what's there. Subagents have fresh eyes. + +Convert slides to images (see [Converting to Images](#converting-to-images)), then use this prompt: + +``` +Visually inspect these slides. Assume there are issues — find them. + +Look for: +- Overlapping elements (text through shapes, lines through words, stacked elements) +- Text overflow or cut off at edges/box boundaries +- Decorative lines positioned for single-line text but title wrapped to two lines +- Source citations or footers colliding with content above +- Elements too close (< 0.3" gaps) or cards/sections nearly touching +- Uneven gaps (large empty area in one place, cramped in another) +- Insufficient margin from slide edges (< 0.5") +- Columns or similar elements not aligned consistently +- Low-contrast text (e.g., light gray text on cream-colored background) +- Low-contrast icons (e.g., dark icons on dark backgrounds without a contrasting circle) +- Text boxes too narrow causing excessive wrapping +- Leftover placeholder content + +For each slide, list issues or areas of concern, even if minor. + +Read and analyze these images: +1. /path/to/slide-01.jpg (Expected: [brief description]) +2. /path/to/slide-02.jpg (Expected: [brief description]) + +Report ALL issues found, including minor ones. +``` + +### Verification Loop + +1. Generate slides → Convert to images → Inspect +2. **List issues found** (if none found, look again more critically) +3. Fix issues +4. **Re-verify affected slides** — one fix often creates another problem +5. Repeat until a full pass reveals no new issues + +**Do not declare success until you've completed at least one fix-and-verify cycle.** + +--- + +## Converting to Images + +Convert presentations to individual slide images for visual inspection: + +```bash +python scripts/office/soffice.py --headless --convert-to pdf output.pptx +pdftoppm -jpeg -r 150 output.pdf slide +``` + +This creates `slide-01.jpg`, `slide-02.jpg`, etc. + +To re-render specific slides after fixes: + +```bash +pdftoppm -jpeg -r 150 -f N -l N output.pdf slide-fixed +``` + +--- + +## Dependencies + +- `pip install "markitdown[pptx]"` - text extraction +- `pip install Pillow` - thumbnail grids +- `npm install -g pptxgenjs` - creating from scratch +- LibreOffice (`soffice`) - PDF conversion (auto-configured for sandboxed environments via `scripts/office/soffice.py`) +- Poppler (`pdftoppm`) - PDF to images diff --git a/.claude/skills/pptx/editing.md b/.claude/skills/pptx/editing.md new file mode 100644 index 0000000..f873e8a --- /dev/null +++ b/.claude/skills/pptx/editing.md @@ -0,0 +1,205 @@ +# Editing Presentations + +## Template-Based Workflow + +When using an existing presentation as a template: + +1. **Analyze existing slides**: + ```bash + python scripts/thumbnail.py template.pptx + python -m markitdown template.pptx + ``` + Review `thumbnails.jpg` to see layouts, and markitdown output to see placeholder text. + +2. **Plan slide mapping**: For each content section, choose a template slide. + + ⚠️ **USE VARIED LAYOUTS** — monotonous presentations are a common failure mode. Don't default to basic title + bullet slides. Actively seek out: + - Multi-column layouts (2-column, 3-column) + - Image + text combinations + - Full-bleed images with text overlay + - Quote or callout slides + - Section dividers + - Stat/number callouts + - Icon grids or icon + text rows + + **Avoid:** Repeating the same text-heavy layout for every slide. + + Match content type to layout style (e.g., key points → bullet slide, team info → multi-column, testimonials → quote slide). + +3. **Unpack**: `python scripts/office/unpack.py template.pptx unpacked/` + +4. **Build presentation** (do this yourself, not with subagents): + - Delete unwanted slides (remove from ``) + - Duplicate slides you want to reuse (`add_slide.py`) + - Reorder slides in `` + - **Complete all structural changes before step 5** + +5. **Edit content**: Update text in each `slide{N}.xml`. + **Use subagents here if available** — slides are separate XML files, so subagents can edit in parallel. + +6. **Clean**: `python scripts/clean.py unpacked/` + +7. **Pack**: `python scripts/office/pack.py unpacked/ output.pptx --original template.pptx` + +--- + +## Scripts + +| Script | Purpose | +|--------|---------| +| `unpack.py` | Extract and pretty-print PPTX | +| `add_slide.py` | Duplicate slide or create from layout | +| `clean.py` | Remove orphaned files | +| `pack.py` | Repack with validation | +| `thumbnail.py` | Create visual grid of slides | + +### unpack.py + +```bash +python scripts/office/unpack.py input.pptx unpacked/ +``` + +Extracts PPTX, pretty-prints XML, escapes smart quotes. + +### add_slide.py + +```bash +python scripts/add_slide.py unpacked/ slide2.xml # Duplicate slide +python scripts/add_slide.py unpacked/ slideLayout2.xml # From layout +``` + +Prints `` to add to `` at desired position. + +### clean.py + +```bash +python scripts/clean.py unpacked/ +``` + +Removes slides not in ``, unreferenced media, orphaned rels. + +### pack.py + +```bash +python scripts/office/pack.py unpacked/ output.pptx --original input.pptx +``` + +Validates, repairs, condenses XML, re-encodes smart quotes. + +### thumbnail.py + +```bash +python scripts/thumbnail.py input.pptx [output_prefix] [--cols N] +``` + +Creates `thumbnails.jpg` with slide filenames as labels. Default 3 columns, max 12 per grid. + +**Use for template analysis only** (choosing layouts). For visual QA, use `soffice` + `pdftoppm` to create full-resolution individual slide images—see SKILL.md. + +--- + +## Slide Operations + +Slide order is in `ppt/presentation.xml` → ``. + +**Reorder**: Rearrange `` elements. + +**Delete**: Remove ``, then run `clean.py`. + +**Add**: Use `add_slide.py`. Never manually copy slide files—the script handles notes references, Content_Types.xml, and relationship IDs that manual copying misses. + +--- + +## Editing Content + +**Subagents:** If available, use them here (after completing step 4). Each slide is a separate XML file, so subagents can edit in parallel. In your prompt to subagents, include: +- The slide file path(s) to edit +- **"Use the Edit tool for all changes"** +- The formatting rules and common pitfalls below + +For each slide: +1. Read the slide's XML +2. Identify ALL placeholder content—text, images, charts, icons, captions +3. Replace each placeholder with final content + +**Use the Edit tool, not sed or Python scripts.** The Edit tool forces specificity about what to replace and where, yielding better reliability. + +### Formatting Rules + +- **Bold all headers, subheadings, and inline labels**: Use `b="1"` on ``. This includes: + - Slide titles + - Section headers within a slide + - Inline labels like (e.g.: "Status:", "Description:") at the start of a line +- **Never use unicode bullets (•)**: Use proper list formatting with `` or `` +- **Bullet consistency**: Let bullets inherit from the layout. Only specify `` or ``. + +--- + +## Common Pitfalls + +### Template Adaptation + +When source content has fewer items than the template: +- **Remove excess elements entirely** (images, shapes, text boxes), don't just clear text +- Check for orphaned visuals after clearing text content +- Run visual QA to catch mismatched counts + +When replacing text with different length content: +- **Shorter replacements**: Usually safe +- **Longer replacements**: May overflow or wrap unexpectedly +- Test with visual QA after text changes +- Consider truncating or splitting content to fit the template's design constraints + +**Template slots ≠ Source items**: If template has 4 team members but source has 3 users, delete the 4th member's entire group (image + text boxes), not just the text. + +### Multi-Item Content + +If source has multiple items (numbered lists, multiple sections), create separate `` elements for each — **never concatenate into one string**. + +**❌ WRONG** — all items in one paragraph: +```xml + + Step 1: Do the first thing. Step 2: Do the second thing. + +``` + +**✅ CORRECT** — separate paragraphs with bold headers: +```xml + + + Step 1 + + + + Do the first thing. + + + + Step 2 + + +``` + +Copy `` from the original paragraph to preserve line spacing. Use `b="1"` on headers. + +### Smart Quotes + +Handled automatically by unpack/pack. But the Edit tool converts smart quotes to ASCII. + +**When adding new text with quotes, use XML entities:** + +```xml +the “Agreement” +``` + +| Character | Name | Unicode | XML Entity | +|-----------|------|---------|------------| +| `“` | Left double quote | U+201C | `“` | +| `”` | Right double quote | U+201D | `”` | +| `‘` | Left single quote | U+2018 | `‘` | +| `’` | Right single quote | U+2019 | `’` | + +### Other + +- **Whitespace**: Use `xml:space="preserve"` on `` with leading/trailing spaces +- **XML parsing**: Use `defusedxml.minidom`, not `xml.etree.ElementTree` (corrupts namespaces) diff --git a/.claude/skills/pptx/pptxgenjs.md b/.claude/skills/pptx/pptxgenjs.md new file mode 100644 index 0000000..6bfed90 --- /dev/null +++ b/.claude/skills/pptx/pptxgenjs.md @@ -0,0 +1,420 @@ +# PptxGenJS Tutorial + +## Setup & Basic Structure + +```javascript +const pptxgen = require("pptxgenjs"); + +let pres = new pptxgen(); +pres.layout = 'LAYOUT_16x9'; // or 'LAYOUT_16x10', 'LAYOUT_4x3', 'LAYOUT_WIDE' +pres.author = 'Your Name'; +pres.title = 'Presentation Title'; + +let slide = pres.addSlide(); +slide.addText("Hello World!", { x: 0.5, y: 0.5, fontSize: 36, color: "363636" }); + +pres.writeFile({ fileName: "Presentation.pptx" }); +``` + +## Layout Dimensions + +Slide dimensions (coordinates in inches): +- `LAYOUT_16x9`: 10" × 5.625" (default) +- `LAYOUT_16x10`: 10" × 6.25" +- `LAYOUT_4x3`: 10" × 7.5" +- `LAYOUT_WIDE`: 13.3" × 7.5" + +--- + +## Text & Formatting + +```javascript +// Basic text +slide.addText("Simple Text", { + x: 1, y: 1, w: 8, h: 2, fontSize: 24, fontFace: "Arial", + color: "363636", bold: true, align: "center", valign: "middle" +}); + +// Character spacing (use charSpacing, not letterSpacing which is silently ignored) +slide.addText("SPACED TEXT", { x: 1, y: 1, w: 8, h: 1, charSpacing: 6 }); + +// Rich text arrays +slide.addText([ + { text: "Bold ", options: { bold: true } }, + { text: "Italic ", options: { italic: true } } +], { x: 1, y: 3, w: 8, h: 1 }); + +// Multi-line text (requires breakLine: true) +slide.addText([ + { text: "Line 1", options: { breakLine: true } }, + { text: "Line 2", options: { breakLine: true } }, + { text: "Line 3" } // Last item doesn't need breakLine +], { x: 0.5, y: 0.5, w: 8, h: 2 }); + +// Text box margin (internal padding) +slide.addText("Title", { + x: 0.5, y: 0.3, w: 9, h: 0.6, + margin: 0 // Use 0 when aligning text with other elements like shapes or icons +}); +``` + +**Tip:** Text boxes have internal margin by default. Set `margin: 0` when you need text to align precisely with shapes, lines, or icons at the same x-position. + +--- + +## Lists & Bullets + +```javascript +// ✅ CORRECT: Multiple bullets +slide.addText([ + { text: "First item", options: { bullet: true, breakLine: true } }, + { text: "Second item", options: { bullet: true, breakLine: true } }, + { text: "Third item", options: { bullet: true } } +], { x: 0.5, y: 0.5, w: 8, h: 3 }); + +// ❌ WRONG: Never use unicode bullets +slide.addText("• First item", { ... }); // Creates double bullets + +// Sub-items and numbered lists +{ text: "Sub-item", options: { bullet: true, indentLevel: 1 } } +{ text: "First", options: { bullet: { type: "number" }, breakLine: true } } +``` + +--- + +## Shapes + +```javascript +slide.addShape(pres.shapes.RECTANGLE, { + x: 0.5, y: 0.8, w: 1.5, h: 3.0, + fill: { color: "FF0000" }, line: { color: "000000", width: 2 } +}); + +slide.addShape(pres.shapes.OVAL, { x: 4, y: 1, w: 2, h: 2, fill: { color: "0000FF" } }); + +slide.addShape(pres.shapes.LINE, { + x: 1, y: 3, w: 5, h: 0, line: { color: "FF0000", width: 3, dashType: "dash" } +}); + +// With transparency +slide.addShape(pres.shapes.RECTANGLE, { + x: 1, y: 1, w: 3, h: 2, + fill: { color: "0088CC", transparency: 50 } +}); + +// Rounded rectangle (rectRadius only works with ROUNDED_RECTANGLE, not RECTANGLE) +// ⚠️ Don't pair with rectangular accent overlays — they won't cover rounded corners. Use RECTANGLE instead. +slide.addShape(pres.shapes.ROUNDED_RECTANGLE, { + x: 1, y: 1, w: 3, h: 2, + fill: { color: "FFFFFF" }, rectRadius: 0.1 +}); + +// With shadow +slide.addShape(pres.shapes.RECTANGLE, { + x: 1, y: 1, w: 3, h: 2, + fill: { color: "FFFFFF" }, + shadow: { type: "outer", color: "000000", blur: 6, offset: 2, angle: 135, opacity: 0.15 } +}); +``` + +Shadow options: + +| Property | Type | Range | Notes | +|----------|------|-------|-------| +| `type` | string | `"outer"`, `"inner"` | | +| `color` | string | 6-char hex (e.g. `"000000"`) | No `#` prefix, no 8-char hex — see Common Pitfalls | +| `blur` | number | 0-100 pt | | +| `offset` | number | 0-200 pt | **Must be non-negative** — negative values corrupt the file | +| `angle` | number | 0-359 degrees | Direction the shadow falls (135 = bottom-right, 270 = upward) | +| `opacity` | number | 0.0-1.0 | Use this for transparency, never encode in color string | + +To cast a shadow upward (e.g. on a footer bar), use `angle: 270` with a positive offset — do **not** use a negative offset. + +**Note**: Gradient fills are not natively supported. Use a gradient image as a background instead. + +--- + +## Images + +### Image Sources + +```javascript +// From file path +slide.addImage({ path: "images/chart.png", x: 1, y: 1, w: 5, h: 3 }); + +// From URL +slide.addImage({ path: "https://example.com/image.jpg", x: 1, y: 1, w: 5, h: 3 }); + +// From base64 (faster, no file I/O) +slide.addImage({ data: "image/png;base64,iVBORw0KGgo...", x: 1, y: 1, w: 5, h: 3 }); +``` + +### Image Options + +```javascript +slide.addImage({ + path: "image.png", + x: 1, y: 1, w: 5, h: 3, + rotate: 45, // 0-359 degrees + rounding: true, // Circular crop + transparency: 50, // 0-100 + flipH: true, // Horizontal flip + flipV: false, // Vertical flip + altText: "Description", // Accessibility + hyperlink: { url: "https://example.com" } +}); +``` + +### Image Sizing Modes + +```javascript +// Contain - fit inside, preserve ratio +{ sizing: { type: 'contain', w: 4, h: 3 } } + +// Cover - fill area, preserve ratio (may crop) +{ sizing: { type: 'cover', w: 4, h: 3 } } + +// Crop - cut specific portion +{ sizing: { type: 'crop', x: 0.5, y: 0.5, w: 2, h: 2 } } +``` + +### Calculate Dimensions (preserve aspect ratio) + +```javascript +const origWidth = 1978, origHeight = 923, maxHeight = 3.0; +const calcWidth = maxHeight * (origWidth / origHeight); +const centerX = (10 - calcWidth) / 2; + +slide.addImage({ path: "image.png", x: centerX, y: 1.2, w: calcWidth, h: maxHeight }); +``` + +### Supported Formats + +- **Standard**: PNG, JPG, GIF (animated GIFs work in Microsoft 365) +- **SVG**: Works in modern PowerPoint/Microsoft 365 + +--- + +## Icons + +Use react-icons to generate SVG icons, then rasterize to PNG for universal compatibility. + +### Setup + +```javascript +const React = require("react"); +const ReactDOMServer = require("react-dom/server"); +const sharp = require("sharp"); +const { FaCheckCircle, FaChartLine } = require("react-icons/fa"); + +function renderIconSvg(IconComponent, color = "#000000", size = 256) { + return ReactDOMServer.renderToStaticMarkup( + React.createElement(IconComponent, { color, size: String(size) }) + ); +} + +async function iconToBase64Png(IconComponent, color, size = 256) { + const svg = renderIconSvg(IconComponent, color, size); + const pngBuffer = await sharp(Buffer.from(svg)).png().toBuffer(); + return "image/png;base64," + pngBuffer.toString("base64"); +} +``` + +### Add Icon to Slide + +```javascript +const iconData = await iconToBase64Png(FaCheckCircle, "#4472C4", 256); + +slide.addImage({ + data: iconData, + x: 1, y: 1, w: 0.5, h: 0.5 // Size in inches +}); +``` + +**Note**: Use size 256 or higher for crisp icons. The size parameter controls the rasterization resolution, not the display size on the slide (which is set by `w` and `h` in inches). + +### Icon Libraries + +Install: `npm install -g react-icons react react-dom sharp` + +Popular icon sets in react-icons: +- `react-icons/fa` - Font Awesome +- `react-icons/md` - Material Design +- `react-icons/hi` - Heroicons +- `react-icons/bi` - Bootstrap Icons + +--- + +## Slide Backgrounds + +```javascript +// Solid color +slide.background = { color: "F1F1F1" }; + +// Color with transparency +slide.background = { color: "FF3399", transparency: 50 }; + +// Image from URL +slide.background = { path: "https://example.com/bg.jpg" }; + +// Image from base64 +slide.background = { data: "image/png;base64,iVBORw0KGgo..." }; +``` + +--- + +## Tables + +```javascript +slide.addTable([ + ["Header 1", "Header 2"], + ["Cell 1", "Cell 2"] +], { + x: 1, y: 1, w: 8, h: 2, + border: { pt: 1, color: "999999" }, fill: { color: "F1F1F1" } +}); + +// Advanced with merged cells +let tableData = [ + [{ text: "Header", options: { fill: { color: "6699CC" }, color: "FFFFFF", bold: true } }, "Cell"], + [{ text: "Merged", options: { colspan: 2 } }] +]; +slide.addTable(tableData, { x: 1, y: 3.5, w: 8, colW: [4, 4] }); +``` + +--- + +## Charts + +```javascript +// Bar chart +slide.addChart(pres.charts.BAR, [{ + name: "Sales", labels: ["Q1", "Q2", "Q3", "Q4"], values: [4500, 5500, 6200, 7100] +}], { + x: 0.5, y: 0.6, w: 6, h: 3, barDir: 'col', + showTitle: true, title: 'Quarterly Sales' +}); + +// Line chart +slide.addChart(pres.charts.LINE, [{ + name: "Temp", labels: ["Jan", "Feb", "Mar"], values: [32, 35, 42] +}], { x: 0.5, y: 4, w: 6, h: 3, lineSize: 3, lineSmooth: true }); + +// Pie chart +slide.addChart(pres.charts.PIE, [{ + name: "Share", labels: ["A", "B", "Other"], values: [35, 45, 20] +}], { x: 7, y: 1, w: 5, h: 4, showPercent: true }); +``` + +### Better-Looking Charts + +Default charts look dated. Apply these options for a modern, clean appearance: + +```javascript +slide.addChart(pres.charts.BAR, chartData, { + x: 0.5, y: 1, w: 9, h: 4, barDir: "col", + + // Custom colors (match your presentation palette) + chartColors: ["0D9488", "14B8A6", "5EEAD4"], + + // Clean background + chartArea: { fill: { color: "FFFFFF" }, roundedCorners: true }, + + // Muted axis labels + catAxisLabelColor: "64748B", + valAxisLabelColor: "64748B", + + // Subtle grid (value axis only) + valGridLine: { color: "E2E8F0", size: 0.5 }, + catGridLine: { style: "none" }, + + // Data labels on bars + showValue: true, + dataLabelPosition: "outEnd", + dataLabelColor: "1E293B", + + // Hide legend for single series + showLegend: false, +}); +``` + +**Key styling options:** +- `chartColors: [...]` - hex colors for series/segments +- `chartArea: { fill, border, roundedCorners }` - chart background +- `catGridLine/valGridLine: { color, style, size }` - grid lines (`style: "none"` to hide) +- `lineSmooth: true` - curved lines (line charts) +- `legendPos: "r"` - legend position: "b", "t", "l", "r", "tr" + +--- + +## Slide Masters + +```javascript +pres.defineSlideMaster({ + title: 'TITLE_SLIDE', background: { color: '283A5E' }, + objects: [{ + placeholder: { options: { name: 'title', type: 'title', x: 1, y: 2, w: 8, h: 2 } } + }] +}); + +let titleSlide = pres.addSlide({ masterName: "TITLE_SLIDE" }); +titleSlide.addText("My Title", { placeholder: "title" }); +``` + +--- + +## Common Pitfalls + +⚠️ These issues cause file corruption, visual bugs, or broken output. Avoid them. + +1. **NEVER use "#" with hex colors** - causes file corruption + ```javascript + color: "FF0000" // ✅ CORRECT + color: "#FF0000" // ❌ WRONG + ``` + +2. **NEVER encode opacity in hex color strings** - 8-char colors (e.g., `"00000020"`) corrupt the file. Use the `opacity` property instead. + ```javascript + shadow: { type: "outer", blur: 6, offset: 2, color: "00000020" } // ❌ CORRUPTS FILE + shadow: { type: "outer", blur: 6, offset: 2, color: "000000", opacity: 0.12 } // ✅ CORRECT + ``` + +3. **Use `bullet: true`** - NEVER unicode symbols like "•" (creates double bullets) + +4. **Use `breakLine: true`** between array items or text runs together + +5. **Avoid `lineSpacing` with bullets** - causes excessive gaps; use `paraSpaceAfter` instead + +6. **Each presentation needs fresh instance** - don't reuse `pptxgen()` objects + +7. **NEVER reuse option objects across calls** - PptxGenJS mutates objects in-place (e.g. converting shadow values to EMU). Sharing one object between multiple calls corrupts the second shape. + ```javascript + const shadow = { type: "outer", blur: 6, offset: 2, color: "000000", opacity: 0.15 }; + slide.addShape(pres.shapes.RECTANGLE, { shadow, ... }); // ❌ second call gets already-converted values + slide.addShape(pres.shapes.RECTANGLE, { shadow, ... }); + + const makeShadow = () => ({ type: "outer", blur: 6, offset: 2, color: "000000", opacity: 0.15 }); + slide.addShape(pres.shapes.RECTANGLE, { shadow: makeShadow(), ... }); // ✅ fresh object each time + slide.addShape(pres.shapes.RECTANGLE, { shadow: makeShadow(), ... }); + ``` + +8. **Don't use `ROUNDED_RECTANGLE` with accent borders** - rectangular overlay bars won't cover rounded corners. Use `RECTANGLE` instead. + ```javascript + // ❌ WRONG: Accent bar doesn't cover rounded corners + slide.addShape(pres.shapes.ROUNDED_RECTANGLE, { x: 1, y: 1, w: 3, h: 1.5, fill: { color: "FFFFFF" } }); + slide.addShape(pres.shapes.RECTANGLE, { x: 1, y: 1, w: 0.08, h: 1.5, fill: { color: "0891B2" } }); + + // ✅ CORRECT: Use RECTANGLE for clean alignment + slide.addShape(pres.shapes.RECTANGLE, { x: 1, y: 1, w: 3, h: 1.5, fill: { color: "FFFFFF" } }); + slide.addShape(pres.shapes.RECTANGLE, { x: 1, y: 1, w: 0.08, h: 1.5, fill: { color: "0891B2" } }); + ``` + +--- + +## Quick Reference + +- **Shapes**: RECTANGLE, OVAL, LINE, ROUNDED_RECTANGLE +- **Charts**: BAR, LINE, PIE, DOUGHNUT, SCATTER, BUBBLE, RADAR +- **Layouts**: LAYOUT_16x9 (10"×5.625"), LAYOUT_16x10, LAYOUT_4x3, LAYOUT_WIDE +- **Alignment**: "left", "center", "right" +- **Chart data labels**: "outEnd", "inEnd", "center" diff --git a/.claude/skills/pptx/scripts/__init__.py b/.claude/skills/pptx/scripts/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/.claude/skills/pptx/scripts/add_slide.py b/.claude/skills/pptx/scripts/add_slide.py new file mode 100644 index 0000000..13700df --- /dev/null +++ b/.claude/skills/pptx/scripts/add_slide.py @@ -0,0 +1,195 @@ +"""Add a new slide to an unpacked PPTX directory. + +Usage: python add_slide.py + +The source can be: + - A slide file (e.g., slide2.xml) - duplicates the slide + - A layout file (e.g., slideLayout2.xml) - creates from layout + +Examples: + python add_slide.py unpacked/ slide2.xml + # Duplicates slide2, creates slide5.xml + + python add_slide.py unpacked/ slideLayout2.xml + # Creates slide5.xml from slideLayout2.xml + +To see available layouts: ls unpacked/ppt/slideLayouts/ + +Prints the element to add to presentation.xml. +""" + +import re +import shutil +import sys +from pathlib import Path + + +def get_next_slide_number(slides_dir: Path) -> int: + existing = [int(m.group(1)) for f in slides_dir.glob("slide*.xml") + if (m := re.match(r"slide(\d+)\.xml", f.name))] + return max(existing) + 1 if existing else 1 + + +def create_slide_from_layout(unpacked_dir: Path, layout_file: str) -> None: + slides_dir = unpacked_dir / "ppt" / "slides" + rels_dir = slides_dir / "_rels" + layouts_dir = unpacked_dir / "ppt" / "slideLayouts" + + layout_path = layouts_dir / layout_file + if not layout_path.exists(): + print(f"Error: {layout_path} not found", file=sys.stderr) + sys.exit(1) + + next_num = get_next_slide_number(slides_dir) + dest = f"slide{next_num}.xml" + dest_slide = slides_dir / dest + dest_rels = rels_dir / f"{dest}.rels" + + slide_xml = ''' + + + + + + + + + + + + + + + + + + + + + +''' + dest_slide.write_text(slide_xml, encoding="utf-8") + + rels_dir.mkdir(exist_ok=True) + rels_xml = f''' + + +''' + dest_rels.write_text(rels_xml, encoding="utf-8") + + _add_to_content_types(unpacked_dir, dest) + + rid = _add_to_presentation_rels(unpacked_dir, dest) + + next_slide_id = _get_next_slide_id(unpacked_dir) + + print(f"Created {dest} from {layout_file}") + print(f'Add to presentation.xml : ') + + +def duplicate_slide(unpacked_dir: Path, source: str) -> None: + slides_dir = unpacked_dir / "ppt" / "slides" + rels_dir = slides_dir / "_rels" + + source_slide = slides_dir / source + + if not source_slide.exists(): + print(f"Error: {source_slide} not found", file=sys.stderr) + sys.exit(1) + + next_num = get_next_slide_number(slides_dir) + dest = f"slide{next_num}.xml" + dest_slide = slides_dir / dest + + source_rels = rels_dir / f"{source}.rels" + dest_rels = rels_dir / f"{dest}.rels" + + shutil.copy2(source_slide, dest_slide) + + if source_rels.exists(): + shutil.copy2(source_rels, dest_rels) + + rels_content = dest_rels.read_text(encoding="utf-8") + rels_content = re.sub( + r'\s*]*Type="[^"]*notesSlide"[^>]*/>\s*', + "\n", + rels_content, + ) + dest_rels.write_text(rels_content, encoding="utf-8") + + _add_to_content_types(unpacked_dir, dest) + + rid = _add_to_presentation_rels(unpacked_dir, dest) + + next_slide_id = _get_next_slide_id(unpacked_dir) + + print(f"Created {dest} from {source}") + print(f'Add to presentation.xml : ') + + +def _add_to_content_types(unpacked_dir: Path, dest: str) -> None: + content_types_path = unpacked_dir / "[Content_Types].xml" + content_types = content_types_path.read_text(encoding="utf-8") + + new_override = f'' + + if f"/ppt/slides/{dest}" not in content_types: + content_types = content_types.replace("", f" {new_override}\n") + content_types_path.write_text(content_types, encoding="utf-8") + + +def _add_to_presentation_rels(unpacked_dir: Path, dest: str) -> str: + pres_rels_path = unpacked_dir / "ppt" / "_rels" / "presentation.xml.rels" + pres_rels = pres_rels_path.read_text(encoding="utf-8") + + rids = [int(m) for m in re.findall(r'Id="rId(\d+)"', pres_rels)] + next_rid = max(rids) + 1 if rids else 1 + rid = f"rId{next_rid}" + + new_rel = f'' + + if f"slides/{dest}" not in pres_rels: + pres_rels = pres_rels.replace("", f" {new_rel}\n") + pres_rels_path.write_text(pres_rels, encoding="utf-8") + + return rid + + +def _get_next_slide_id(unpacked_dir: Path) -> int: + pres_path = unpacked_dir / "ppt" / "presentation.xml" + pres_content = pres_path.read_text(encoding="utf-8") + slide_ids = [int(m) for m in re.findall(r']*id="(\d+)"', pres_content)] + return max(slide_ids) + 1 if slide_ids else 256 + + +def parse_source(source: str) -> tuple[str, str | None]: + if source.startswith("slideLayout") and source.endswith(".xml"): + return ("layout", source) + + return ("slide", None) + + +if __name__ == "__main__": + if len(sys.argv) != 3: + print("Usage: python add_slide.py ", file=sys.stderr) + print("", file=sys.stderr) + print("Source can be:", file=sys.stderr) + print(" slide2.xml - duplicate an existing slide", file=sys.stderr) + print(" slideLayout2.xml - create from a layout template", file=sys.stderr) + print("", file=sys.stderr) + print("To see available layouts: ls /ppt/slideLayouts/", file=sys.stderr) + sys.exit(1) + + unpacked_dir = Path(sys.argv[1]) + source = sys.argv[2] + + if not unpacked_dir.exists(): + print(f"Error: {unpacked_dir} not found", file=sys.stderr) + sys.exit(1) + + source_type, layout_file = parse_source(source) + + if source_type == "layout" and layout_file is not None: + create_slide_from_layout(unpacked_dir, layout_file) + else: + duplicate_slide(unpacked_dir, source) diff --git a/.claude/skills/pptx/scripts/clean.py b/.claude/skills/pptx/scripts/clean.py new file mode 100755 index 0000000..3d13994 --- /dev/null +++ b/.claude/skills/pptx/scripts/clean.py @@ -0,0 +1,286 @@ +"""Remove unreferenced files from an unpacked PPTX directory. + +Usage: python clean.py + +Example: + python clean.py unpacked/ + +This script removes: +- Orphaned slides (not in sldIdLst) and their relationships +- [trash] directory (unreferenced files) +- Orphaned .rels files for deleted resources +- Unreferenced media, embeddings, charts, diagrams, drawings, ink files +- Unreferenced theme files +- Unreferenced notes slides +- Content-Type overrides for deleted files +""" + +import sys +from pathlib import Path + +import defusedxml.minidom + + +import re + + +def get_slides_in_sldidlst(unpacked_dir: Path) -> set[str]: + pres_path = unpacked_dir / "ppt" / "presentation.xml" + pres_rels_path = unpacked_dir / "ppt" / "_rels" / "presentation.xml.rels" + + if not pres_path.exists() or not pres_rels_path.exists(): + return set() + + rels_dom = defusedxml.minidom.parse(str(pres_rels_path)) + rid_to_slide = {} + for rel in rels_dom.getElementsByTagName("Relationship"): + rid = rel.getAttribute("Id") + target = rel.getAttribute("Target") + rel_type = rel.getAttribute("Type") + if "slide" in rel_type and target.startswith("slides/"): + rid_to_slide[rid] = target.replace("slides/", "") + + pres_content = pres_path.read_text(encoding="utf-8") + referenced_rids = set(re.findall(r']*r:id="([^"]+)"', pres_content)) + + return {rid_to_slide[rid] for rid in referenced_rids if rid in rid_to_slide} + + +def remove_orphaned_slides(unpacked_dir: Path) -> list[str]: + slides_dir = unpacked_dir / "ppt" / "slides" + slides_rels_dir = slides_dir / "_rels" + pres_rels_path = unpacked_dir / "ppt" / "_rels" / "presentation.xml.rels" + + if not slides_dir.exists(): + return [] + + referenced_slides = get_slides_in_sldidlst(unpacked_dir) + removed = [] + + for slide_file in slides_dir.glob("slide*.xml"): + if slide_file.name not in referenced_slides: + rel_path = slide_file.relative_to(unpacked_dir) + slide_file.unlink() + removed.append(str(rel_path)) + + rels_file = slides_rels_dir / f"{slide_file.name}.rels" + if rels_file.exists(): + rels_file.unlink() + removed.append(str(rels_file.relative_to(unpacked_dir))) + + if removed and pres_rels_path.exists(): + rels_dom = defusedxml.minidom.parse(str(pres_rels_path)) + changed = False + + for rel in list(rels_dom.getElementsByTagName("Relationship")): + target = rel.getAttribute("Target") + if target.startswith("slides/"): + slide_name = target.replace("slides/", "") + if slide_name not in referenced_slides: + if rel.parentNode: + rel.parentNode.removeChild(rel) + changed = True + + if changed: + with open(pres_rels_path, "wb") as f: + f.write(rels_dom.toxml(encoding="utf-8")) + + return removed + + +def remove_trash_directory(unpacked_dir: Path) -> list[str]: + trash_dir = unpacked_dir / "[trash]" + removed = [] + + if trash_dir.exists() and trash_dir.is_dir(): + for file_path in trash_dir.iterdir(): + if file_path.is_file(): + rel_path = file_path.relative_to(unpacked_dir) + removed.append(str(rel_path)) + file_path.unlink() + trash_dir.rmdir() + + return removed + + +def get_slide_referenced_files(unpacked_dir: Path) -> set: + referenced = set() + slides_rels_dir = unpacked_dir / "ppt" / "slides" / "_rels" + + if not slides_rels_dir.exists(): + return referenced + + for rels_file in slides_rels_dir.glob("*.rels"): + dom = defusedxml.minidom.parse(str(rels_file)) + for rel in dom.getElementsByTagName("Relationship"): + target = rel.getAttribute("Target") + if not target: + continue + target_path = (rels_file.parent.parent / target).resolve() + try: + referenced.add(target_path.relative_to(unpacked_dir.resolve())) + except ValueError: + pass + + return referenced + + +def remove_orphaned_rels_files(unpacked_dir: Path) -> list[str]: + resource_dirs = ["charts", "diagrams", "drawings"] + removed = [] + slide_referenced = get_slide_referenced_files(unpacked_dir) + + for dir_name in resource_dirs: + rels_dir = unpacked_dir / "ppt" / dir_name / "_rels" + if not rels_dir.exists(): + continue + + for rels_file in rels_dir.glob("*.rels"): + resource_file = rels_dir.parent / rels_file.name.replace(".rels", "") + try: + resource_rel_path = resource_file.resolve().relative_to(unpacked_dir.resolve()) + except ValueError: + continue + + if not resource_file.exists() or resource_rel_path not in slide_referenced: + rels_file.unlink() + rel_path = rels_file.relative_to(unpacked_dir) + removed.append(str(rel_path)) + + return removed + + +def get_referenced_files(unpacked_dir: Path) -> set: + referenced = set() + + for rels_file in unpacked_dir.rglob("*.rels"): + dom = defusedxml.minidom.parse(str(rels_file)) + for rel in dom.getElementsByTagName("Relationship"): + target = rel.getAttribute("Target") + if not target: + continue + target_path = (rels_file.parent.parent / target).resolve() + try: + referenced.add(target_path.relative_to(unpacked_dir.resolve())) + except ValueError: + pass + + return referenced + + +def remove_orphaned_files(unpacked_dir: Path, referenced: set) -> list[str]: + resource_dirs = ["media", "embeddings", "charts", "diagrams", "tags", "drawings", "ink"] + removed = [] + + for dir_name in resource_dirs: + dir_path = unpacked_dir / "ppt" / dir_name + if not dir_path.exists(): + continue + + for file_path in dir_path.glob("*"): + if not file_path.is_file(): + continue + rel_path = file_path.relative_to(unpacked_dir) + if rel_path not in referenced: + file_path.unlink() + removed.append(str(rel_path)) + + theme_dir = unpacked_dir / "ppt" / "theme" + if theme_dir.exists(): + for file_path in theme_dir.glob("theme*.xml"): + rel_path = file_path.relative_to(unpacked_dir) + if rel_path not in referenced: + file_path.unlink() + removed.append(str(rel_path)) + theme_rels = theme_dir / "_rels" / f"{file_path.name}.rels" + if theme_rels.exists(): + theme_rels.unlink() + removed.append(str(theme_rels.relative_to(unpacked_dir))) + + notes_dir = unpacked_dir / "ppt" / "notesSlides" + if notes_dir.exists(): + for file_path in notes_dir.glob("*.xml"): + if not file_path.is_file(): + continue + rel_path = file_path.relative_to(unpacked_dir) + if rel_path not in referenced: + file_path.unlink() + removed.append(str(rel_path)) + + notes_rels_dir = notes_dir / "_rels" + if notes_rels_dir.exists(): + for file_path in notes_rels_dir.glob("*.rels"): + notes_file = notes_dir / file_path.name.replace(".rels", "") + if not notes_file.exists(): + file_path.unlink() + removed.append(str(file_path.relative_to(unpacked_dir))) + + return removed + + +def update_content_types(unpacked_dir: Path, removed_files: list[str]) -> None: + ct_path = unpacked_dir / "[Content_Types].xml" + if not ct_path.exists(): + return + + dom = defusedxml.minidom.parse(str(ct_path)) + changed = False + + for override in list(dom.getElementsByTagName("Override")): + part_name = override.getAttribute("PartName").lstrip("/") + if part_name in removed_files: + if override.parentNode: + override.parentNode.removeChild(override) + changed = True + + if changed: + with open(ct_path, "wb") as f: + f.write(dom.toxml(encoding="utf-8")) + + +def clean_unused_files(unpacked_dir: Path) -> list[str]: + all_removed = [] + + slides_removed = remove_orphaned_slides(unpacked_dir) + all_removed.extend(slides_removed) + + trash_removed = remove_trash_directory(unpacked_dir) + all_removed.extend(trash_removed) + + while True: + removed_rels = remove_orphaned_rels_files(unpacked_dir) + referenced = get_referenced_files(unpacked_dir) + removed_files = remove_orphaned_files(unpacked_dir, referenced) + + total_removed = removed_rels + removed_files + if not total_removed: + break + + all_removed.extend(total_removed) + + if all_removed: + update_content_types(unpacked_dir, all_removed) + + return all_removed + + +if __name__ == "__main__": + if len(sys.argv) != 2: + print("Usage: python clean.py ", file=sys.stderr) + print("Example: python clean.py unpacked/", file=sys.stderr) + sys.exit(1) + + unpacked_dir = Path(sys.argv[1]) + + if not unpacked_dir.exists(): + print(f"Error: {unpacked_dir} not found", file=sys.stderr) + sys.exit(1) + + removed = clean_unused_files(unpacked_dir) + + if removed: + print(f"Removed {len(removed)} unreferenced files:") + for f in removed: + print(f" {f}") + else: + print("No unreferenced files found") diff --git a/.claude/skills/pptx/scripts/office/helpers/__init__.py b/.claude/skills/pptx/scripts/office/helpers/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/.claude/skills/pptx/scripts/office/helpers/merge_runs.py b/.claude/skills/pptx/scripts/office/helpers/merge_runs.py new file mode 100644 index 0000000..ad7c25e --- /dev/null +++ b/.claude/skills/pptx/scripts/office/helpers/merge_runs.py @@ -0,0 +1,199 @@ +"""Merge adjacent runs with identical formatting in DOCX. + +Merges adjacent elements that have identical properties. +Works on runs in paragraphs and inside tracked changes (, ). + +Also: +- Removes rsid attributes from runs (revision metadata that doesn't affect rendering) +- Removes proofErr elements (spell/grammar markers that block merging) +""" + +from pathlib import Path + +import defusedxml.minidom + + +def merge_runs(input_dir: str) -> tuple[int, str]: + doc_xml = Path(input_dir) / "word" / "document.xml" + + if not doc_xml.exists(): + return 0, f"Error: {doc_xml} not found" + + try: + dom = defusedxml.minidom.parseString(doc_xml.read_text(encoding="utf-8")) + root = dom.documentElement + + _remove_elements(root, "proofErr") + _strip_run_rsid_attrs(root) + + containers = {run.parentNode for run in _find_elements(root, "r")} + + merge_count = 0 + for container in containers: + merge_count += _merge_runs_in(container) + + doc_xml.write_bytes(dom.toxml(encoding="UTF-8")) + return merge_count, f"Merged {merge_count} runs" + + except Exception as e: + return 0, f"Error: {e}" + + + + +def _find_elements(root, tag: str) -> list: + results = [] + + def traverse(node): + if node.nodeType == node.ELEMENT_NODE: + name = node.localName or node.tagName + if name == tag or name.endswith(f":{tag}"): + results.append(node) + for child in node.childNodes: + traverse(child) + + traverse(root) + return results + + +def _get_child(parent, tag: str): + for child in parent.childNodes: + if child.nodeType == child.ELEMENT_NODE: + name = child.localName or child.tagName + if name == tag or name.endswith(f":{tag}"): + return child + return None + + +def _get_children(parent, tag: str) -> list: + results = [] + for child in parent.childNodes: + if child.nodeType == child.ELEMENT_NODE: + name = child.localName or child.tagName + if name == tag or name.endswith(f":{tag}"): + results.append(child) + return results + + +def _is_adjacent(elem1, elem2) -> bool: + node = elem1.nextSibling + while node: + if node == elem2: + return True + if node.nodeType == node.ELEMENT_NODE: + return False + if node.nodeType == node.TEXT_NODE and node.data.strip(): + return False + node = node.nextSibling + return False + + + + +def _remove_elements(root, tag: str): + for elem in _find_elements(root, tag): + if elem.parentNode: + elem.parentNode.removeChild(elem) + + +def _strip_run_rsid_attrs(root): + for run in _find_elements(root, "r"): + for attr in list(run.attributes.values()): + if "rsid" in attr.name.lower(): + run.removeAttribute(attr.name) + + + + +def _merge_runs_in(container) -> int: + merge_count = 0 + run = _first_child_run(container) + + while run: + while True: + next_elem = _next_element_sibling(run) + if next_elem and _is_run(next_elem) and _can_merge(run, next_elem): + _merge_run_content(run, next_elem) + container.removeChild(next_elem) + merge_count += 1 + else: + break + + _consolidate_text(run) + run = _next_sibling_run(run) + + return merge_count + + +def _first_child_run(container): + for child in container.childNodes: + if child.nodeType == child.ELEMENT_NODE and _is_run(child): + return child + return None + + +def _next_element_sibling(node): + sibling = node.nextSibling + while sibling: + if sibling.nodeType == sibling.ELEMENT_NODE: + return sibling + sibling = sibling.nextSibling + return None + + +def _next_sibling_run(node): + sibling = node.nextSibling + while sibling: + if sibling.nodeType == sibling.ELEMENT_NODE: + if _is_run(sibling): + return sibling + sibling = sibling.nextSibling + return None + + +def _is_run(node) -> bool: + name = node.localName or node.tagName + return name == "r" or name.endswith(":r") + + +def _can_merge(run1, run2) -> bool: + rpr1 = _get_child(run1, "rPr") + rpr2 = _get_child(run2, "rPr") + + if (rpr1 is None) != (rpr2 is None): + return False + if rpr1 is None: + return True + return rpr1.toxml() == rpr2.toxml() + + +def _merge_run_content(target, source): + for child in list(source.childNodes): + if child.nodeType == child.ELEMENT_NODE: + name = child.localName or child.tagName + if name != "rPr" and not name.endswith(":rPr"): + target.appendChild(child) + + +def _consolidate_text(run): + t_elements = _get_children(run, "t") + + for i in range(len(t_elements) - 1, 0, -1): + curr, prev = t_elements[i], t_elements[i - 1] + + if _is_adjacent(prev, curr): + prev_text = prev.firstChild.data if prev.firstChild else "" + curr_text = curr.firstChild.data if curr.firstChild else "" + merged = prev_text + curr_text + + if prev.firstChild: + prev.firstChild.data = merged + else: + prev.appendChild(run.ownerDocument.createTextNode(merged)) + + if merged.startswith(" ") or merged.endswith(" "): + prev.setAttribute("xml:space", "preserve") + elif prev.hasAttribute("xml:space"): + prev.removeAttribute("xml:space") + + run.removeChild(curr) diff --git a/.claude/skills/pptx/scripts/office/helpers/simplify_redlines.py b/.claude/skills/pptx/scripts/office/helpers/simplify_redlines.py new file mode 100644 index 0000000..db963bb --- /dev/null +++ b/.claude/skills/pptx/scripts/office/helpers/simplify_redlines.py @@ -0,0 +1,197 @@ +"""Simplify tracked changes by merging adjacent w:ins or w:del elements. + +Merges adjacent elements from the same author into a single element. +Same for elements. This makes heavily-redlined documents easier to +work with by reducing the number of tracked change wrappers. + +Rules: +- Only merges w:ins with w:ins, w:del with w:del (same element type) +- Only merges if same author (ignores timestamp differences) +- Only merges if truly adjacent (only whitespace between them) +""" + +import xml.etree.ElementTree as ET +import zipfile +from pathlib import Path + +import defusedxml.minidom + +WORD_NS = "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + + +def simplify_redlines(input_dir: str) -> tuple[int, str]: + doc_xml = Path(input_dir) / "word" / "document.xml" + + if not doc_xml.exists(): + return 0, f"Error: {doc_xml} not found" + + try: + dom = defusedxml.minidom.parseString(doc_xml.read_text(encoding="utf-8")) + root = dom.documentElement + + merge_count = 0 + + containers = _find_elements(root, "p") + _find_elements(root, "tc") + + for container in containers: + merge_count += _merge_tracked_changes_in(container, "ins") + merge_count += _merge_tracked_changes_in(container, "del") + + doc_xml.write_bytes(dom.toxml(encoding="UTF-8")) + return merge_count, f"Simplified {merge_count} tracked changes" + + except Exception as e: + return 0, f"Error: {e}" + + +def _merge_tracked_changes_in(container, tag: str) -> int: + merge_count = 0 + + tracked = [ + child + for child in container.childNodes + if child.nodeType == child.ELEMENT_NODE and _is_element(child, tag) + ] + + if len(tracked) < 2: + return 0 + + i = 0 + while i < len(tracked) - 1: + curr = tracked[i] + next_elem = tracked[i + 1] + + if _can_merge_tracked(curr, next_elem): + _merge_tracked_content(curr, next_elem) + container.removeChild(next_elem) + tracked.pop(i + 1) + merge_count += 1 + else: + i += 1 + + return merge_count + + +def _is_element(node, tag: str) -> bool: + name = node.localName or node.tagName + return name == tag or name.endswith(f":{tag}") + + +def _get_author(elem) -> str: + author = elem.getAttribute("w:author") + if not author: + for attr in elem.attributes.values(): + if attr.localName == "author" or attr.name.endswith(":author"): + return attr.value + return author + + +def _can_merge_tracked(elem1, elem2) -> bool: + if _get_author(elem1) != _get_author(elem2): + return False + + node = elem1.nextSibling + while node and node != elem2: + if node.nodeType == node.ELEMENT_NODE: + return False + if node.nodeType == node.TEXT_NODE and node.data.strip(): + return False + node = node.nextSibling + + return True + + +def _merge_tracked_content(target, source): + while source.firstChild: + child = source.firstChild + source.removeChild(child) + target.appendChild(child) + + +def _find_elements(root, tag: str) -> list: + results = [] + + def traverse(node): + if node.nodeType == node.ELEMENT_NODE: + name = node.localName or node.tagName + if name == tag or name.endswith(f":{tag}"): + results.append(node) + for child in node.childNodes: + traverse(child) + + traverse(root) + return results + + +def get_tracked_change_authors(doc_xml_path: Path) -> dict[str, int]: + if not doc_xml_path.exists(): + return {} + + try: + tree = ET.parse(doc_xml_path) + root = tree.getroot() + except ET.ParseError: + return {} + + namespaces = {"w": WORD_NS} + author_attr = f"{{{WORD_NS}}}author" + + authors: dict[str, int] = {} + for tag in ["ins", "del"]: + for elem in root.findall(f".//w:{tag}", namespaces): + author = elem.get(author_attr) + if author: + authors[author] = authors.get(author, 0) + 1 + + return authors + + +def _get_authors_from_docx(docx_path: Path) -> dict[str, int]: + try: + with zipfile.ZipFile(docx_path, "r") as zf: + if "word/document.xml" not in zf.namelist(): + return {} + with zf.open("word/document.xml") as f: + tree = ET.parse(f) + root = tree.getroot() + + namespaces = {"w": WORD_NS} + author_attr = f"{{{WORD_NS}}}author" + + authors: dict[str, int] = {} + for tag in ["ins", "del"]: + for elem in root.findall(f".//w:{tag}", namespaces): + author = elem.get(author_attr) + if author: + authors[author] = authors.get(author, 0) + 1 + return authors + except (zipfile.BadZipFile, ET.ParseError): + return {} + + +def infer_author(modified_dir: Path, original_docx: Path, default: str = "Claude") -> str: + modified_xml = modified_dir / "word" / "document.xml" + modified_authors = get_tracked_change_authors(modified_xml) + + if not modified_authors: + return default + + original_authors = _get_authors_from_docx(original_docx) + + new_changes: dict[str, int] = {} + for author, count in modified_authors.items(): + original_count = original_authors.get(author, 0) + diff = count - original_count + if diff > 0: + new_changes[author] = diff + + if not new_changes: + return default + + if len(new_changes) == 1: + return next(iter(new_changes)) + + raise ValueError( + f"Multiple authors added new changes: {new_changes}. " + "Cannot infer which author to validate." + ) diff --git a/.claude/skills/pptx/scripts/office/pack.py b/.claude/skills/pptx/scripts/office/pack.py new file mode 100755 index 0000000..db29ed8 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/pack.py @@ -0,0 +1,159 @@ +"""Pack a directory into a DOCX, PPTX, or XLSX file. + +Validates with auto-repair, condenses XML formatting, and creates the Office file. + +Usage: + python pack.py [--original ] [--validate true|false] + +Examples: + python pack.py unpacked/ output.docx --original input.docx + python pack.py unpacked/ output.pptx --validate false +""" + +import argparse +import sys +import shutil +import tempfile +import zipfile +from pathlib import Path + +import defusedxml.minidom + +from validators import DOCXSchemaValidator, PPTXSchemaValidator, RedliningValidator + +def pack( + input_directory: str, + output_file: str, + original_file: str | None = None, + validate: bool = True, + infer_author_func=None, +) -> tuple[None, str]: + input_dir = Path(input_directory) + output_path = Path(output_file) + suffix = output_path.suffix.lower() + + if not input_dir.is_dir(): + return None, f"Error: {input_dir} is not a directory" + + if suffix not in {".docx", ".pptx", ".xlsx"}: + return None, f"Error: {output_file} must be a .docx, .pptx, or .xlsx file" + + if validate and original_file: + original_path = Path(original_file) + if original_path.exists(): + success, output = _run_validation( + input_dir, original_path, suffix, infer_author_func + ) + if output: + print(output) + if not success: + return None, f"Error: Validation failed for {input_dir}" + + with tempfile.TemporaryDirectory() as temp_dir: + temp_content_dir = Path(temp_dir) / "content" + shutil.copytree(input_dir, temp_content_dir) + + for pattern in ["*.xml", "*.rels"]: + for xml_file in temp_content_dir.rglob(pattern): + _condense_xml(xml_file) + + output_path.parent.mkdir(parents=True, exist_ok=True) + with zipfile.ZipFile(output_path, "w", zipfile.ZIP_DEFLATED) as zf: + for f in temp_content_dir.rglob("*"): + if f.is_file(): + zf.write(f, f.relative_to(temp_content_dir)) + + return None, f"Successfully packed {input_dir} to {output_file}" + + +def _run_validation( + unpacked_dir: Path, + original_file: Path, + suffix: str, + infer_author_func=None, +) -> tuple[bool, str | None]: + output_lines = [] + validators = [] + + if suffix == ".docx": + author = "Claude" + if infer_author_func: + try: + author = infer_author_func(unpacked_dir, original_file) + except ValueError as e: + print(f"Warning: {e} Using default author 'Claude'.", file=sys.stderr) + + validators = [ + DOCXSchemaValidator(unpacked_dir, original_file), + RedliningValidator(unpacked_dir, original_file, author=author), + ] + elif suffix == ".pptx": + validators = [PPTXSchemaValidator(unpacked_dir, original_file)] + + if not validators: + return True, None + + total_repairs = sum(v.repair() for v in validators) + if total_repairs: + output_lines.append(f"Auto-repaired {total_repairs} issue(s)") + + success = all(v.validate() for v in validators) + + if success: + output_lines.append("All validations PASSED!") + + return success, "\n".join(output_lines) if output_lines else None + + +def _condense_xml(xml_file: Path) -> None: + try: + with open(xml_file, encoding="utf-8") as f: + dom = defusedxml.minidom.parse(f) + + for element in dom.getElementsByTagName("*"): + if element.tagName.endswith(":t"): + continue + + for child in list(element.childNodes): + if ( + child.nodeType == child.TEXT_NODE + and child.nodeValue + and child.nodeValue.strip() == "" + ) or child.nodeType == child.COMMENT_NODE: + element.removeChild(child) + + xml_file.write_bytes(dom.toxml(encoding="UTF-8")) + except Exception as e: + print(f"ERROR: Failed to parse {xml_file.name}: {e}", file=sys.stderr) + raise + + +if __name__ == "__main__": + parser = argparse.ArgumentParser( + description="Pack a directory into a DOCX, PPTX, or XLSX file" + ) + parser.add_argument("input_directory", help="Unpacked Office document directory") + parser.add_argument("output_file", help="Output Office file (.docx/.pptx/.xlsx)") + parser.add_argument( + "--original", + help="Original file for validation comparison", + ) + parser.add_argument( + "--validate", + type=lambda x: x.lower() == "true", + default=True, + metavar="true|false", + help="Run validation with auto-repair (default: true)", + ) + args = parser.parse_args() + + _, message = pack( + args.input_directory, + args.output_file, + original_file=args.original, + validate=args.validate, + ) + print(message) + + if "Error" in message: + sys.exit(1) diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd new file mode 100644 index 0000000..6454ef9 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd @@ -0,0 +1,1499 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd new file mode 100644 index 0000000..afa4f46 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd @@ -0,0 +1,146 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd new file mode 100644 index 0000000..64e66b8 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd @@ -0,0 +1,1085 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd new file mode 100644 index 0000000..687eea8 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd @@ -0,0 +1,11 @@ + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd new file mode 100644 index 0000000..6ac81b0 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd @@ -0,0 +1,3081 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd new file mode 100644 index 0000000..1dbf051 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd @@ -0,0 +1,23 @@ + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd new file mode 100644 index 0000000..f1af17d --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd @@ -0,0 +1,185 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd new file mode 100644 index 0000000..0a185ab --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd @@ -0,0 +1,287 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd new file mode 100644 index 0000000..14ef488 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd @@ -0,0 +1,1676 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd new file mode 100644 index 0000000..c20f3bf --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd @@ -0,0 +1,28 @@ + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd new file mode 100644 index 0000000..ac60252 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd @@ -0,0 +1,144 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd new file mode 100644 index 0000000..424b8ba --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd @@ -0,0 +1,174 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd new file mode 100644 index 0000000..2bddce2 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd @@ -0,0 +1,25 @@ + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd new file mode 100644 index 0000000..8a8c18b --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd @@ -0,0 +1,18 @@ + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd new file mode 100644 index 0000000..5c42706 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd @@ -0,0 +1,59 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd new file mode 100644 index 0000000..853c341 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd @@ -0,0 +1,56 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd new file mode 100644 index 0000000..da835ee --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd @@ -0,0 +1,195 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd new file mode 100644 index 0000000..87ad265 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd @@ -0,0 +1,582 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd new file mode 100644 index 0000000..9e86f1b --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd @@ -0,0 +1,25 @@ + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd new file mode 100644 index 0000000..d0be42e --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd @@ -0,0 +1,4439 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd new file mode 100644 index 0000000..8821dd1 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd @@ -0,0 +1,570 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd new file mode 100644 index 0000000..ca2575c --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd @@ -0,0 +1,509 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd new file mode 100644 index 0000000..dd079e6 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd @@ -0,0 +1,12 @@ + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd new file mode 100644 index 0000000..3dd6cf6 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd @@ -0,0 +1,108 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd new file mode 100644 index 0000000..f1041e3 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd @@ -0,0 +1,96 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd new file mode 100644 index 0000000..9c5b7a6 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd @@ -0,0 +1,3646 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd new file mode 100644 index 0000000..0f13678 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd @@ -0,0 +1,116 @@ + + + + + + See http://www.w3.org/XML/1998/namespace.html and + http://www.w3.org/TR/REC-xml for information about this namespace. + + This schema document describes the XML namespace, in a form + suitable for import by other schema documents. + + Note that local names in this namespace are intended to be defined + only by the World Wide Web Consortium or its subgroups. The + following names are currently defined in this namespace and should + not be used with conflicting semantics by any Working Group, + specification, or document instance: + + base (as an attribute name): denotes an attribute whose value + provides a URI to be used as the base for interpreting any + relative URIs in the scope of the element on which it + appears; its value is inherited. This name is reserved + by virtue of its definition in the XML Base specification. + + lang (as an attribute name): denotes an attribute whose value + is a language code for the natural language of the content of + any element; its value is inherited. This name is reserved + by virtue of its definition in the XML specification. + + space (as an attribute name): denotes an attribute whose + value is a keyword indicating what whitespace processing + discipline is intended for the content of the element; its + value is inherited. This name is reserved by virtue of its + definition in the XML specification. + + Father (in any context at all): denotes Jon Bosak, the chair of + the original XML Working Group. This name is reserved by + the following decision of the W3C XML Plenary and + XML Coordination groups: + + In appreciation for his vision, leadership and dedication + the W3C XML Plenary on this 10th day of February, 2000 + reserves for Jon Bosak in perpetuity the XML name + xml:Father + + + + + This schema defines attributes and an attribute group + suitable for use by + schemas wishing to allow xml:base, xml:lang or xml:space attributes + on elements they define. + + To enable this, such a schema must import this schema + for the XML namespace, e.g. as follows: + <schema . . .> + . . . + <import namespace="http://www.w3.org/XML/1998/namespace" + schemaLocation="http://www.w3.org/2001/03/xml.xsd"/> + + Subsequently, qualified reference to any of the attributes + or the group defined below will have the desired effect, e.g. + + <type . . .> + . . . + <attributeGroup ref="xml:specialAttrs"/> + + will define a type which will schema-validate an instance + element with any of those attributes + + + + In keeping with the XML Schema WG's standard versioning + policy, this schema document will persist at + http://www.w3.org/2001/03/xml.xsd. + At the date of issue it can also be found at + http://www.w3.org/2001/xml.xsd. + The schema document at that URI may however change in the future, + in order to remain compatible with the latest version of XML Schema + itself. In other words, if the XML Schema namespace changes, the version + of this document at + http://www.w3.org/2001/xml.xsd will change + accordingly; the version at + http://www.w3.org/2001/03/xml.xsd will not change. + + + + + + In due course, we should install the relevant ISO 2- and 3-letter + codes as the enumerated possible values . . . + + + + + + + + + + + + + + + See http://www.w3.org/TR/xmlbase/ for + information about this attribute. + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd b/.claude/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd new file mode 100644 index 0000000..a6de9d2 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd @@ -0,0 +1,42 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd b/.claude/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd new file mode 100644 index 0000000..10e978b --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd @@ -0,0 +1,50 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd b/.claude/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd new file mode 100644 index 0000000..4248bf7 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd @@ -0,0 +1,49 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd b/.claude/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd new file mode 100644 index 0000000..5649746 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd @@ -0,0 +1,33 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/mce/mc.xsd b/.claude/skills/pptx/scripts/office/schemas/mce/mc.xsd new file mode 100644 index 0000000..ef72545 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/mce/mc.xsd @@ -0,0 +1,75 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/microsoft/wml-2010.xsd b/.claude/skills/pptx/scripts/office/schemas/microsoft/wml-2010.xsd new file mode 100644 index 0000000..f65f777 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/microsoft/wml-2010.xsd @@ -0,0 +1,560 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/microsoft/wml-2012.xsd b/.claude/skills/pptx/scripts/office/schemas/microsoft/wml-2012.xsd new file mode 100644 index 0000000..6b00755 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/microsoft/wml-2012.xsd @@ -0,0 +1,67 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/microsoft/wml-2018.xsd b/.claude/skills/pptx/scripts/office/schemas/microsoft/wml-2018.xsd new file mode 100644 index 0000000..f321d33 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/microsoft/wml-2018.xsd @@ -0,0 +1,14 @@ + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/microsoft/wml-cex-2018.xsd b/.claude/skills/pptx/scripts/office/schemas/microsoft/wml-cex-2018.xsd new file mode 100644 index 0000000..364c6a9 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/microsoft/wml-cex-2018.xsd @@ -0,0 +1,20 @@ + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/microsoft/wml-cid-2016.xsd b/.claude/skills/pptx/scripts/office/schemas/microsoft/wml-cid-2016.xsd new file mode 100644 index 0000000..fed9d15 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/microsoft/wml-cid-2016.xsd @@ -0,0 +1,13 @@ + + + + + + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd b/.claude/skills/pptx/scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd new file mode 100644 index 0000000..680cf15 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd @@ -0,0 +1,4 @@ + + + + diff --git a/.claude/skills/pptx/scripts/office/schemas/microsoft/wml-symex-2015.xsd b/.claude/skills/pptx/scripts/office/schemas/microsoft/wml-symex-2015.xsd new file mode 100644 index 0000000..89ada90 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/schemas/microsoft/wml-symex-2015.xsd @@ -0,0 +1,8 @@ + + + + + + + + diff --git a/.claude/skills/pptx/scripts/office/soffice.py b/.claude/skills/pptx/scripts/office/soffice.py new file mode 100644 index 0000000..c7f7e32 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/soffice.py @@ -0,0 +1,183 @@ +""" +Helper for running LibreOffice (soffice) in environments where AF_UNIX +sockets may be blocked (e.g., sandboxed VMs). Detects the restriction +at runtime and applies an LD_PRELOAD shim if needed. + +Usage: + from office.soffice import run_soffice, get_soffice_env + + # Option 1 – run soffice directly + result = run_soffice(["--headless", "--convert-to", "pdf", "input.docx"]) + + # Option 2 – get env dict for your own subprocess calls + env = get_soffice_env() + subprocess.run(["soffice", ...], env=env) +""" + +import os +import socket +import subprocess +import tempfile +from pathlib import Path + + +def get_soffice_env() -> dict: + env = os.environ.copy() + env["SAL_USE_VCLPLUGIN"] = "svp" + + if _needs_shim(): + shim = _ensure_shim() + env["LD_PRELOAD"] = str(shim) + + return env + + +def run_soffice(args: list[str], **kwargs) -> subprocess.CompletedProcess: + env = get_soffice_env() + return subprocess.run(["soffice"] + args, env=env, **kwargs) + + + +_SHIM_SO = Path(tempfile.gettempdir()) / "lo_socket_shim.so" + + +def _needs_shim() -> bool: + try: + s = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM) + s.close() + return False + except OSError: + return True + + +def _ensure_shim() -> Path: + if _SHIM_SO.exists(): + return _SHIM_SO + + src = Path(tempfile.gettempdir()) / "lo_socket_shim.c" + src.write_text(_SHIM_SOURCE) + subprocess.run( + ["gcc", "-shared", "-fPIC", "-o", str(_SHIM_SO), str(src), "-ldl"], + check=True, + capture_output=True, + ) + src.unlink() + return _SHIM_SO + + + +_SHIM_SOURCE = r""" +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include + +static int (*real_socket)(int, int, int); +static int (*real_socketpair)(int, int, int, int[2]); +static int (*real_listen)(int, int); +static int (*real_accept)(int, struct sockaddr *, socklen_t *); +static int (*real_close)(int); +static int (*real_read)(int, void *, size_t); + +/* Per-FD bookkeeping (FDs >= 1024 are passed through unshimmed). */ +static int is_shimmed[1024]; +static int peer_of[1024]; +static int wake_r[1024]; /* accept() blocks reading this */ +static int wake_w[1024]; /* close() writes to this */ +static int listener_fd = -1; /* FD that received listen() */ + +__attribute__((constructor)) +static void init(void) { + real_socket = dlsym(RTLD_NEXT, "socket"); + real_socketpair = dlsym(RTLD_NEXT, "socketpair"); + real_listen = dlsym(RTLD_NEXT, "listen"); + real_accept = dlsym(RTLD_NEXT, "accept"); + real_close = dlsym(RTLD_NEXT, "close"); + real_read = dlsym(RTLD_NEXT, "read"); + for (int i = 0; i < 1024; i++) { + peer_of[i] = -1; + wake_r[i] = -1; + wake_w[i] = -1; + } +} + +/* ---- socket ---------------------------------------------------------- */ +int socket(int domain, int type, int protocol) { + if (domain == AF_UNIX) { + int fd = real_socket(domain, type, protocol); + if (fd >= 0) return fd; + /* socket(AF_UNIX) blocked – fall back to socketpair(). */ + int sv[2]; + if (real_socketpair(domain, type, protocol, sv) == 0) { + if (sv[0] >= 0 && sv[0] < 1024) { + is_shimmed[sv[0]] = 1; + peer_of[sv[0]] = sv[1]; + int wp[2]; + if (pipe(wp) == 0) { + wake_r[sv[0]] = wp[0]; + wake_w[sv[0]] = wp[1]; + } + } + return sv[0]; + } + errno = EPERM; + return -1; + } + return real_socket(domain, type, protocol); +} + +/* ---- listen ---------------------------------------------------------- */ +int listen(int sockfd, int backlog) { + if (sockfd >= 0 && sockfd < 1024 && is_shimmed[sockfd]) { + listener_fd = sockfd; + return 0; + } + return real_listen(sockfd, backlog); +} + +/* ---- accept ---------------------------------------------------------- */ +int accept(int sockfd, struct sockaddr *addr, socklen_t *addrlen) { + if (sockfd >= 0 && sockfd < 1024 && is_shimmed[sockfd]) { + /* Block until close() writes to the wake pipe. */ + if (wake_r[sockfd] >= 0) { + char buf; + real_read(wake_r[sockfd], &buf, 1); + } + errno = ECONNABORTED; + return -1; + } + return real_accept(sockfd, addr, addrlen); +} + +/* ---- close ----------------------------------------------------------- */ +int close(int fd) { + if (fd >= 0 && fd < 1024 && is_shimmed[fd]) { + int was_listener = (fd == listener_fd); + is_shimmed[fd] = 0; + + if (wake_w[fd] >= 0) { /* unblock accept() */ + char c = 0; + write(wake_w[fd], &c, 1); + real_close(wake_w[fd]); + wake_w[fd] = -1; + } + if (wake_r[fd] >= 0) { real_close(wake_r[fd]); wake_r[fd] = -1; } + if (peer_of[fd] >= 0) { real_close(peer_of[fd]); peer_of[fd] = -1; } + + if (was_listener) + _exit(0); /* conversion done – exit */ + } + return real_close(fd); +} +""" + + + +if __name__ == "__main__": + import sys + result = run_soffice(sys.argv[1:]) + sys.exit(result.returncode) diff --git a/.claude/skills/pptx/scripts/office/unpack.py b/.claude/skills/pptx/scripts/office/unpack.py new file mode 100755 index 0000000..0015253 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/unpack.py @@ -0,0 +1,132 @@ +"""Unpack Office files (DOCX, PPTX, XLSX) for editing. + +Extracts the ZIP archive, pretty-prints XML files, and optionally: +- Merges adjacent runs with identical formatting (DOCX only) +- Simplifies adjacent tracked changes from same author (DOCX only) + +Usage: + python unpack.py [options] + +Examples: + python unpack.py document.docx unpacked/ + python unpack.py presentation.pptx unpacked/ + python unpack.py document.docx unpacked/ --merge-runs false +""" + +import argparse +import sys +import zipfile +from pathlib import Path + +import defusedxml.minidom + +from helpers.merge_runs import merge_runs as do_merge_runs +from helpers.simplify_redlines import simplify_redlines as do_simplify_redlines + +SMART_QUOTE_REPLACEMENTS = { + "\u201c": "“", + "\u201d": "”", + "\u2018": "‘", + "\u2019": "’", +} + + +def unpack( + input_file: str, + output_directory: str, + merge_runs: bool = True, + simplify_redlines: bool = True, +) -> tuple[None, str]: + input_path = Path(input_file) + output_path = Path(output_directory) + suffix = input_path.suffix.lower() + + if not input_path.exists(): + return None, f"Error: {input_file} does not exist" + + if suffix not in {".docx", ".pptx", ".xlsx"}: + return None, f"Error: {input_file} must be a .docx, .pptx, or .xlsx file" + + try: + output_path.mkdir(parents=True, exist_ok=True) + + with zipfile.ZipFile(input_path, "r") as zf: + zf.extractall(output_path) + + xml_files = list(output_path.rglob("*.xml")) + list(output_path.rglob("*.rels")) + for xml_file in xml_files: + _pretty_print_xml(xml_file) + + message = f"Unpacked {input_file} ({len(xml_files)} XML files)" + + if suffix == ".docx": + if simplify_redlines: + simplify_count, _ = do_simplify_redlines(str(output_path)) + message += f", simplified {simplify_count} tracked changes" + + if merge_runs: + merge_count, _ = do_merge_runs(str(output_path)) + message += f", merged {merge_count} runs" + + for xml_file in xml_files: + _escape_smart_quotes(xml_file) + + return None, message + + except zipfile.BadZipFile: + return None, f"Error: {input_file} is not a valid Office file" + except Exception as e: + return None, f"Error unpacking: {e}" + + +def _pretty_print_xml(xml_file: Path) -> None: + try: + content = xml_file.read_text(encoding="utf-8") + dom = defusedxml.minidom.parseString(content) + xml_file.write_bytes(dom.toprettyxml(indent=" ", encoding="utf-8")) + except Exception: + pass + + +def _escape_smart_quotes(xml_file: Path) -> None: + try: + content = xml_file.read_text(encoding="utf-8") + for char, entity in SMART_QUOTE_REPLACEMENTS.items(): + content = content.replace(char, entity) + xml_file.write_text(content, encoding="utf-8") + except Exception: + pass + + +if __name__ == "__main__": + parser = argparse.ArgumentParser( + description="Unpack an Office file (DOCX, PPTX, XLSX) for editing" + ) + parser.add_argument("input_file", help="Office file to unpack") + parser.add_argument("output_directory", help="Output directory") + parser.add_argument( + "--merge-runs", + type=lambda x: x.lower() == "true", + default=True, + metavar="true|false", + help="Merge adjacent runs with identical formatting (DOCX only, default: true)", + ) + parser.add_argument( + "--simplify-redlines", + type=lambda x: x.lower() == "true", + default=True, + metavar="true|false", + help="Merge adjacent tracked changes from same author (DOCX only, default: true)", + ) + args = parser.parse_args() + + _, message = unpack( + args.input_file, + args.output_directory, + merge_runs=args.merge_runs, + simplify_redlines=args.simplify_redlines, + ) + print(message) + + if "Error" in message: + sys.exit(1) diff --git a/.claude/skills/pptx/scripts/office/validate.py b/.claude/skills/pptx/scripts/office/validate.py new file mode 100755 index 0000000..03b01f6 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/validate.py @@ -0,0 +1,111 @@ +""" +Command line tool to validate Office document XML files against XSD schemas and tracked changes. + +Usage: + python validate.py [--original ] [--auto-repair] [--author NAME] + +The first argument can be either: +- An unpacked directory containing the Office document XML files +- A packed Office file (.docx/.pptx/.xlsx) which will be unpacked to a temp directory + +Auto-repair fixes: +- paraId/durableId values that exceed OOXML limits +- Missing xml:space="preserve" on w:t elements with whitespace +""" + +import argparse +import sys +import tempfile +import zipfile +from pathlib import Path + +from validators import DOCXSchemaValidator, PPTXSchemaValidator, RedliningValidator + + +def main(): + parser = argparse.ArgumentParser(description="Validate Office document XML files") + parser.add_argument( + "path", + help="Path to unpacked directory or packed Office file (.docx/.pptx/.xlsx)", + ) + parser.add_argument( + "--original", + required=False, + default=None, + help="Path to original file (.docx/.pptx/.xlsx). If omitted, all XSD errors are reported and redlining validation is skipped.", + ) + parser.add_argument( + "-v", + "--verbose", + action="store_true", + help="Enable verbose output", + ) + parser.add_argument( + "--auto-repair", + action="store_true", + help="Automatically repair common issues (hex IDs, whitespace preservation)", + ) + parser.add_argument( + "--author", + default="Claude", + help="Author name for redlining validation (default: Claude)", + ) + args = parser.parse_args() + + path = Path(args.path) + assert path.exists(), f"Error: {path} does not exist" + + original_file = None + if args.original: + original_file = Path(args.original) + assert original_file.is_file(), f"Error: {original_file} is not a file" + assert original_file.suffix.lower() in [".docx", ".pptx", ".xlsx"], ( + f"Error: {original_file} must be a .docx, .pptx, or .xlsx file" + ) + + file_extension = (original_file or path).suffix.lower() + assert file_extension in [".docx", ".pptx", ".xlsx"], ( + f"Error: Cannot determine file type from {path}. Use --original or provide a .docx/.pptx/.xlsx file." + ) + + if path.is_file() and path.suffix.lower() in [".docx", ".pptx", ".xlsx"]: + temp_dir = tempfile.mkdtemp() + with zipfile.ZipFile(path, "r") as zf: + zf.extractall(temp_dir) + unpacked_dir = Path(temp_dir) + else: + assert path.is_dir(), f"Error: {path} is not a directory or Office file" + unpacked_dir = path + + match file_extension: + case ".docx": + validators = [ + DOCXSchemaValidator(unpacked_dir, original_file, verbose=args.verbose), + ] + if original_file: + validators.append( + RedliningValidator(unpacked_dir, original_file, verbose=args.verbose, author=args.author) + ) + case ".pptx": + validators = [ + PPTXSchemaValidator(unpacked_dir, original_file, verbose=args.verbose), + ] + case _: + print(f"Error: Validation not supported for file type {file_extension}") + sys.exit(1) + + if args.auto_repair: + total_repairs = sum(v.repair() for v in validators) + if total_repairs: + print(f"Auto-repaired {total_repairs} issue(s)") + + success = all(v.validate() for v in validators) + + if success: + print("All validations PASSED!") + + sys.exit(0 if success else 1) + + +if __name__ == "__main__": + main() diff --git a/.claude/skills/pptx/scripts/office/validators/__init__.py b/.claude/skills/pptx/scripts/office/validators/__init__.py new file mode 100644 index 0000000..db092ec --- /dev/null +++ b/.claude/skills/pptx/scripts/office/validators/__init__.py @@ -0,0 +1,15 @@ +""" +Validation modules for Word document processing. +""" + +from .base import BaseSchemaValidator +from .docx import DOCXSchemaValidator +from .pptx import PPTXSchemaValidator +from .redlining import RedliningValidator + +__all__ = [ + "BaseSchemaValidator", + "DOCXSchemaValidator", + "PPTXSchemaValidator", + "RedliningValidator", +] diff --git a/.claude/skills/pptx/scripts/office/validators/base.py b/.claude/skills/pptx/scripts/office/validators/base.py new file mode 100644 index 0000000..db4a06a --- /dev/null +++ b/.claude/skills/pptx/scripts/office/validators/base.py @@ -0,0 +1,847 @@ +""" +Base validator with common validation logic for document files. +""" + +import re +from pathlib import Path + +import defusedxml.minidom +import lxml.etree + + +class BaseSchemaValidator: + + IGNORED_VALIDATION_ERRORS = [ + "hyphenationZone", + "purl.org/dc/terms", + ] + + UNIQUE_ID_REQUIREMENTS = { + "comment": ("id", "file"), + "commentrangestart": ("id", "file"), + "commentrangeend": ("id", "file"), + "bookmarkstart": ("id", "file"), + "bookmarkend": ("id", "file"), + "sldid": ("id", "file"), + "sldmasterid": ("id", "global"), + "sldlayoutid": ("id", "global"), + "cm": ("authorid", "file"), + "sheet": ("sheetid", "file"), + "definedname": ("id", "file"), + "cxnsp": ("id", "file"), + "sp": ("id", "file"), + "pic": ("id", "file"), + "grpsp": ("id", "file"), + } + + EXCLUDED_ID_CONTAINERS = { + "sectionlst", + } + + ELEMENT_RELATIONSHIP_TYPES = {} + + SCHEMA_MAPPINGS = { + "word": "ISO-IEC29500-4_2016/wml.xsd", + "ppt": "ISO-IEC29500-4_2016/pml.xsd", + "xl": "ISO-IEC29500-4_2016/sml.xsd", + "[Content_Types].xml": "ecma/fouth-edition/opc-contentTypes.xsd", + "app.xml": "ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd", + "core.xml": "ecma/fouth-edition/opc-coreProperties.xsd", + "custom.xml": "ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd", + ".rels": "ecma/fouth-edition/opc-relationships.xsd", + "people.xml": "microsoft/wml-2012.xsd", + "commentsIds.xml": "microsoft/wml-cid-2016.xsd", + "commentsExtensible.xml": "microsoft/wml-cex-2018.xsd", + "commentsExtended.xml": "microsoft/wml-2012.xsd", + "chart": "ISO-IEC29500-4_2016/dml-chart.xsd", + "theme": "ISO-IEC29500-4_2016/dml-main.xsd", + "drawing": "ISO-IEC29500-4_2016/dml-main.xsd", + } + + MC_NAMESPACE = "http://schemas.openxmlformats.org/markup-compatibility/2006" + XML_NAMESPACE = "http://www.w3.org/XML/1998/namespace" + + PACKAGE_RELATIONSHIPS_NAMESPACE = ( + "http://schemas.openxmlformats.org/package/2006/relationships" + ) + OFFICE_RELATIONSHIPS_NAMESPACE = ( + "http://schemas.openxmlformats.org/officeDocument/2006/relationships" + ) + CONTENT_TYPES_NAMESPACE = ( + "http://schemas.openxmlformats.org/package/2006/content-types" + ) + + MAIN_CONTENT_FOLDERS = {"word", "ppt", "xl"} + + OOXML_NAMESPACES = { + "http://schemas.openxmlformats.org/officeDocument/2006/math", + "http://schemas.openxmlformats.org/officeDocument/2006/relationships", + "http://schemas.openxmlformats.org/schemaLibrary/2006/main", + "http://schemas.openxmlformats.org/drawingml/2006/main", + "http://schemas.openxmlformats.org/drawingml/2006/chart", + "http://schemas.openxmlformats.org/drawingml/2006/chartDrawing", + "http://schemas.openxmlformats.org/drawingml/2006/diagram", + "http://schemas.openxmlformats.org/drawingml/2006/picture", + "http://schemas.openxmlformats.org/drawingml/2006/spreadsheetDrawing", + "http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing", + "http://schemas.openxmlformats.org/wordprocessingml/2006/main", + "http://schemas.openxmlformats.org/presentationml/2006/main", + "http://schemas.openxmlformats.org/spreadsheetml/2006/main", + "http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes", + "http://www.w3.org/XML/1998/namespace", + } + + def __init__(self, unpacked_dir, original_file=None, verbose=False): + self.unpacked_dir = Path(unpacked_dir).resolve() + self.original_file = Path(original_file) if original_file else None + self.verbose = verbose + + self.schemas_dir = Path(__file__).parent.parent / "schemas" + + patterns = ["*.xml", "*.rels"] + self.xml_files = [ + f for pattern in patterns for f in self.unpacked_dir.rglob(pattern) + ] + + if not self.xml_files: + print(f"Warning: No XML files found in {self.unpacked_dir}") + + def validate(self): + raise NotImplementedError("Subclasses must implement the validate method") + + def repair(self) -> int: + return self.repair_whitespace_preservation() + + def repair_whitespace_preservation(self) -> int: + repairs = 0 + + for xml_file in self.xml_files: + try: + content = xml_file.read_text(encoding="utf-8") + dom = defusedxml.minidom.parseString(content) + modified = False + + for elem in dom.getElementsByTagName("*"): + if elem.tagName.endswith(":t") and elem.firstChild: + text = elem.firstChild.nodeValue + if text and (text.startswith((' ', '\t')) or text.endswith((' ', '\t'))): + if elem.getAttribute("xml:space") != "preserve": + elem.setAttribute("xml:space", "preserve") + text_preview = repr(text[:30]) + "..." if len(text) > 30 else repr(text) + print(f" Repaired: {xml_file.name}: Added xml:space='preserve' to {elem.tagName}: {text_preview}") + repairs += 1 + modified = True + + if modified: + xml_file.write_bytes(dom.toxml(encoding="UTF-8")) + + except Exception: + pass + + return repairs + + def validate_xml(self): + errors = [] + + for xml_file in self.xml_files: + try: + lxml.etree.parse(str(xml_file)) + except lxml.etree.XMLSyntaxError as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {e.lineno}: {e.msg}" + ) + except Exception as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Unexpected error: {str(e)}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} XML violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All XML files are well-formed") + return True + + def validate_namespaces(self): + errors = [] + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + declared = set(root.nsmap.keys()) - {None} + + for attr_val in [ + v for k, v in root.attrib.items() if k.endswith("Ignorable") + ]: + undeclared = set(attr_val.split()) - declared + errors.extend( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Namespace '{ns}' in Ignorable but not declared" + for ns in undeclared + ) + except lxml.etree.XMLSyntaxError: + continue + + if errors: + print(f"FAILED - {len(errors)} namespace issues:") + for error in errors: + print(error) + return False + if self.verbose: + print("PASSED - All namespace prefixes properly declared") + return True + + def validate_unique_ids(self): + errors = [] + global_ids = {} + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + file_ids = {} + + mc_elements = root.xpath( + ".//mc:AlternateContent", namespaces={"mc": self.MC_NAMESPACE} + ) + for elem in mc_elements: + elem.getparent().remove(elem) + + for elem in root.iter(): + tag = ( + elem.tag.split("}")[-1].lower() + if "}" in elem.tag + else elem.tag.lower() + ) + + if tag in self.UNIQUE_ID_REQUIREMENTS: + in_excluded_container = any( + ancestor.tag.split("}")[-1].lower() in self.EXCLUDED_ID_CONTAINERS + for ancestor in elem.iterancestors() + ) + if in_excluded_container: + continue + + attr_name, scope = self.UNIQUE_ID_REQUIREMENTS[tag] + + id_value = None + for attr, value in elem.attrib.items(): + attr_local = ( + attr.split("}")[-1].lower() + if "}" in attr + else attr.lower() + ) + if attr_local == attr_name: + id_value = value + break + + if id_value is not None: + if scope == "global": + if id_value in global_ids: + prev_file, prev_line, prev_tag = global_ids[ + id_value + ] + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: Global ID '{id_value}' in <{tag}> " + f"already used in {prev_file} at line {prev_line} in <{prev_tag}>" + ) + else: + global_ids[id_value] = ( + xml_file.relative_to(self.unpacked_dir), + elem.sourceline, + tag, + ) + elif scope == "file": + key = (tag, attr_name) + if key not in file_ids: + file_ids[key] = {} + + if id_value in file_ids[key]: + prev_line = file_ids[key][id_value] + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: Duplicate {attr_name}='{id_value}' in <{tag}> " + f"(first occurrence at line {prev_line})" + ) + else: + file_ids[key][id_value] = elem.sourceline + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} ID uniqueness violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All required IDs are unique") + return True + + def validate_file_references(self): + errors = [] + + rels_files = list(self.unpacked_dir.rglob("*.rels")) + + if not rels_files: + if self.verbose: + print("PASSED - No .rels files found") + return True + + all_files = [] + for file_path in self.unpacked_dir.rglob("*"): + if ( + file_path.is_file() + and file_path.name != "[Content_Types].xml" + and not file_path.name.endswith(".rels") + ): + all_files.append(file_path.resolve()) + + all_referenced_files = set() + + if self.verbose: + print( + f"Found {len(rels_files)} .rels files and {len(all_files)} target files" + ) + + for rels_file in rels_files: + try: + rels_root = lxml.etree.parse(str(rels_file)).getroot() + + rels_dir = rels_file.parent + + referenced_files = set() + broken_refs = [] + + for rel in rels_root.findall( + ".//ns:Relationship", + namespaces={"ns": self.PACKAGE_RELATIONSHIPS_NAMESPACE}, + ): + target = rel.get("Target") + if target and not target.startswith( + ("http", "mailto:") + ): + if target.startswith("/"): + target_path = self.unpacked_dir / target.lstrip("/") + elif rels_file.name == ".rels": + target_path = self.unpacked_dir / target + else: + base_dir = rels_dir.parent + target_path = base_dir / target + + try: + target_path = target_path.resolve() + if target_path.exists() and target_path.is_file(): + referenced_files.add(target_path) + all_referenced_files.add(target_path) + else: + broken_refs.append((target, rel.sourceline)) + except (OSError, ValueError): + broken_refs.append((target, rel.sourceline)) + + if broken_refs: + rel_path = rels_file.relative_to(self.unpacked_dir) + for broken_ref, line_num in broken_refs: + errors.append( + f" {rel_path}: Line {line_num}: Broken reference to {broken_ref}" + ) + + except Exception as e: + rel_path = rels_file.relative_to(self.unpacked_dir) + errors.append(f" Error parsing {rel_path}: {e}") + + unreferenced_files = set(all_files) - all_referenced_files + + if unreferenced_files: + for unref_file in sorted(unreferenced_files): + unref_rel_path = unref_file.relative_to(self.unpacked_dir) + errors.append(f" Unreferenced file: {unref_rel_path}") + + if errors: + print(f"FAILED - Found {len(errors)} relationship validation errors:") + for error in errors: + print(error) + print( + "CRITICAL: These errors will cause the document to appear corrupt. " + + "Broken references MUST be fixed, " + + "and unreferenced files MUST be referenced or removed." + ) + return False + else: + if self.verbose: + print( + "PASSED - All references are valid and all files are properly referenced" + ) + return True + + def validate_all_relationship_ids(self): + import lxml.etree + + errors = [] + + for xml_file in self.xml_files: + if xml_file.suffix == ".rels": + continue + + rels_dir = xml_file.parent / "_rels" + rels_file = rels_dir / f"{xml_file.name}.rels" + + if not rels_file.exists(): + continue + + try: + rels_root = lxml.etree.parse(str(rels_file)).getroot() + rid_to_type = {} + + for rel in rels_root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rid = rel.get("Id") + rel_type = rel.get("Type", "") + if rid: + if rid in rid_to_type: + rels_rel_path = rels_file.relative_to(self.unpacked_dir) + errors.append( + f" {rels_rel_path}: Line {rel.sourceline}: " + f"Duplicate relationship ID '{rid}' (IDs must be unique)" + ) + type_name = ( + rel_type.split("/")[-1] if "/" in rel_type else rel_type + ) + rid_to_type[rid] = type_name + + xml_root = lxml.etree.parse(str(xml_file)).getroot() + + r_ns = self.OFFICE_RELATIONSHIPS_NAMESPACE + rid_attrs_to_check = ["id", "embed", "link"] + for elem in xml_root.iter(): + for attr_name in rid_attrs_to_check: + rid_attr = elem.get(f"{{{r_ns}}}{attr_name}") + if not rid_attr: + continue + xml_rel_path = xml_file.relative_to(self.unpacked_dir) + elem_name = ( + elem.tag.split("}")[-1] if "}" in elem.tag else elem.tag + ) + + if rid_attr not in rid_to_type: + errors.append( + f" {xml_rel_path}: Line {elem.sourceline}: " + f"<{elem_name}> r:{attr_name} references non-existent relationship '{rid_attr}' " + f"(valid IDs: {', '.join(sorted(rid_to_type.keys())[:5])}{'...' if len(rid_to_type) > 5 else ''})" + ) + elif attr_name == "id" and self.ELEMENT_RELATIONSHIP_TYPES: + expected_type = self._get_expected_relationship_type( + elem_name + ) + if expected_type: + actual_type = rid_to_type[rid_attr] + if expected_type not in actual_type.lower(): + errors.append( + f" {xml_rel_path}: Line {elem.sourceline}: " + f"<{elem_name}> references '{rid_attr}' which points to '{actual_type}' " + f"but should point to a '{expected_type}' relationship" + ) + + except Exception as e: + xml_rel_path = xml_file.relative_to(self.unpacked_dir) + errors.append(f" Error processing {xml_rel_path}: {e}") + + if errors: + print(f"FAILED - Found {len(errors)} relationship ID reference errors:") + for error in errors: + print(error) + print("\nThese ID mismatches will cause the document to appear corrupt!") + return False + else: + if self.verbose: + print("PASSED - All relationship ID references are valid") + return True + + def _get_expected_relationship_type(self, element_name): + elem_lower = element_name.lower() + + if elem_lower in self.ELEMENT_RELATIONSHIP_TYPES: + return self.ELEMENT_RELATIONSHIP_TYPES[elem_lower] + + if elem_lower.endswith("id") and len(elem_lower) > 2: + prefix = elem_lower[:-2] + if prefix.endswith("master"): + return prefix.lower() + elif prefix.endswith("layout"): + return prefix.lower() + else: + if prefix == "sld": + return "slide" + return prefix.lower() + + if elem_lower.endswith("reference") and len(elem_lower) > 9: + prefix = elem_lower[:-9] + return prefix.lower() + + return None + + def validate_content_types(self): + errors = [] + + content_types_file = self.unpacked_dir / "[Content_Types].xml" + if not content_types_file.exists(): + print("FAILED - [Content_Types].xml file not found") + return False + + try: + root = lxml.etree.parse(str(content_types_file)).getroot() + declared_parts = set() + declared_extensions = set() + + for override in root.findall( + f".//{{{self.CONTENT_TYPES_NAMESPACE}}}Override" + ): + part_name = override.get("PartName") + if part_name is not None: + declared_parts.add(part_name.lstrip("/")) + + for default in root.findall( + f".//{{{self.CONTENT_TYPES_NAMESPACE}}}Default" + ): + extension = default.get("Extension") + if extension is not None: + declared_extensions.add(extension.lower()) + + declarable_roots = { + "sld", + "sldLayout", + "sldMaster", + "presentation", + "document", + "workbook", + "worksheet", + "theme", + } + + media_extensions = { + "png": "image/png", + "jpg": "image/jpeg", + "jpeg": "image/jpeg", + "gif": "image/gif", + "bmp": "image/bmp", + "tiff": "image/tiff", + "wmf": "image/x-wmf", + "emf": "image/x-emf", + } + + all_files = list(self.unpacked_dir.rglob("*")) + all_files = [f for f in all_files if f.is_file()] + + for xml_file in self.xml_files: + path_str = str(xml_file.relative_to(self.unpacked_dir)).replace( + "\\", "/" + ) + + if any( + skip in path_str + for skip in [".rels", "[Content_Types]", "docProps/", "_rels/"] + ): + continue + + try: + root_tag = lxml.etree.parse(str(xml_file)).getroot().tag + root_name = root_tag.split("}")[-1] if "}" in root_tag else root_tag + + if root_name in declarable_roots and path_str not in declared_parts: + errors.append( + f" {path_str}: File with <{root_name}> root not declared in [Content_Types].xml" + ) + + except Exception: + continue + + for file_path in all_files: + if file_path.suffix.lower() in {".xml", ".rels"}: + continue + if file_path.name == "[Content_Types].xml": + continue + if "_rels" in file_path.parts or "docProps" in file_path.parts: + continue + + extension = file_path.suffix.lstrip(".").lower() + if extension and extension not in declared_extensions: + if extension in media_extensions: + relative_path = file_path.relative_to(self.unpacked_dir) + errors.append( + f' {relative_path}: File with extension \'{extension}\' not declared in [Content_Types].xml - should add: ' + ) + + except Exception as e: + errors.append(f" Error parsing [Content_Types].xml: {e}") + + if errors: + print(f"FAILED - Found {len(errors)} content type declaration errors:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print( + "PASSED - All content files are properly declared in [Content_Types].xml" + ) + return True + + def validate_file_against_xsd(self, xml_file, verbose=False): + xml_file = Path(xml_file).resolve() + unpacked_dir = self.unpacked_dir.resolve() + + is_valid, current_errors = self._validate_single_file_xsd( + xml_file, unpacked_dir + ) + + if is_valid is None: + return None, set() + elif is_valid: + return True, set() + + original_errors = self._get_original_file_errors(xml_file) + + assert current_errors is not None + new_errors = current_errors - original_errors + + new_errors = { + e for e in new_errors + if not any(pattern in e for pattern in self.IGNORED_VALIDATION_ERRORS) + } + + if new_errors: + if verbose: + relative_path = xml_file.relative_to(unpacked_dir) + print(f"FAILED - {relative_path}: {len(new_errors)} new error(s)") + for error in list(new_errors)[:3]: + truncated = error[:250] + "..." if len(error) > 250 else error + print(f" - {truncated}") + return False, new_errors + else: + if verbose: + print( + f"PASSED - No new errors (original had {len(current_errors)} errors)" + ) + return True, set() + + def validate_against_xsd(self): + new_errors = [] + original_error_count = 0 + valid_count = 0 + skipped_count = 0 + + for xml_file in self.xml_files: + relative_path = str(xml_file.relative_to(self.unpacked_dir)) + is_valid, new_file_errors = self.validate_file_against_xsd( + xml_file, verbose=False + ) + + if is_valid is None: + skipped_count += 1 + continue + elif is_valid and not new_file_errors: + valid_count += 1 + continue + elif is_valid: + original_error_count += 1 + valid_count += 1 + continue + + new_errors.append(f" {relative_path}: {len(new_file_errors)} new error(s)") + for error in list(new_file_errors)[:3]: + new_errors.append( + f" - {error[:250]}..." if len(error) > 250 else f" - {error}" + ) + + if self.verbose: + print(f"Validated {len(self.xml_files)} files:") + print(f" - Valid: {valid_count}") + print(f" - Skipped (no schema): {skipped_count}") + if original_error_count: + print(f" - With original errors (ignored): {original_error_count}") + print( + f" - With NEW errors: {len(new_errors) > 0 and len([e for e in new_errors if not e.startswith(' ')]) or 0}" + ) + + if new_errors: + print("\nFAILED - Found NEW validation errors:") + for error in new_errors: + print(error) + return False + else: + if self.verbose: + print("\nPASSED - No new XSD validation errors introduced") + return True + + def _get_schema_path(self, xml_file): + if xml_file.name in self.SCHEMA_MAPPINGS: + return self.schemas_dir / self.SCHEMA_MAPPINGS[xml_file.name] + + if xml_file.suffix == ".rels": + return self.schemas_dir / self.SCHEMA_MAPPINGS[".rels"] + + if "charts/" in str(xml_file) and xml_file.name.startswith("chart"): + return self.schemas_dir / self.SCHEMA_MAPPINGS["chart"] + + if "theme/" in str(xml_file) and xml_file.name.startswith("theme"): + return self.schemas_dir / self.SCHEMA_MAPPINGS["theme"] + + if xml_file.parent.name in self.MAIN_CONTENT_FOLDERS: + return self.schemas_dir / self.SCHEMA_MAPPINGS[xml_file.parent.name] + + return None + + def _clean_ignorable_namespaces(self, xml_doc): + xml_string = lxml.etree.tostring(xml_doc, encoding="unicode") + xml_copy = lxml.etree.fromstring(xml_string) + + for elem in xml_copy.iter(): + attrs_to_remove = [] + + for attr in elem.attrib: + if "{" in attr: + ns = attr.split("}")[0][1:] + if ns not in self.OOXML_NAMESPACES: + attrs_to_remove.append(attr) + + for attr in attrs_to_remove: + del elem.attrib[attr] + + self._remove_ignorable_elements(xml_copy) + + return lxml.etree.ElementTree(xml_copy) + + def _remove_ignorable_elements(self, root): + elements_to_remove = [] + + for elem in list(root): + if not hasattr(elem, "tag") or callable(elem.tag): + continue + + tag_str = str(elem.tag) + if tag_str.startswith("{"): + ns = tag_str.split("}")[0][1:] + if ns not in self.OOXML_NAMESPACES: + elements_to_remove.append(elem) + continue + + self._remove_ignorable_elements(elem) + + for elem in elements_to_remove: + root.remove(elem) + + def _preprocess_for_mc_ignorable(self, xml_doc): + root = xml_doc.getroot() + + if f"{{{self.MC_NAMESPACE}}}Ignorable" in root.attrib: + del root.attrib[f"{{{self.MC_NAMESPACE}}}Ignorable"] + + return xml_doc + + def _validate_single_file_xsd(self, xml_file, base_path): + schema_path = self._get_schema_path(xml_file) + if not schema_path: + return None, None + + try: + with open(schema_path, "rb") as xsd_file: + parser = lxml.etree.XMLParser() + xsd_doc = lxml.etree.parse( + xsd_file, parser=parser, base_url=str(schema_path) + ) + schema = lxml.etree.XMLSchema(xsd_doc) + + with open(xml_file, "r") as f: + xml_doc = lxml.etree.parse(f) + + xml_doc, _ = self._remove_template_tags_from_text_nodes(xml_doc) + xml_doc = self._preprocess_for_mc_ignorable(xml_doc) + + relative_path = xml_file.relative_to(base_path) + if ( + relative_path.parts + and relative_path.parts[0] in self.MAIN_CONTENT_FOLDERS + ): + xml_doc = self._clean_ignorable_namespaces(xml_doc) + + if schema.validate(xml_doc): + return True, set() + else: + errors = set() + for error in schema.error_log: + errors.add(error.message) + return False, errors + + except Exception as e: + return False, {str(e)} + + def _get_original_file_errors(self, xml_file): + if self.original_file is None: + return set() + + import tempfile + import zipfile + + xml_file = Path(xml_file).resolve() + unpacked_dir = self.unpacked_dir.resolve() + relative_path = xml_file.relative_to(unpacked_dir) + + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + with zipfile.ZipFile(self.original_file, "r") as zip_ref: + zip_ref.extractall(temp_path) + + original_xml_file = temp_path / relative_path + + if not original_xml_file.exists(): + return set() + + is_valid, errors = self._validate_single_file_xsd( + original_xml_file, temp_path + ) + return errors if errors else set() + + def _remove_template_tags_from_text_nodes(self, xml_doc): + warnings = [] + template_pattern = re.compile(r"\{\{[^}]*\}\}") + + xml_string = lxml.etree.tostring(xml_doc, encoding="unicode") + xml_copy = lxml.etree.fromstring(xml_string) + + def process_text_content(text, content_type): + if not text: + return text + matches = list(template_pattern.finditer(text)) + if matches: + for match in matches: + warnings.append( + f"Found template tag in {content_type}: {match.group()}" + ) + return template_pattern.sub("", text) + return text + + for elem in xml_copy.iter(): + if not hasattr(elem, "tag") or callable(elem.tag): + continue + tag_str = str(elem.tag) + if tag_str.endswith("}t") or tag_str == "t": + continue + + elem.text = process_text_content(elem.text, "text content") + elem.tail = process_text_content(elem.tail, "tail content") + + return lxml.etree.ElementTree(xml_copy), warnings + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/.claude/skills/pptx/scripts/office/validators/docx.py b/.claude/skills/pptx/scripts/office/validators/docx.py new file mode 100644 index 0000000..fec405e --- /dev/null +++ b/.claude/skills/pptx/scripts/office/validators/docx.py @@ -0,0 +1,446 @@ +""" +Validator for Word document XML files against XSD schemas. +""" + +import random +import re +import tempfile +import zipfile + +import defusedxml.minidom +import lxml.etree + +from .base import BaseSchemaValidator + + +class DOCXSchemaValidator(BaseSchemaValidator): + + WORD_2006_NAMESPACE = "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + W14_NAMESPACE = "http://schemas.microsoft.com/office/word/2010/wordml" + W16CID_NAMESPACE = "http://schemas.microsoft.com/office/word/2016/wordml/cid" + + ELEMENT_RELATIONSHIP_TYPES = {} + + def validate(self): + if not self.validate_xml(): + return False + + all_valid = True + if not self.validate_namespaces(): + all_valid = False + + if not self.validate_unique_ids(): + all_valid = False + + if not self.validate_file_references(): + all_valid = False + + if not self.validate_content_types(): + all_valid = False + + if not self.validate_against_xsd(): + all_valid = False + + if not self.validate_whitespace_preservation(): + all_valid = False + + if not self.validate_deletions(): + all_valid = False + + if not self.validate_insertions(): + all_valid = False + + if not self.validate_all_relationship_ids(): + all_valid = False + + if not self.validate_id_constraints(): + all_valid = False + + if not self.validate_comment_markers(): + all_valid = False + + self.compare_paragraph_counts() + + return all_valid + + def validate_whitespace_preservation(self): + errors = [] + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + + for elem in root.iter(f"{{{self.WORD_2006_NAMESPACE}}}t"): + if elem.text: + text = elem.text + if re.search(r"^[ \t\n\r]", text) or re.search( + r"[ \t\n\r]$", text + ): + xml_space_attr = f"{{{self.XML_NAMESPACE}}}space" + if ( + xml_space_attr not in elem.attrib + or elem.attrib[xml_space_attr] != "preserve" + ): + text_preview = ( + repr(text)[:50] + "..." + if len(repr(text)) > 50 + else repr(text) + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: w:t element with whitespace missing xml:space='preserve': {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} whitespace preservation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All whitespace is properly preserved") + return True + + def validate_deletions(self): + errors = [] + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + namespaces = {"w": self.WORD_2006_NAMESPACE} + + for t_elem in root.xpath(".//w:del//w:t", namespaces=namespaces): + if t_elem.text: + text_preview = ( + repr(t_elem.text)[:50] + "..." + if len(repr(t_elem.text)) > 50 + else repr(t_elem.text) + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {t_elem.sourceline}: found within : {text_preview}" + ) + + for instr_elem in root.xpath( + ".//w:del//w:instrText", namespaces=namespaces + ): + text_preview = ( + repr(instr_elem.text or "")[:50] + "..." + if len(repr(instr_elem.text or "")) > 50 + else repr(instr_elem.text or "") + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {instr_elem.sourceline}: found within (use ): {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} deletion validation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - No w:t elements found within w:del elements") + return True + + def count_paragraphs_in_unpacked(self): + count = 0 + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + paragraphs = root.findall(f".//{{{self.WORD_2006_NAMESPACE}}}p") + count = len(paragraphs) + except Exception as e: + print(f"Error counting paragraphs in unpacked document: {e}") + + return count + + def count_paragraphs_in_original(self): + original = self.original_file + if original is None: + return 0 + + count = 0 + + try: + with tempfile.TemporaryDirectory() as temp_dir: + with zipfile.ZipFile(original, "r") as zip_ref: + zip_ref.extractall(temp_dir) + + doc_xml_path = temp_dir + "/word/document.xml" + root = lxml.etree.parse(doc_xml_path).getroot() + + paragraphs = root.findall(f".//{{{self.WORD_2006_NAMESPACE}}}p") + count = len(paragraphs) + + except Exception as e: + print(f"Error counting paragraphs in original document: {e}") + + return count + + def validate_insertions(self): + errors = [] + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + namespaces = {"w": self.WORD_2006_NAMESPACE} + + invalid_elements = root.xpath( + ".//w:ins//w:delText[not(ancestor::w:del)]", namespaces=namespaces + ) + + for elem in invalid_elements: + text_preview = ( + repr(elem.text or "")[:50] + "..." + if len(repr(elem.text or "")) > 50 + else repr(elem.text or "") + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: within : {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} insertion validation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - No w:delText elements within w:ins elements") + return True + + def compare_paragraph_counts(self): + original_count = self.count_paragraphs_in_original() + new_count = self.count_paragraphs_in_unpacked() + + diff = new_count - original_count + diff_str = f"+{diff}" if diff > 0 else str(diff) + print(f"\nParagraphs: {original_count} → {new_count} ({diff_str})") + + def _parse_id_value(self, val: str, base: int = 16) -> int: + return int(val, base) + + def validate_id_constraints(self): + errors = [] + para_id_attr = f"{{{self.W14_NAMESPACE}}}paraId" + durable_id_attr = f"{{{self.W16CID_NAMESPACE}}}durableId" + + for xml_file in self.xml_files: + try: + for elem in lxml.etree.parse(str(xml_file)).iter(): + if val := elem.get(para_id_attr): + if self._parse_id_value(val, base=16) >= 0x80000000: + errors.append( + f" {xml_file.name}:{elem.sourceline}: paraId={val} >= 0x80000000" + ) + + if val := elem.get(durable_id_attr): + if xml_file.name == "numbering.xml": + try: + if self._parse_id_value(val, base=10) >= 0x7FFFFFFF: + errors.append( + f" {xml_file.name}:{elem.sourceline}: " + f"durableId={val} >= 0x7FFFFFFF" + ) + except ValueError: + errors.append( + f" {xml_file.name}:{elem.sourceline}: " + f"durableId={val} must be decimal in numbering.xml" + ) + else: + if self._parse_id_value(val, base=16) >= 0x7FFFFFFF: + errors.append( + f" {xml_file.name}:{elem.sourceline}: " + f"durableId={val} >= 0x7FFFFFFF" + ) + except Exception: + pass + + if errors: + print(f"FAILED - {len(errors)} ID constraint violations:") + for e in errors: + print(e) + elif self.verbose: + print("PASSED - All paraId/durableId values within constraints") + return not errors + + def validate_comment_markers(self): + errors = [] + + document_xml = None + comments_xml = None + for xml_file in self.xml_files: + if xml_file.name == "document.xml" and "word" in str(xml_file): + document_xml = xml_file + elif xml_file.name == "comments.xml": + comments_xml = xml_file + + if not document_xml: + if self.verbose: + print("PASSED - No document.xml found (skipping comment validation)") + return True + + try: + doc_root = lxml.etree.parse(str(document_xml)).getroot() + namespaces = {"w": self.WORD_2006_NAMESPACE} + + range_starts = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in doc_root.xpath( + ".//w:commentRangeStart", namespaces=namespaces + ) + } + range_ends = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in doc_root.xpath( + ".//w:commentRangeEnd", namespaces=namespaces + ) + } + references = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in doc_root.xpath( + ".//w:commentReference", namespaces=namespaces + ) + } + + orphaned_ends = range_ends - range_starts + for comment_id in sorted( + orphaned_ends, key=lambda x: int(x) if x and x.isdigit() else 0 + ): + errors.append( + f' document.xml: commentRangeEnd id="{comment_id}" has no matching commentRangeStart' + ) + + orphaned_starts = range_starts - range_ends + for comment_id in sorted( + orphaned_starts, key=lambda x: int(x) if x and x.isdigit() else 0 + ): + errors.append( + f' document.xml: commentRangeStart id="{comment_id}" has no matching commentRangeEnd' + ) + + comment_ids = set() + if comments_xml and comments_xml.exists(): + comments_root = lxml.etree.parse(str(comments_xml)).getroot() + comment_ids = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in comments_root.xpath( + ".//w:comment", namespaces=namespaces + ) + } + + marker_ids = range_starts | range_ends | references + invalid_refs = marker_ids - comment_ids + for comment_id in sorted( + invalid_refs, key=lambda x: int(x) if x and x.isdigit() else 0 + ): + if comment_id: + errors.append( + f' document.xml: marker id="{comment_id}" references non-existent comment' + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append(f" Error parsing XML: {e}") + + if errors: + print(f"FAILED - {len(errors)} comment marker violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All comment markers properly paired") + return True + + def repair(self) -> int: + repairs = super().repair() + repairs += self.repair_durableId() + return repairs + + def repair_durableId(self) -> int: + repairs = 0 + + for xml_file in self.xml_files: + try: + content = xml_file.read_text(encoding="utf-8") + dom = defusedxml.minidom.parseString(content) + modified = False + + for elem in dom.getElementsByTagName("*"): + if not elem.hasAttribute("w16cid:durableId"): + continue + + durable_id = elem.getAttribute("w16cid:durableId") + needs_repair = False + + if xml_file.name == "numbering.xml": + try: + needs_repair = ( + self._parse_id_value(durable_id, base=10) >= 0x7FFFFFFF + ) + except ValueError: + needs_repair = True + else: + try: + needs_repair = ( + self._parse_id_value(durable_id, base=16) >= 0x7FFFFFFF + ) + except ValueError: + needs_repair = True + + if needs_repair: + value = random.randint(1, 0x7FFFFFFE) + if xml_file.name == "numbering.xml": + new_id = str(value) + else: + new_id = f"{value:08X}" + + elem.setAttribute("w16cid:durableId", new_id) + print( + f" Repaired: {xml_file.name}: durableId {durable_id} → {new_id}" + ) + repairs += 1 + modified = True + + if modified: + xml_file.write_bytes(dom.toxml(encoding="UTF-8")) + + except Exception: + pass + + return repairs + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/.claude/skills/pptx/scripts/office/validators/pptx.py b/.claude/skills/pptx/scripts/office/validators/pptx.py new file mode 100644 index 0000000..09842aa --- /dev/null +++ b/.claude/skills/pptx/scripts/office/validators/pptx.py @@ -0,0 +1,275 @@ +""" +Validator for PowerPoint presentation XML files against XSD schemas. +""" + +import re + +from .base import BaseSchemaValidator + + +class PPTXSchemaValidator(BaseSchemaValidator): + + PRESENTATIONML_NAMESPACE = ( + "http://schemas.openxmlformats.org/presentationml/2006/main" + ) + + ELEMENT_RELATIONSHIP_TYPES = { + "sldid": "slide", + "sldmasterid": "slidemaster", + "notesmasterid": "notesmaster", + "sldlayoutid": "slidelayout", + "themeid": "theme", + "tablestyleid": "tablestyles", + } + + def validate(self): + if not self.validate_xml(): + return False + + all_valid = True + if not self.validate_namespaces(): + all_valid = False + + if not self.validate_unique_ids(): + all_valid = False + + if not self.validate_uuid_ids(): + all_valid = False + + if not self.validate_file_references(): + all_valid = False + + if not self.validate_slide_layout_ids(): + all_valid = False + + if not self.validate_content_types(): + all_valid = False + + if not self.validate_against_xsd(): + all_valid = False + + if not self.validate_notes_slide_references(): + all_valid = False + + if not self.validate_all_relationship_ids(): + all_valid = False + + if not self.validate_no_duplicate_slide_layouts(): + all_valid = False + + return all_valid + + def validate_uuid_ids(self): + import lxml.etree + + errors = [] + uuid_pattern = re.compile( + r"^[\{\(]?[0-9A-Fa-f]{8}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{12}[\}\)]?$" + ) + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + + for elem in root.iter(): + for attr, value in elem.attrib.items(): + attr_name = attr.split("}")[-1].lower() + if attr_name == "id" or attr_name.endswith("id"): + if self._looks_like_uuid(value): + if not uuid_pattern.match(value): + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: ID '{value}' appears to be a UUID but contains invalid hex characters" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} UUID ID validation errors:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All UUID-like IDs contain valid hex values") + return True + + def _looks_like_uuid(self, value): + clean_value = value.strip("{}()").replace("-", "") + return len(clean_value) == 32 and all(c.isalnum() for c in clean_value) + + def validate_slide_layout_ids(self): + import lxml.etree + + errors = [] + + slide_masters = list(self.unpacked_dir.glob("ppt/slideMasters/*.xml")) + + if not slide_masters: + if self.verbose: + print("PASSED - No slide masters found") + return True + + for slide_master in slide_masters: + try: + root = lxml.etree.parse(str(slide_master)).getroot() + + rels_file = slide_master.parent / "_rels" / f"{slide_master.name}.rels" + + if not rels_file.exists(): + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: " + f"Missing relationships file: {rels_file.relative_to(self.unpacked_dir)}" + ) + continue + + rels_root = lxml.etree.parse(str(rels_file)).getroot() + + valid_layout_rids = set() + for rel in rels_root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rel_type = rel.get("Type", "") + if "slideLayout" in rel_type: + valid_layout_rids.add(rel.get("Id")) + + for sld_layout_id in root.findall( + f".//{{{self.PRESENTATIONML_NAMESPACE}}}sldLayoutId" + ): + r_id = sld_layout_id.get( + f"{{{self.OFFICE_RELATIONSHIPS_NAMESPACE}}}id" + ) + layout_id = sld_layout_id.get("id") + + if r_id and r_id not in valid_layout_rids: + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: " + f"Line {sld_layout_id.sourceline}: sldLayoutId with id='{layout_id}' " + f"references r:id='{r_id}' which is not found in slide layout relationships" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} slide layout ID validation errors:") + for error in errors: + print(error) + print( + "Remove invalid references or add missing slide layouts to the relationships file." + ) + return False + else: + if self.verbose: + print("PASSED - All slide layout IDs reference valid slide layouts") + return True + + def validate_no_duplicate_slide_layouts(self): + import lxml.etree + + errors = [] + slide_rels_files = list(self.unpacked_dir.glob("ppt/slides/_rels/*.xml.rels")) + + for rels_file in slide_rels_files: + try: + root = lxml.etree.parse(str(rels_file)).getroot() + + layout_rels = [ + rel + for rel in root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ) + if "slideLayout" in rel.get("Type", "") + ] + + if len(layout_rels) > 1: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: has {len(layout_rels)} slideLayout references" + ) + + except Exception as e: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print("FAILED - Found slides with duplicate slideLayout references:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All slides have exactly one slideLayout reference") + return True + + def validate_notes_slide_references(self): + import lxml.etree + + errors = [] + notes_slide_references = {} + + slide_rels_files = list(self.unpacked_dir.glob("ppt/slides/_rels/*.xml.rels")) + + if not slide_rels_files: + if self.verbose: + print("PASSED - No slide relationship files found") + return True + + for rels_file in slide_rels_files: + try: + root = lxml.etree.parse(str(rels_file)).getroot() + + for rel in root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rel_type = rel.get("Type", "") + if "notesSlide" in rel_type: + target = rel.get("Target", "") + if target: + normalized_target = target.replace("../", "") + + slide_name = rels_file.stem.replace( + ".xml", "" + ) + + if normalized_target not in notes_slide_references: + notes_slide_references[normalized_target] = [] + notes_slide_references[normalized_target].append( + (slide_name, rels_file) + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + for target, references in notes_slide_references.items(): + if len(references) > 1: + slide_names = [ref[0] for ref in references] + errors.append( + f" Notes slide '{target}' is referenced by multiple slides: {', '.join(slide_names)}" + ) + for slide_name, rels_file in references: + errors.append(f" - {rels_file.relative_to(self.unpacked_dir)}") + + if errors: + print( + f"FAILED - Found {len([e for e in errors if not e.startswith(' ')])} notes slide reference validation errors:" + ) + for error in errors: + print(error) + print("Each slide may optionally have its own slide file.") + return False + else: + if self.verbose: + print("PASSED - All notes slide references are unique") + return True + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/.claude/skills/pptx/scripts/office/validators/redlining.py b/.claude/skills/pptx/scripts/office/validators/redlining.py new file mode 100644 index 0000000..71c81b6 --- /dev/null +++ b/.claude/skills/pptx/scripts/office/validators/redlining.py @@ -0,0 +1,247 @@ +""" +Validator for tracked changes in Word documents. +""" + +import subprocess +import tempfile +import zipfile +from pathlib import Path + + +class RedliningValidator: + + def __init__(self, unpacked_dir, original_docx, verbose=False, author="Claude"): + self.unpacked_dir = Path(unpacked_dir) + self.original_docx = Path(original_docx) + self.verbose = verbose + self.author = author + self.namespaces = { + "w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + } + + def repair(self) -> int: + return 0 + + def validate(self): + modified_file = self.unpacked_dir / "word" / "document.xml" + if not modified_file.exists(): + print(f"FAILED - Modified document.xml not found at {modified_file}") + return False + + try: + import xml.etree.ElementTree as ET + + tree = ET.parse(modified_file) + root = tree.getroot() + + del_elements = root.findall(".//w:del", self.namespaces) + ins_elements = root.findall(".//w:ins", self.namespaces) + + author_del_elements = [ + elem + for elem in del_elements + if elem.get(f"{{{self.namespaces['w']}}}author") == self.author + ] + author_ins_elements = [ + elem + for elem in ins_elements + if elem.get(f"{{{self.namespaces['w']}}}author") == self.author + ] + + if not author_del_elements and not author_ins_elements: + if self.verbose: + print(f"PASSED - No tracked changes by {self.author} found.") + return True + + except Exception: + pass + + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + try: + with zipfile.ZipFile(self.original_docx, "r") as zip_ref: + zip_ref.extractall(temp_path) + except Exception as e: + print(f"FAILED - Error unpacking original docx: {e}") + return False + + original_file = temp_path / "word" / "document.xml" + if not original_file.exists(): + print( + f"FAILED - Original document.xml not found in {self.original_docx}" + ) + return False + + try: + import xml.etree.ElementTree as ET + + modified_tree = ET.parse(modified_file) + modified_root = modified_tree.getroot() + original_tree = ET.parse(original_file) + original_root = original_tree.getroot() + except ET.ParseError as e: + print(f"FAILED - Error parsing XML files: {e}") + return False + + self._remove_author_tracked_changes(original_root) + self._remove_author_tracked_changes(modified_root) + + modified_text = self._extract_text_content(modified_root) + original_text = self._extract_text_content(original_root) + + if modified_text != original_text: + error_message = self._generate_detailed_diff( + original_text, modified_text + ) + print(error_message) + return False + + if self.verbose: + print(f"PASSED - All changes by {self.author} are properly tracked") + return True + + def _generate_detailed_diff(self, original_text, modified_text): + error_parts = [ + f"FAILED - Document text doesn't match after removing {self.author}'s tracked changes", + "", + "Likely causes:", + " 1. Modified text inside another author's or tags", + " 2. Made edits without proper tracked changes", + " 3. Didn't nest inside when deleting another's insertion", + "", + "For pre-redlined documents, use correct patterns:", + " - To reject another's INSERTION: Nest inside their ", + " - To restore another's DELETION: Add new AFTER their ", + "", + ] + + git_diff = self._get_git_word_diff(original_text, modified_text) + if git_diff: + error_parts.extend(["Differences:", "============", git_diff]) + else: + error_parts.append("Unable to generate word diff (git not available)") + + return "\n".join(error_parts) + + def _get_git_word_diff(self, original_text, modified_text): + try: + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + original_file = temp_path / "original.txt" + modified_file = temp_path / "modified.txt" + + original_file.write_text(original_text, encoding="utf-8") + modified_file.write_text(modified_text, encoding="utf-8") + + result = subprocess.run( + [ + "git", + "diff", + "--word-diff=plain", + "--word-diff-regex=.", + "-U0", + "--no-index", + str(original_file), + str(modified_file), + ], + capture_output=True, + text=True, + ) + + if result.stdout.strip(): + lines = result.stdout.split("\n") + content_lines = [] + in_content = False + for line in lines: + if line.startswith("@@"): + in_content = True + continue + if in_content and line.strip(): + content_lines.append(line) + + if content_lines: + return "\n".join(content_lines) + + result = subprocess.run( + [ + "git", + "diff", + "--word-diff=plain", + "-U0", + "--no-index", + str(original_file), + str(modified_file), + ], + capture_output=True, + text=True, + ) + + if result.stdout.strip(): + lines = result.stdout.split("\n") + content_lines = [] + in_content = False + for line in lines: + if line.startswith("@@"): + in_content = True + continue + if in_content and line.strip(): + content_lines.append(line) + return "\n".join(content_lines) + + except (subprocess.CalledProcessError, FileNotFoundError, Exception): + pass + + return None + + def _remove_author_tracked_changes(self, root): + ins_tag = f"{{{self.namespaces['w']}}}ins" + del_tag = f"{{{self.namespaces['w']}}}del" + author_attr = f"{{{self.namespaces['w']}}}author" + + for parent in root.iter(): + to_remove = [] + for child in parent: + if child.tag == ins_tag and child.get(author_attr) == self.author: + to_remove.append(child) + for elem in to_remove: + parent.remove(elem) + + deltext_tag = f"{{{self.namespaces['w']}}}delText" + t_tag = f"{{{self.namespaces['w']}}}t" + + for parent in root.iter(): + to_process = [] + for child in parent: + if child.tag == del_tag and child.get(author_attr) == self.author: + to_process.append((child, list(parent).index(child))) + + for del_elem, del_index in reversed(to_process): + for elem in del_elem.iter(): + if elem.tag == deltext_tag: + elem.tag = t_tag + + for child in reversed(list(del_elem)): + parent.insert(del_index, child) + parent.remove(del_elem) + + def _extract_text_content(self, root): + p_tag = f"{{{self.namespaces['w']}}}p" + t_tag = f"{{{self.namespaces['w']}}}t" + + paragraphs = [] + for p_elem in root.findall(f".//{p_tag}"): + text_parts = [] + for t_elem in p_elem.findall(f".//{t_tag}"): + if t_elem.text: + text_parts.append(t_elem.text) + paragraph_text = "".join(text_parts) + if paragraph_text: + paragraphs.append(paragraph_text) + + return "\n".join(paragraphs) + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/.claude/skills/pptx/scripts/thumbnail.py b/.claude/skills/pptx/scripts/thumbnail.py new file mode 100644 index 0000000..edcbdc0 --- /dev/null +++ b/.claude/skills/pptx/scripts/thumbnail.py @@ -0,0 +1,289 @@ +"""Create thumbnail grids from PowerPoint presentation slides. + +Creates a grid layout of slide thumbnails for quick visual analysis. +Labels each thumbnail with its XML filename (e.g., slide1.xml). +Hidden slides are shown with a placeholder pattern. + +Usage: + python thumbnail.py input.pptx [output_prefix] [--cols N] + +Examples: + python thumbnail.py presentation.pptx + # Creates: thumbnails.jpg + + python thumbnail.py template.pptx grid --cols 4 + # Creates: grid.jpg (or grid-1.jpg, grid-2.jpg for large decks) +""" + +import argparse +import subprocess +import sys +import tempfile +import zipfile +from pathlib import Path + +import defusedxml.minidom +from office.soffice import get_soffice_env +from PIL import Image, ImageDraw, ImageFont + +THUMBNAIL_WIDTH = 300 +CONVERSION_DPI = 100 +MAX_COLS = 6 +DEFAULT_COLS = 3 +JPEG_QUALITY = 95 +GRID_PADDING = 20 +BORDER_WIDTH = 2 +FONT_SIZE_RATIO = 0.10 +LABEL_PADDING_RATIO = 0.4 + + +def main(): + parser = argparse.ArgumentParser( + description="Create thumbnail grids from PowerPoint slides." + ) + parser.add_argument("input", help="Input PowerPoint file (.pptx)") + parser.add_argument( + "output_prefix", + nargs="?", + default="thumbnails", + help="Output prefix for image files (default: thumbnails)", + ) + parser.add_argument( + "--cols", + type=int, + default=DEFAULT_COLS, + help=f"Number of columns (default: {DEFAULT_COLS}, max: {MAX_COLS})", + ) + + args = parser.parse_args() + + cols = min(args.cols, MAX_COLS) + if args.cols > MAX_COLS: + print(f"Warning: Columns limited to {MAX_COLS}") + + input_path = Path(args.input) + if not input_path.exists() or input_path.suffix.lower() != ".pptx": + print(f"Error: Invalid PowerPoint file: {args.input}", file=sys.stderr) + sys.exit(1) + + output_path = Path(f"{args.output_prefix}.jpg") + + try: + slide_info = get_slide_info(input_path) + + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + visible_images = convert_to_images(input_path, temp_path) + + if not visible_images and not any(s["hidden"] for s in slide_info): + print("Error: No slides found", file=sys.stderr) + sys.exit(1) + + slides = build_slide_list(slide_info, visible_images, temp_path) + + grid_files = create_grids(slides, cols, THUMBNAIL_WIDTH, output_path) + + print(f"Created {len(grid_files)} grid(s):") + for grid_file in grid_files: + print(f" {grid_file}") + + except Exception as e: + print(f"Error: {e}", file=sys.stderr) + sys.exit(1) + + +def get_slide_info(pptx_path: Path) -> list[dict]: + with zipfile.ZipFile(pptx_path, "r") as zf: + rels_content = zf.read("ppt/_rels/presentation.xml.rels").decode("utf-8") + rels_dom = defusedxml.minidom.parseString(rels_content) + + rid_to_slide = {} + for rel in rels_dom.getElementsByTagName("Relationship"): + rid = rel.getAttribute("Id") + target = rel.getAttribute("Target") + rel_type = rel.getAttribute("Type") + if "slide" in rel_type and target.startswith("slides/"): + rid_to_slide[rid] = target.replace("slides/", "") + + pres_content = zf.read("ppt/presentation.xml").decode("utf-8") + pres_dom = defusedxml.minidom.parseString(pres_content) + + slides = [] + for sld_id in pres_dom.getElementsByTagName("p:sldId"): + rid = sld_id.getAttribute("r:id") + if rid in rid_to_slide: + hidden = sld_id.getAttribute("show") == "0" + slides.append({"name": rid_to_slide[rid], "hidden": hidden}) + + return slides + + +def build_slide_list( + slide_info: list[dict], + visible_images: list[Path], + temp_dir: Path, +) -> list[tuple[Path, str]]: + if visible_images: + with Image.open(visible_images[0]) as img: + placeholder_size = img.size + else: + placeholder_size = (1920, 1080) + + slides = [] + visible_idx = 0 + + for info in slide_info: + if info["hidden"]: + placeholder_path = temp_dir / f"hidden-{info['name']}.jpg" + placeholder_img = create_hidden_placeholder(placeholder_size) + placeholder_img.save(placeholder_path, "JPEG") + slides.append((placeholder_path, f"{info['name']} (hidden)")) + else: + if visible_idx < len(visible_images): + slides.append((visible_images[visible_idx], info["name"])) + visible_idx += 1 + + return slides + + +def create_hidden_placeholder(size: tuple[int, int]) -> Image.Image: + img = Image.new("RGB", size, color="#F0F0F0") + draw = ImageDraw.Draw(img) + line_width = max(5, min(size) // 100) + draw.line([(0, 0), size], fill="#CCCCCC", width=line_width) + draw.line([(size[0], 0), (0, size[1])], fill="#CCCCCC", width=line_width) + return img + + +def convert_to_images(pptx_path: Path, temp_dir: Path) -> list[Path]: + pdf_path = temp_dir / f"{pptx_path.stem}.pdf" + + result = subprocess.run( + [ + "soffice", + "--headless", + "--convert-to", + "pdf", + "--outdir", + str(temp_dir), + str(pptx_path), + ], + capture_output=True, + text=True, + env=get_soffice_env(), + ) + if result.returncode != 0 or not pdf_path.exists(): + raise RuntimeError("PDF conversion failed") + + result = subprocess.run( + [ + "pdftoppm", + "-jpeg", + "-r", + str(CONVERSION_DPI), + str(pdf_path), + str(temp_dir / "slide"), + ], + capture_output=True, + text=True, + ) + if result.returncode != 0: + raise RuntimeError("Image conversion failed") + + return sorted(temp_dir.glob("slide-*.jpg")) + + +def create_grids( + slides: list[tuple[Path, str]], + cols: int, + width: int, + output_path: Path, +) -> list[str]: + max_per_grid = cols * (cols + 1) + grid_files = [] + + for chunk_idx, start_idx in enumerate(range(0, len(slides), max_per_grid)): + end_idx = min(start_idx + max_per_grid, len(slides)) + chunk_slides = slides[start_idx:end_idx] + + grid = create_grid(chunk_slides, cols, width) + + if len(slides) <= max_per_grid: + grid_filename = output_path + else: + stem = output_path.stem + suffix = output_path.suffix + grid_filename = output_path.parent / f"{stem}-{chunk_idx + 1}{suffix}" + + grid_filename.parent.mkdir(parents=True, exist_ok=True) + grid.save(str(grid_filename), quality=JPEG_QUALITY) + grid_files.append(str(grid_filename)) + + return grid_files + + +def create_grid( + slides: list[tuple[Path, str]], + cols: int, + width: int, +) -> Image.Image: + font_size = int(width * FONT_SIZE_RATIO) + label_padding = int(font_size * LABEL_PADDING_RATIO) + + with Image.open(slides[0][0]) as img: + aspect = img.height / img.width + height = int(width * aspect) + + rows = (len(slides) + cols - 1) // cols + grid_w = cols * width + (cols + 1) * GRID_PADDING + grid_h = rows * (height + font_size + label_padding * 2) + (rows + 1) * GRID_PADDING + + grid = Image.new("RGB", (grid_w, grid_h), "white") + draw = ImageDraw.Draw(grid) + + try: + font = ImageFont.load_default(size=font_size) + except Exception: + font = ImageFont.load_default() + + for i, (img_path, slide_name) in enumerate(slides): + row, col = i // cols, i % cols + x = col * width + (col + 1) * GRID_PADDING + y_base = ( + row * (height + font_size + label_padding * 2) + (row + 1) * GRID_PADDING + ) + + label = slide_name + bbox = draw.textbbox((0, 0), label, font=font) + text_w = bbox[2] - bbox[0] + draw.text( + (x + (width - text_w) // 2, y_base + label_padding), + label, + fill="black", + font=font, + ) + + y_thumbnail = y_base + label_padding + font_size + label_padding + + with Image.open(img_path) as img: + img.thumbnail((width, height), Image.Resampling.LANCZOS) + w, h = img.size + tx = x + (width - w) // 2 + ty = y_thumbnail + (height - h) // 2 + grid.paste(img, (tx, ty)) + + if BORDER_WIDTH > 0: + draw.rectangle( + [ + (tx - BORDER_WIDTH, ty - BORDER_WIDTH), + (tx + w + BORDER_WIDTH - 1, ty + h + BORDER_WIDTH - 1), + ], + outline="gray", + width=BORDER_WIDTH, + ) + + return grid + + +if __name__ == "__main__": + main() diff --git a/.claude/skills/skill-creator/LICENSE.txt b/.claude/skills/skill-creator/LICENSE.txt new file mode 100644 index 0000000..7a4a3ea --- /dev/null +++ b/.claude/skills/skill-creator/LICENSE.txt @@ -0,0 +1,202 @@ + + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [yyyy] [name of copyright owner] + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. \ No newline at end of file diff --git a/.claude/skills/skill-creator/SKILL.md b/.claude/skills/skill-creator/SKILL.md new file mode 100644 index 0000000..b7f8659 --- /dev/null +++ b/.claude/skills/skill-creator/SKILL.md @@ -0,0 +1,356 @@ +--- +name: skill-creator +description: Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. +license: Complete terms in LICENSE.txt +--- + +# Skill Creator + +This skill provides guidance for creating effective skills. + +## About Skills + +Skills are modular, self-contained packages that extend Claude's capabilities by providing +specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific +domains or tasks—they transform Claude from a general-purpose agent into a specialized agent +equipped with procedural knowledge that no model can fully possess. + +### What Skills Provide + +1. Specialized workflows - Multi-step procedures for specific domains +2. Tool integrations - Instructions for working with specific file formats or APIs +3. Domain expertise - Company-specific knowledge, schemas, business logic +4. Bundled resources - Scripts, references, and assets for complex and repetitive tasks + +## Core Principles + +### Concise is Key + +The context window is a public good. Skills share the context window with everything else Claude needs: system prompt, conversation history, other Skills' metadata, and the actual user request. + +**Default assumption: Claude is already very smart.** Only add context Claude doesn't already have. Challenge each piece of information: "Does Claude really need this explanation?" and "Does this paragraph justify its token cost?" + +Prefer concise examples over verbose explanations. + +### Set Appropriate Degrees of Freedom + +Match the level of specificity to the task's fragility and variability: + +**High freedom (text-based instructions)**: Use when multiple approaches are valid, decisions depend on context, or heuristics guide the approach. + +**Medium freedom (pseudocode or scripts with parameters)**: Use when a preferred pattern exists, some variation is acceptable, or configuration affects behavior. + +**Low freedom (specific scripts, few parameters)**: Use when operations are fragile and error-prone, consistency is critical, or a specific sequence must be followed. + +Think of Claude as exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom). + +### Anatomy of a Skill + +Every skill consists of a required SKILL.md file and optional bundled resources: + +``` +skill-name/ +├── SKILL.md (required) +│ ├── YAML frontmatter metadata (required) +│ │ ├── name: (required) +│ │ └── description: (required) +│ └── Markdown instructions (required) +└── Bundled Resources (optional) + ├── scripts/ - Executable code (Python/Bash/etc.) + ├── references/ - Documentation intended to be loaded into context as needed + └── assets/ - Files used in output (templates, icons, fonts, etc.) +``` + +#### SKILL.md (required) + +Every SKILL.md consists of: + +- **Frontmatter** (YAML): Contains `name` and `description` fields. These are the only fields that Claude reads to determine when the skill gets used, thus it is very important to be clear and comprehensive in describing what the skill is, and when it should be used. +- **Body** (Markdown): Instructions and guidance for using the skill. Only loaded AFTER the skill triggers (if at all). + +#### Bundled Resources (optional) + +##### Scripts (`scripts/`) + +Executable code (Python/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten. + +- **When to include**: When the same code is being rewritten repeatedly or deterministic reliability is needed +- **Example**: `scripts/rotate_pdf.py` for PDF rotation tasks +- **Benefits**: Token efficient, deterministic, may be executed without loading into context +- **Note**: Scripts may still need to be read by Claude for patching or environment-specific adjustments + +##### References (`references/`) + +Documentation and reference material intended to be loaded as needed into context to inform Claude's process and thinking. + +- **When to include**: For documentation that Claude should reference while working +- **Examples**: `references/finance.md` for financial schemas, `references/mnda.md` for company NDA template, `references/policies.md` for company policies, `references/api_docs.md` for API specifications +- **Use cases**: Database schemas, API documentation, domain knowledge, company policies, detailed workflow guides +- **Benefits**: Keeps SKILL.md lean, loaded only when Claude determines it's needed +- **Best practice**: If files are large (>10k words), include grep search patterns in SKILL.md +- **Avoid duplication**: Information should live in either SKILL.md or references files, not both. Prefer references files for detailed information unless it's truly core to the skill—this keeps SKILL.md lean while making information discoverable without hogging the context window. Keep only essential procedural instructions and workflow guidance in SKILL.md; move detailed reference material, schemas, and examples to references files. + +##### Assets (`assets/`) + +Files not intended to be loaded into context, but rather used within the output Claude produces. + +- **When to include**: When the skill needs files that will be used in the final output +- **Examples**: `assets/logo.png` for brand assets, `assets/slides.pptx` for PowerPoint templates, `assets/frontend-template/` for HTML/React boilerplate, `assets/font.ttf` for typography +- **Use cases**: Templates, images, icons, boilerplate code, fonts, sample documents that get copied or modified +- **Benefits**: Separates output resources from documentation, enables Claude to use files without loading them into context + +#### What to Not Include in a Skill + +A skill should only contain essential files that directly support its functionality. Do NOT create extraneous documentation or auxiliary files, including: + +- README.md +- INSTALLATION_GUIDE.md +- QUICK_REFERENCE.md +- CHANGELOG.md +- etc. + +The skill should only contain the information needed for an AI agent to do the job at hand. It should not contain auxilary context about the process that went into creating it, setup and testing procedures, user-facing documentation, etc. Creating additional documentation files just adds clutter and confusion. + +### Progressive Disclosure Design Principle + +Skills use a three-level loading system to manage context efficiently: + +1. **Metadata (name + description)** - Always in context (~100 words) +2. **SKILL.md body** - When skill triggers (<5k words) +3. **Bundled resources** - As needed by Claude (Unlimited because scripts can be executed without reading into context window) + +#### Progressive Disclosure Patterns + +Keep SKILL.md body to the essentials and under 500 lines to minimize context bloat. Split content into separate files when approaching this limit. When splitting out content into other files, it is very important to reference them from SKILL.md and describe clearly when to read them, to ensure the reader of the skill knows they exist and when to use them. + +**Key principle:** When a skill supports multiple variations, frameworks, or options, keep only the core workflow and selection guidance in SKILL.md. Move variant-specific details (patterns, examples, configuration) into separate reference files. + +**Pattern 1: High-level guide with references** + +```markdown +# PDF Processing + +## Quick start + +Extract text with pdfplumber: +[code example] + +## Advanced features + +- **Form filling**: See [FORMS.md](FORMS.md) for complete guide +- **API reference**: See [REFERENCE.md](REFERENCE.md) for all methods +- **Examples**: See [EXAMPLES.md](EXAMPLES.md) for common patterns +``` + +Claude loads FORMS.md, REFERENCE.md, or EXAMPLES.md only when needed. + +**Pattern 2: Domain-specific organization** + +For Skills with multiple domains, organize content by domain to avoid loading irrelevant context: + +``` +bigquery-skill/ +├── SKILL.md (overview and navigation) +└── reference/ + ├── finance.md (revenue, billing metrics) + ├── sales.md (opportunities, pipeline) + ├── product.md (API usage, features) + └── marketing.md (campaigns, attribution) +``` + +When a user asks about sales metrics, Claude only reads sales.md. + +Similarly, for skills supporting multiple frameworks or variants, organize by variant: + +``` +cloud-deploy/ +├── SKILL.md (workflow + provider selection) +└── references/ + ├── aws.md (AWS deployment patterns) + ├── gcp.md (GCP deployment patterns) + └── azure.md (Azure deployment patterns) +``` + +When the user chooses AWS, Claude only reads aws.md. + +**Pattern 3: Conditional details** + +Show basic content, link to advanced content: + +```markdown +# DOCX Processing + +## Creating documents + +Use docx-js for new documents. See [DOCX-JS.md](DOCX-JS.md). + +## Editing documents + +For simple edits, modify the XML directly. + +**For tracked changes**: See [REDLINING.md](REDLINING.md) +**For OOXML details**: See [OOXML.md](OOXML.md) +``` + +Claude reads REDLINING.md or OOXML.md only when the user needs those features. + +**Important guidelines:** + +- **Avoid deeply nested references** - Keep references one level deep from SKILL.md. All reference files should link directly from SKILL.md. +- **Structure longer reference files** - For files longer than 100 lines, include a table of contents at the top so Claude can see the full scope when previewing. + +## Skill Creation Process + +Skill creation involves these steps: + +1. Understand the skill with concrete examples +2. Plan reusable skill contents (scripts, references, assets) +3. Initialize the skill (run init_skill.py) +4. Edit the skill (implement resources and write SKILL.md) +5. Package the skill (run package_skill.py) +6. Iterate based on real usage + +Follow these steps in order, skipping only if there is a clear reason why they are not applicable. + +### Step 1: Understanding the Skill with Concrete Examples + +Skip this step only when the skill's usage patterns are already clearly understood. It remains valuable even when working with an existing skill. + +To create an effective skill, clearly understand concrete examples of how the skill will be used. This understanding can come from either direct user examples or generated examples that are validated with user feedback. + +For example, when building an image-editor skill, relevant questions include: + +- "What functionality should the image-editor skill support? Editing, rotating, anything else?" +- "Can you give some examples of how this skill would be used?" +- "I can imagine users asking for things like 'Remove the red-eye from this image' or 'Rotate this image'. Are there other ways you imagine this skill being used?" +- "What would a user say that should trigger this skill?" + +To avoid overwhelming users, avoid asking too many questions in a single message. Start with the most important questions and follow up as needed for better effectiveness. + +Conclude this step when there is a clear sense of the functionality the skill should support. + +### Step 2: Planning the Reusable Skill Contents + +To turn concrete examples into an effective skill, analyze each example by: + +1. Considering how to execute on the example from scratch +2. Identifying what scripts, references, and assets would be helpful when executing these workflows repeatedly + +Example: When building a `pdf-editor` skill to handle queries like "Help me rotate this PDF," the analysis shows: + +1. Rotating a PDF requires re-writing the same code each time +2. A `scripts/rotate_pdf.py` script would be helpful to store in the skill + +Example: When designing a `frontend-webapp-builder` skill for queries like "Build me a todo app" or "Build me a dashboard to track my steps," the analysis shows: + +1. Writing a frontend webapp requires the same boilerplate HTML/React each time +2. An `assets/hello-world/` template containing the boilerplate HTML/React project files would be helpful to store in the skill + +Example: When building a `big-query` skill to handle queries like "How many users have logged in today?" the analysis shows: + +1. Querying BigQuery requires re-discovering the table schemas and relationships each time +2. A `references/schema.md` file documenting the table schemas would be helpful to store in the skill + +To establish the skill's contents, analyze each concrete example to create a list of the reusable resources to include: scripts, references, and assets. + +### Step 3: Initializing the Skill + +At this point, it is time to actually create the skill. + +Skip this step only if the skill being developed already exists, and iteration or packaging is needed. In this case, continue to the next step. + +When creating a new skill from scratch, always run the `init_skill.py` script. The script conveniently generates a new template skill directory that automatically includes everything a skill requires, making the skill creation process much more efficient and reliable. + +Usage: + +```bash +scripts/init_skill.py --path +``` + +The script: + +- Creates the skill directory at the specified path +- Generates a SKILL.md template with proper frontmatter and TODO placeholders +- Creates example resource directories: `scripts/`, `references/`, and `assets/` +- Adds example files in each directory that can be customized or deleted + +After initialization, customize or remove the generated SKILL.md and example files as needed. + +### Step 4: Edit the Skill + +When editing the (newly-generated or existing) skill, remember that the skill is being created for another instance of Claude to use. Include information that would be beneficial and non-obvious to Claude. Consider what procedural knowledge, domain-specific details, or reusable assets would help another Claude instance execute these tasks more effectively. + +#### Learn Proven Design Patterns + +Consult these helpful guides based on your skill's needs: + +- **Multi-step processes**: See references/workflows.md for sequential workflows and conditional logic +- **Specific output formats or quality standards**: See references/output-patterns.md for template and example patterns + +These files contain established best practices for effective skill design. + +#### Start with Reusable Skill Contents + +To begin implementation, start with the reusable resources identified above: `scripts/`, `references/`, and `assets/` files. Note that this step may require user input. For example, when implementing a `brand-guidelines` skill, the user may need to provide brand assets or templates to store in `assets/`, or documentation to store in `references/`. + +Added scripts must be tested by actually running them to ensure there are no bugs and that the output matches what is expected. If there are many similar scripts, only a representative sample needs to be tested to ensure confidence that they all work while balancing time to completion. + +Any example files and directories not needed for the skill should be deleted. The initialization script creates example files in `scripts/`, `references/`, and `assets/` to demonstrate structure, but most skills won't need all of them. + +#### Update SKILL.md + +**Writing Guidelines:** Always use imperative/infinitive form. + +##### Frontmatter + +Write the YAML frontmatter with `name` and `description`: + +- `name`: The skill name +- `description`: This is the primary triggering mechanism for your skill, and helps Claude understand when to use the skill. + - Include both what the Skill does and specific triggers/contexts for when to use it. + - Include all "when to use" information here - Not in the body. The body is only loaded after triggering, so "When to Use This Skill" sections in the body are not helpful to Claude. + - Example description for a `docx` skill: "Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. Use when Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks" + +Do not include any other fields in YAML frontmatter. + +##### Body + +Write instructions for using the skill and its bundled resources. + +### Step 5: Packaging a Skill + +Once development of the skill is complete, it must be packaged into a distributable .skill file that gets shared with the user. The packaging process automatically validates the skill first to ensure it meets all requirements: + +```bash +scripts/package_skill.py +``` + +Optional output directory specification: + +```bash +scripts/package_skill.py ./dist +``` + +The packaging script will: + +1. **Validate** the skill automatically, checking: + + - YAML frontmatter format and required fields + - Skill naming conventions and directory structure + - Description completeness and quality + - File organization and resource references + +2. **Package** the skill if validation passes, creating a .skill file named after the skill (e.g., `my-skill.skill`) that includes all files and maintains the proper directory structure for distribution. The .skill file is a zip file with a .skill extension. + +If validation fails, the script will report the errors and exit without creating a package. Fix any validation errors and run the packaging command again. + +### Step 6: Iterate + +After testing the skill, users may request improvements. Often this happens right after using the skill, with fresh context of how the skill performed. + +**Iteration workflow:** + +1. Use the skill on real tasks +2. Notice struggles or inefficiencies +3. Identify how SKILL.md or bundled resources should be updated +4. Implement changes and test again diff --git a/.claude/skills/skill-creator/references/output-patterns.md b/.claude/skills/skill-creator/references/output-patterns.md new file mode 100644 index 0000000..073ddda --- /dev/null +++ b/.claude/skills/skill-creator/references/output-patterns.md @@ -0,0 +1,82 @@ +# Output Patterns + +Use these patterns when skills need to produce consistent, high-quality output. + +## Template Pattern + +Provide templates for output format. Match the level of strictness to your needs. + +**For strict requirements (like API responses or data formats):** + +```markdown +## Report structure + +ALWAYS use this exact template structure: + +# [Analysis Title] + +## Executive summary +[One-paragraph overview of key findings] + +## Key findings +- Finding 1 with supporting data +- Finding 2 with supporting data +- Finding 3 with supporting data + +## Recommendations +1. Specific actionable recommendation +2. Specific actionable recommendation +``` + +**For flexible guidance (when adaptation is useful):** + +```markdown +## Report structure + +Here is a sensible default format, but use your best judgment: + +# [Analysis Title] + +## Executive summary +[Overview] + +## Key findings +[Adapt sections based on what you discover] + +## Recommendations +[Tailor to the specific context] + +Adjust sections as needed for the specific analysis type. +``` + +## Examples Pattern + +For skills where output quality depends on seeing examples, provide input/output pairs: + +```markdown +## Commit message format + +Generate commit messages following these examples: + +**Example 1:** +Input: Added user authentication with JWT tokens +Output: +``` +feat(auth): implement JWT-based authentication + +Add login endpoint and token validation middleware +``` + +**Example 2:** +Input: Fixed bug where dates displayed incorrectly in reports +Output: +``` +fix(reports): correct date formatting in timezone conversion + +Use UTC timestamps consistently across report generation +``` + +Follow this style: type(scope): brief description, then detailed explanation. +``` + +Examples help Claude understand the desired style and level of detail more clearly than descriptions alone. diff --git a/.claude/skills/skill-creator/references/workflows.md b/.claude/skills/skill-creator/references/workflows.md new file mode 100644 index 0000000..a350c3c --- /dev/null +++ b/.claude/skills/skill-creator/references/workflows.md @@ -0,0 +1,28 @@ +# Workflow Patterns + +## Sequential Workflows + +For complex tasks, break operations into clear, sequential steps. It is often helpful to give Claude an overview of the process towards the beginning of SKILL.md: + +```markdown +Filling a PDF form involves these steps: + +1. Analyze the form (run analyze_form.py) +2. Create field mapping (edit fields.json) +3. Validate mapping (run validate_fields.py) +4. Fill the form (run fill_form.py) +5. Verify output (run verify_output.py) +``` + +## Conditional Workflows + +For tasks with branching logic, guide Claude through decision points: + +```markdown +1. Determine the modification type: + **Creating new content?** → Follow "Creation workflow" below + **Editing existing content?** → Follow "Editing workflow" below + +2. Creation workflow: [steps] +3. Editing workflow: [steps] +``` \ No newline at end of file diff --git a/.claude/skills/skill-creator/scripts/__pycache__/quick_validate.cpython-311.pyc b/.claude/skills/skill-creator/scripts/__pycache__/quick_validate.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..7519b921ba752026c61008991bc159f14b6a3b57 GIT binary patch literal 4524 zcma)9Z)h7w7N37(zK*;auplx+Fo1Q zb#~WItVl(Ld~l1QzEY^61Vpb*Q*sA6u7PlHTxmJDkGp0eVxbT?@*&(8K{+V-bZ=IY zB{^xYtJ#^^o!`FqoA>6u8GTh->qT%)=l&{uUyIPc@k8k%i=7{X1VW!84$UHt;B0YX zmatmetj%ievv#W`XGv)7aYw>A>m(3I-a)f2-px6dY*>;k*bwjGiA75zesd4xK7hM$ zan2<>?#Zoyqc~UfD1qQDu~<_CBhLMbaaW~u&fQW1@6vP)_{`SM)?qz--7Dl&=;3Q+ zn59U(tdFx@Lii4Ql7rrhD?)6ES!Lq_$Et!PGD=JqmQ`j>k{M-5h{qKs!XyMyNU(8c zm6sL3c%Nf_GhxCcFR8oK*IOM z>mIZZN)Je}VcvkX{Ic`sH*|V+^rn23=F4Ck2sSRbs;*S0lSr8$Nzr1zxz($vKCbWef{ z+s-C^r3Xfo@E))ta!Gq662W6FGZJ&<^c&O6oGgiIf>l*sE<)k4lzkvHkLR?%H~m28H9H;^WdXo&AV6GNb+dpMCA8fok^z! z4JF4zjItoD#5ruxg|+1cUW~+8g=Y?96UkOL&SMuU-3%wp3o5j%$Q7{)BZ={~@Czc6 zv_&GxlOZO?ig-yVDl4nKJOFPB>Ov9Cz*!*%Yl4M&LaXqx6;)U*=~bTp4(6NmSnQiWg`!YC7{Lzov4=HIHxroz8`wj|IG=#=A=<`GBci|>M`nAj_%j!{-@1tpWgoXcDC;i z?|t%~MmFZ14#&_Bf#4^icJR0!7&HQd>(mc)%U0Kys!n$sbT@qL86|T5)0+Qu-j4e} zJ)`K25iE45T;=FSEpXx?3l%Q(3C+E``~(+Ba17zrje=JQt>qnD$N-RU4sLZl2_D%F z9?^r{MzC8CM2tX0J36WdMluUB0)2HgX4JQ5gvj}{cO15g!;n7 zepahtVe0<9pZ0#-n~gm5>AnHOH;|daQ(yWLXoL(Zgs1*aVd|IvKJYE2|90BIM-Da0YwL{7J?^D|TV^DJb8O=X~ zdEVBkR)cEY;-ahE=L))+ji1#c9K|Atm`VX3VcK*>qns3jtY=psMcO1q_QQbO43+7^sV**Dw-UCM7vv5+cnA-YtUSMJ zI+kJkg#-)9Ts0k5CNW(JUcq#}Mn3`&$@n1m!abajxRp3RB9Fi$KJzI5feIEiLF7pr zLFN&z+=!quUi`};PsaLHbf}E=%b`75b;*;H1ksU474se%&7S$< z-2IDROzBNWji#gT&t%5ef0H9U(1hNfxigcQ$&odgGk4By9@J|0u3ucgxOGt{_Zj3q QtyJ --path + +Examples: + init_skill.py my-new-skill --path skills/public + init_skill.py my-api-helper --path skills/private + init_skill.py custom-skill --path /custom/location +""" + +import sys +from pathlib import Path + + +SKILL_TEMPLATE = """--- +name: {skill_name} +description: [TODO: Complete and informative explanation of what the skill does and when to use it. Include WHEN to use this skill - specific scenarios, file types, or tasks that trigger it.] +--- + +# {skill_title} + +## Overview + +[TODO: 1-2 sentences explaining what this skill enables] + +## Structuring This Skill + +[TODO: Choose the structure that best fits this skill's purpose. Common patterns: + +**1. Workflow-Based** (best for sequential processes) +- Works well when there are clear step-by-step procedures +- Example: DOCX skill with "Workflow Decision Tree" → "Reading" → "Creating" → "Editing" +- Structure: ## Overview → ## Workflow Decision Tree → ## Step 1 → ## Step 2... + +**2. Task-Based** (best for tool collections) +- Works well when the skill offers different operations/capabilities +- Example: PDF skill with "Quick Start" → "Merge PDFs" → "Split PDFs" → "Extract Text" +- Structure: ## Overview → ## Quick Start → ## Task Category 1 → ## Task Category 2... + +**3. Reference/Guidelines** (best for standards or specifications) +- Works well for brand guidelines, coding standards, or requirements +- Example: Brand styling with "Brand Guidelines" → "Colors" → "Typography" → "Features" +- Structure: ## Overview → ## Guidelines → ## Specifications → ## Usage... + +**4. Capabilities-Based** (best for integrated systems) +- Works well when the skill provides multiple interrelated features +- Example: Product Management with "Core Capabilities" → numbered capability list +- Structure: ## Overview → ## Core Capabilities → ### 1. Feature → ### 2. Feature... + +Patterns can be mixed and matched as needed. Most skills combine patterns (e.g., start with task-based, add workflow for complex operations). + +Delete this entire "Structuring This Skill" section when done - it's just guidance.] + +## [TODO: Replace with the first main section based on chosen structure] + +[TODO: Add content here. See examples in existing skills: +- Code samples for technical skills +- Decision trees for complex workflows +- Concrete examples with realistic user requests +- References to scripts/templates/references as needed] + +## Resources + +This skill includes example resource directories that demonstrate how to organize different types of bundled resources: + +### scripts/ +Executable code (Python/Bash/etc.) that can be run directly to perform specific operations. + +**Examples from other skills:** +- PDF skill: `fill_fillable_fields.py`, `extract_form_field_info.py` - utilities for PDF manipulation +- DOCX skill: `document.py`, `utilities.py` - Python modules for document processing + +**Appropriate for:** Python scripts, shell scripts, or any executable code that performs automation, data processing, or specific operations. + +**Note:** Scripts may be executed without loading into context, but can still be read by Claude for patching or environment adjustments. + +### references/ +Documentation and reference material intended to be loaded into context to inform Claude's process and thinking. + +**Examples from other skills:** +- Product management: `communication.md`, `context_building.md` - detailed workflow guides +- BigQuery: API reference documentation and query examples +- Finance: Schema documentation, company policies + +**Appropriate for:** In-depth documentation, API references, database schemas, comprehensive guides, or any detailed information that Claude should reference while working. + +### assets/ +Files not intended to be loaded into context, but rather used within the output Claude produces. + +**Examples from other skills:** +- Brand styling: PowerPoint template files (.pptx), logo files +- Frontend builder: HTML/React boilerplate project directories +- Typography: Font files (.ttf, .woff2) + +**Appropriate for:** Templates, boilerplate code, document templates, images, icons, fonts, or any files meant to be copied or used in the final output. + +--- + +**Any unneeded directories can be deleted.** Not every skill requires all three types of resources. +""" + +EXAMPLE_SCRIPT = '''#!/usr/bin/env python3 +""" +Example helper script for {skill_name} + +This is a placeholder script that can be executed directly. +Replace with actual implementation or delete if not needed. + +Example real scripts from other skills: +- pdf/scripts/fill_fillable_fields.py - Fills PDF form fields +- pdf/scripts/convert_pdf_to_images.py - Converts PDF pages to images +""" + +def main(): + print("This is an example script for {skill_name}") + # TODO: Add actual script logic here + # This could be data processing, file conversion, API calls, etc. + +if __name__ == "__main__": + main() +''' + +EXAMPLE_REFERENCE = """# Reference Documentation for {skill_title} + +This is a placeholder for detailed reference documentation. +Replace with actual reference content or delete if not needed. + +Example real reference docs from other skills: +- product-management/references/communication.md - Comprehensive guide for status updates +- product-management/references/context_building.md - Deep-dive on gathering context +- bigquery/references/ - API references and query examples + +## When Reference Docs Are Useful + +Reference docs are ideal for: +- Comprehensive API documentation +- Detailed workflow guides +- Complex multi-step processes +- Information too lengthy for main SKILL.md +- Content that's only needed for specific use cases + +## Structure Suggestions + +### API Reference Example +- Overview +- Authentication +- Endpoints with examples +- Error codes +- Rate limits + +### Workflow Guide Example +- Prerequisites +- Step-by-step instructions +- Common patterns +- Troubleshooting +- Best practices +""" + +EXAMPLE_ASSET = """# Example Asset File + +This placeholder represents where asset files would be stored. +Replace with actual asset files (templates, images, fonts, etc.) or delete if not needed. + +Asset files are NOT intended to be loaded into context, but rather used within +the output Claude produces. + +Example asset files from other skills: +- Brand guidelines: logo.png, slides_template.pptx +- Frontend builder: hello-world/ directory with HTML/React boilerplate +- Typography: custom-font.ttf, font-family.woff2 +- Data: sample_data.csv, test_dataset.json + +## Common Asset Types + +- Templates: .pptx, .docx, boilerplate directories +- Images: .png, .jpg, .svg, .gif +- Fonts: .ttf, .otf, .woff, .woff2 +- Boilerplate code: Project directories, starter files +- Icons: .ico, .svg +- Data files: .csv, .json, .xml, .yaml + +Note: This is a text placeholder. Actual assets can be any file type. +""" + + +def title_case_skill_name(skill_name): + """Convert hyphenated skill name to Title Case for display.""" + return ' '.join(word.capitalize() for word in skill_name.split('-')) + + +def init_skill(skill_name, path): + """ + Initialize a new skill directory with template SKILL.md. + + Args: + skill_name: Name of the skill + path: Path where the skill directory should be created + + Returns: + Path to created skill directory, or None if error + """ + # Determine skill directory path + skill_dir = Path(path).resolve() / skill_name + + # Check if directory already exists + if skill_dir.exists(): + print(f"❌ Error: Skill directory already exists: {skill_dir}") + return None + + # Create skill directory + try: + skill_dir.mkdir(parents=True, exist_ok=False) + print(f"✅ Created skill directory: {skill_dir}") + except Exception as e: + print(f"❌ Error creating directory: {e}") + return None + + # Create SKILL.md from template + skill_title = title_case_skill_name(skill_name) + skill_content = SKILL_TEMPLATE.format( + skill_name=skill_name, + skill_title=skill_title + ) + + skill_md_path = skill_dir / 'SKILL.md' + try: + skill_md_path.write_text(skill_content) + print("✅ Created SKILL.md") + except Exception as e: + print(f"❌ Error creating SKILL.md: {e}") + return None + + # Create resource directories with example files + try: + # Create scripts/ directory with example script + scripts_dir = skill_dir / 'scripts' + scripts_dir.mkdir(exist_ok=True) + example_script = scripts_dir / 'example.py' + example_script.write_text(EXAMPLE_SCRIPT.format(skill_name=skill_name)) + example_script.chmod(0o755) + print("✅ Created scripts/example.py") + + # Create references/ directory with example reference doc + references_dir = skill_dir / 'references' + references_dir.mkdir(exist_ok=True) + example_reference = references_dir / 'api_reference.md' + example_reference.write_text(EXAMPLE_REFERENCE.format(skill_title=skill_title)) + print("✅ Created references/api_reference.md") + + # Create assets/ directory with example asset placeholder + assets_dir = skill_dir / 'assets' + assets_dir.mkdir(exist_ok=True) + example_asset = assets_dir / 'example_asset.txt' + example_asset.write_text(EXAMPLE_ASSET) + print("✅ Created assets/example_asset.txt") + except Exception as e: + print(f"❌ Error creating resource directories: {e}") + return None + + # Print next steps + print(f"\n✅ Skill '{skill_name}' initialized successfully at {skill_dir}") + print("\nNext steps:") + print("1. Edit SKILL.md to complete the TODO items and update the description") + print("2. Customize or delete the example files in scripts/, references/, and assets/") + print("3. Run the validator when ready to check the skill structure") + + return skill_dir + + +def main(): + if len(sys.argv) < 4 or sys.argv[2] != '--path': + print("Usage: init_skill.py --path ") + print("\nSkill name requirements:") + print(" - Hyphen-case identifier (e.g., 'data-analyzer')") + print(" - Lowercase letters, digits, and hyphens only") + print(" - Max 40 characters") + print(" - Must match directory name exactly") + print("\nExamples:") + print(" init_skill.py my-new-skill --path skills/public") + print(" init_skill.py my-api-helper --path skills/private") + print(" init_skill.py custom-skill --path /custom/location") + sys.exit(1) + + skill_name = sys.argv[1] + path = sys.argv[3] + + print(f"🚀 Initializing skill: {skill_name}") + print(f" Location: {path}") + print() + + result = init_skill(skill_name, path) + + if result: + sys.exit(0) + else: + sys.exit(1) + + +if __name__ == "__main__": + main() diff --git a/.claude/skills/skill-creator/scripts/package_skill.py b/.claude/skills/skill-creator/scripts/package_skill.py new file mode 100755 index 0000000..5cd36cb --- /dev/null +++ b/.claude/skills/skill-creator/scripts/package_skill.py @@ -0,0 +1,110 @@ +#!/usr/bin/env python3 +""" +Skill Packager - Creates a distributable .skill file of a skill folder + +Usage: + python utils/package_skill.py [output-directory] + +Example: + python utils/package_skill.py skills/public/my-skill + python utils/package_skill.py skills/public/my-skill ./dist +""" + +import sys +import zipfile +from pathlib import Path +from quick_validate import validate_skill + + +def package_skill(skill_path, output_dir=None): + """ + Package a skill folder into a .skill file. + + Args: + skill_path: Path to the skill folder + output_dir: Optional output directory for the .skill file (defaults to current directory) + + Returns: + Path to the created .skill file, or None if error + """ + skill_path = Path(skill_path).resolve() + + # Validate skill folder exists + if not skill_path.exists(): + print(f"❌ Error: Skill folder not found: {skill_path}") + return None + + if not skill_path.is_dir(): + print(f"❌ Error: Path is not a directory: {skill_path}") + return None + + # Validate SKILL.md exists + skill_md = skill_path / "SKILL.md" + if not skill_md.exists(): + print(f"❌ Error: SKILL.md not found in {skill_path}") + return None + + # Run validation before packaging + print("🔍 Validating skill...") + valid, message = validate_skill(skill_path) + if not valid: + print(f"❌ Validation failed: {message}") + print(" Please fix the validation errors before packaging.") + return None + print(f"✅ {message}\n") + + # Determine output location + skill_name = skill_path.name + if output_dir: + output_path = Path(output_dir).resolve() + output_path.mkdir(parents=True, exist_ok=True) + else: + output_path = Path.cwd() + + skill_filename = output_path / f"{skill_name}.skill" + + # Create the .skill file (zip format) + try: + with zipfile.ZipFile(skill_filename, 'w', zipfile.ZIP_DEFLATED) as zipf: + # Walk through the skill directory + for file_path in skill_path.rglob('*'): + if file_path.is_file(): + # Calculate the relative path within the zip + arcname = file_path.relative_to(skill_path.parent) + zipf.write(file_path, arcname) + print(f" Added: {arcname}") + + print(f"\n✅ Successfully packaged skill to: {skill_filename}") + return skill_filename + + except Exception as e: + print(f"❌ Error creating .skill file: {e}") + return None + + +def main(): + if len(sys.argv) < 2: + print("Usage: python utils/package_skill.py [output-directory]") + print("\nExample:") + print(" python utils/package_skill.py skills/public/my-skill") + print(" python utils/package_skill.py skills/public/my-skill ./dist") + sys.exit(1) + + skill_path = sys.argv[1] + output_dir = sys.argv[2] if len(sys.argv) > 2 else None + + print(f"📦 Packaging skill: {skill_path}") + if output_dir: + print(f" Output directory: {output_dir}") + print() + + result = package_skill(skill_path, output_dir) + + if result: + sys.exit(0) + else: + sys.exit(1) + + +if __name__ == "__main__": + main() diff --git a/.claude/skills/skill-creator/scripts/quick_validate.py b/.claude/skills/skill-creator/scripts/quick_validate.py new file mode 100755 index 0000000..d9fbeb7 --- /dev/null +++ b/.claude/skills/skill-creator/scripts/quick_validate.py @@ -0,0 +1,95 @@ +#!/usr/bin/env python3 +""" +Quick validation script for skills - minimal version +""" + +import sys +import os +import re +import yaml +from pathlib import Path + +def validate_skill(skill_path): + """Basic validation of a skill""" + skill_path = Path(skill_path) + + # Check SKILL.md exists + skill_md = skill_path / 'SKILL.md' + if not skill_md.exists(): + return False, "SKILL.md not found" + + # Read and validate frontmatter + content = skill_md.read_text() + if not content.startswith('---'): + return False, "No YAML frontmatter found" + + # Extract frontmatter + match = re.match(r'^---\n(.*?)\n---', content, re.DOTALL) + if not match: + return False, "Invalid frontmatter format" + + frontmatter_text = match.group(1) + + # Parse YAML frontmatter + try: + frontmatter = yaml.safe_load(frontmatter_text) + if not isinstance(frontmatter, dict): + return False, "Frontmatter must be a YAML dictionary" + except yaml.YAMLError as e: + return False, f"Invalid YAML in frontmatter: {e}" + + # Define allowed properties + ALLOWED_PROPERTIES = {'name', 'description', 'license', 'allowed-tools', 'metadata'} + + # Check for unexpected properties (excluding nested keys under metadata) + unexpected_keys = set(frontmatter.keys()) - ALLOWED_PROPERTIES + if unexpected_keys: + return False, ( + f"Unexpected key(s) in SKILL.md frontmatter: {', '.join(sorted(unexpected_keys))}. " + f"Allowed properties are: {', '.join(sorted(ALLOWED_PROPERTIES))}" + ) + + # Check required fields + if 'name' not in frontmatter: + return False, "Missing 'name' in frontmatter" + if 'description' not in frontmatter: + return False, "Missing 'description' in frontmatter" + + # Extract name for validation + name = frontmatter.get('name', '') + if not isinstance(name, str): + return False, f"Name must be a string, got {type(name).__name__}" + name = name.strip() + if name: + # Check naming convention (hyphen-case: lowercase with hyphens) + if not re.match(r'^[a-z0-9-]+$', name): + return False, f"Name '{name}' should be hyphen-case (lowercase letters, digits, and hyphens only)" + if name.startswith('-') or name.endswith('-') or '--' in name: + return False, f"Name '{name}' cannot start/end with hyphen or contain consecutive hyphens" + # Check name length (max 64 characters per spec) + if len(name) > 64: + return False, f"Name is too long ({len(name)} characters). Maximum is 64 characters." + + # Extract and validate description + description = frontmatter.get('description', '') + if not isinstance(description, str): + return False, f"Description must be a string, got {type(description).__name__}" + description = description.strip() + if description: + # Check for angle brackets + if '<' in description or '>' in description: + return False, "Description cannot contain angle brackets (< or >)" + # Check description length (max 1024 characters per spec) + if len(description) > 1024: + return False, f"Description is too long ({len(description)} characters). Maximum is 1024 characters." + + return True, "Skill is valid!" + +if __name__ == "__main__": + if len(sys.argv) != 2: + print("Usage: python quick_validate.py ") + sys.exit(1) + + valid, message = validate_skill(sys.argv[1]) + print(message) + sys.exit(0 if valid else 1) \ No newline at end of file diff --git a/.claude/skills/subagent-debug-logs.skill b/.claude/skills/subagent-debug-logs.skill new file mode 100644 index 0000000000000000000000000000000000000000..20c40767260b9c78f093c04ae2f4b6ef0014aa84 GIT binary patch literal 8026 zcmb7pWmH|=mh2%o!5t1xaF^g7+})jnySux)TW|~R5FCQLy99T4Lg#z8yT98#a^Jge z?H_xr{iAB^v1+VYHK)83I0QNX0Du9wk(p~(QK@T8LjeHakpKY3-(MY_4Gm0i0XdiQwqP)BOKe_D(38Z6R1O7I#M z<+OfFQf=$0(iwcT#)sUy;FS#*D_OL3F?@alg`ASh9nzPGswLodB+Ze_qaSWAlotrxy98!5wpmTPRZOE~JbJrKAo4D&t<<-*w``i$#&>PGG>9c*6Bo6}?s8`5 zGe`Ly?t%CgTsXae@}hgiyI>=}Jm2?Up|Tsb<$hv5ZBFpIQL&53F>;Lj`q0qOkm0MB zuPu?=XW0-hr-w)RlyHJa`ClP9u3&_ERzf6KS+(Jm-jTAi%5*B1+{+tYF`$-XbP8Me z8B|JA+61Ww1=e-f@wRW97Wa62mFRb0^=h^1PjB3}s{+&ef={gN%HbQftRLB=p$S6B zhI8muwi=z=dBq1u!8Q3YZ)1!C$a3FjP9lKTON1;mTi4WT?ya_c$;z>UliUPw;dWcw}4d};5(Od_cBx6B${?H znPx`Gvz+;v^%&RrYEv7|LCoMT=Jp*(Kc&*rI(72rFrr`A6$-o`$%XWmM;UUES*gHz z>2;!{P%2hw4eTt4Jm-$-Na6zW-IE$$??GuaRd620{<{6(FV^kC3Ze*wCEDL2%PxoZ zghgIWrTl#)%Y_1QgulSa|FCJ~ZD}rnIfyWVjx48f2=A67P`g4Cw?L0jE*l|9!O8dt zdRB^M4BmlTEEcaMlKRChdO*oJ7xZlJBZz2U2-^vCd+Ze64qxZ>KY=X-vCG3Y_DwNcyL(HA)ks z8i(?M0d&r=QPzRSEWjcdF;rq#qGIP;1Wk*}NBOjbQ?PotEPn`B~TSjA)9K7>8 z99d5JcKb6g#MD&4!HUH3In1EsiRfK|^|420FVg10UXqaWE*xoxrsIi-H2piI%nRe1 za#>B96`1%UI}`GD&(iF6ah);4b-YY$Xnk!Gf1`Y+zeZoU!2$qMu1rx7-z}Sft%xDd#~NG;-gOwrxFj)< zz#=ceVf`Wy9ZecZStYY*11u(zEN6O*2`idOvodQf7!@5}qULbQH*i4jTIMk`l?f72 z$w#Se#|YPb`Dn-2I&xSPuF+uUMN>W`Tg(yf8>mH+72p^iUr~U(CxhGPD9$WM4$4;u z%W4&~+Z1bGlU}J!_rs10X<~0h!L%kj9h%^$^<0OssDn>X#!E`^{2XDI1ttv4Ik{WS zSx2mMdD$VFKc>Ov8*Nf>w7V4rPA_pvsykN1#7Y-9!FqG89x8^^4st&BZp{`4`gq&F zQsU*dknO;GM6l=LafJNxe43EJi7v!fBIpVhRts)TCnh+xK#XiJ+dC0KmNZ5&q?A4; z;bzw?H?n$+8KH0pI943kFr_|WmGhg{;r}r;(02V`J~@3G4Ay6}w5~~aou16&(5jD(47PhU^UyLg9xwQd%7~VmfCa5TeWFG5U!M zRAqWXlK=1W82h_CKJa;o62Jfe8)yIk-oGf1N>UQi()8A#0rgcmpc=04gPy%`kqOq> zlAjE{>PktnYI}KGa@)(ye1!ce6~`4_j(sL&IEYdo2=CIH-GYn?lLUpNpux!2|32z6 zk$$CgFSm4&WozOEdsO%QuL3H^*q-2KBh-fR>q-h zY8yFw-kLmn?E*EiX>t{}Uc;s187GOma(cg>ZYE*0CUByEHk$_L)}!5efnhXKYn<$H zL^wA#sFqhARPdV)T4NUtR-U#jt2@F9losXIETTDiM5xO7C)i9*zcN)~F3+HNd)cry zng2rOSJx6rnuOd>_0$!{+Bfq?*{ex5vV0&b1rPe+j)puVnO%8gJGtPAT-Qqc##U_T=PXlicpO5bSt=3#dujKre&~BOQb**dVl~{d;cj++stv5$kJ2b3dMkd z;@f`Spd)da3hypKsT@m3zpl0OOm|;*fElf$JzCB5py#)`r~7Z>kxEwg7@a|Z=rvE! zSCltj1xkD@=v1TkF@cL{z6jY2LL7q0i&}32`i?i1-q1n7M%pZ= z0l4N6w-R~7tjY8Pl~}P9^>6UzpJh$WcTLBei43f9lc(ILD3uY9wgch&c z&rds@Y$?*nmJZn}x_Lzk^@D-vR^*o6t~PUsZt|mL@|r55EvmN1omTbJ`>~a$FfDWF!2C;l+2@O{#0vJ7<5Q z1oX)Aj7PLs3y>Wk*Q`SWFuw1y?#42@ec9)0O&^7(>IQBu1O=5&z}KiWm1`vD%w#U|zxea^>^8pYPUlGyqScx$E9EB-CmY z?Sm|@O(hg{wsGJJaF$;Gv)~j%R6=8LXtK!>-4E_=6VRe}*q$V7Kw@ z)i(qtY2__RXl7&`eixs_CEnokQ_WECup3WO*ewa#-r1K`X&ExK@);Dby$JVPJesPa zN$;>Ua7h)|qCTU->c$q6BM-vfKJvXJlPEzce#43zm~}(|2@1TJOIBzISdq9>(MRsK zY)}AlqBJ_b{9wErfxxc^`!9Ep61jAp7p^-~Wmm7oG(Q7>3D|LL;on1d3MmpPZ`Woa z+Zl+2Xar&I*KmTts}9vkf}QAN&6-LYDg(h61iLu)F<(hO$v$^~UrCdbdd?457QMNm zsdkY&x#6+!oQ>gOgq1}~L#UFd0e&%37)(-+;%H4MAzSzI=-+oeMLEc>{ZTf7g*&49 zyb*%igs^uBmd7Pp$OtPIcCiY2j>&)v#<;#3g!qEALz)~z&bo8wfj<$189|N$p(_l86Fn{)kSK#QlJ>2mHQW z<3lL(k-r};BlhNTLuF|Xo?^Khn0=FRg5auYK|fOhv~g-W={L3yH+*mJaL>KjXyF2_ za;Hxd*>Pk8VX|AaPeSyAz~W)gs?$p^5p6+nmD!3b{%}yp2NvXbAw(ghblD1AX96WL z(LWqaF+F*ZV0{AEqNrpDJP0Ir2A{xL>rUcO6gWT|jRpy{lj;0(dG$AYc^+^D<;!XP z_VF-HwT0!;cB#?A`Q|;!*0_yO6>~?!G4{GW!u_JLcs5SAHTK(UJgGHTpYUJ@ljKPf zci=@4xE`6v*(zl058(8`8?`1FXSq!IO-1WXg*owNKp!k2;%zsR+Ydb#vhG}3T?WIR zWZF)~l86qyJ@`z0Ttp`&8(N|iHxkiwy7BS37s%x^Ct@VUg-G6Q4#+hv6umM*@m3i zzUPvS=s8Xyvt&McVI^t3mWbwTLODoeqTFT`RSM1O2)UVCt%5M;x1mz=7yP76lL9A3 zrx(E}xkl!wQnHt-?ynzf$(tL5k3f_b4cVk%e+TjXp4NIHvlKarhuhdug`^$h5Z`l! zW@H9s?BQH8%wg+D74reJ#5>VfmcLdDH3Q$q+$O{3APy3S+cti!Ecr~w(=&npBd3Qb zj5cvLiV(@$TUvG6;@cb10sm=AK+nk8Y&x&Bb&p@(%*gmOv$_Mph50WHOKUC0rAC3m zRDEQeu~fp2Pxtn&q-4l63nz4DjrdXOXUHoI%iP?k`%+mG-3Eq@L1&pMzNfmvJuIT$ z8!O&Dq(>69I`Av2WTA8QG4~HQoZ#;$e%~m#osNT`m-8ngelk9*Yk6YZd39j*gj+(s zA4g?z__w`WTvNT6AE{+0yf2JkYHF4E4sr$PwR{L4Y8e~({zb2e^CLCW@Ww9qQb|@C zhNJv0*KiFLQEgg-?e%5=w%*$OFNk#Bn~m=UYoR%4f<3&mEeP=pE9_{wE?fPjnp{?U zl9i3jb9`Z?szw;)kXF0cLRl=F)Pgi8!ZD1(-OU>GA3f*~H~;n(?!SEnoUae~0T=*a z01g1K{|jGX;OJ=V^vCqg@sIS)!la_qW3$Q#-*G|%vs(w&1b2FEI+t;07AO}7CaE)0gnN)-L zjlwYGRByd-Zh!_}Z`KeUX1(2d_Oj#!nv4Jj#rqZUu59CFnzR!mt*-D(SSuO=_z@=} z!Y)zs)0=K>j%la(h*W;LX3*1)9W-f(z*)MY9nzMU5RFZh8d4X&&o4K(FSV#KpSTnU zP}BOjX5+?qs_>UYUUOFr3r)_eQ<^%`z0~j0pMOPu^7?GWHPl$+N&#(sBL+SLS0z@a zoXadyUOcPi$a70~=0?lNJv_hDuCx>G%0&Qaq=Oapoo zi(B%6OxM}6+%n#4HR5^@p^YpQ|5errHGwYmah$x?sidhweiQ~BWP3E?&a(Y1@S*XS zX1!G^)lgdo73G~I?Wa4nxJdz=!ZW!%gD#vi_=SFEAMz>;pgR2QF~i^5`Kx6^QTYAf z@wawHert#OUueg{*u>bu*v82CkNRQzPyH}PCyvJa){n@;FSrjHPJ8LzuI4P10Z@lT z>4qu6w9{-%9&VqgW4jpWTHR0KKnCI@?ibtRaQ90_!qq5jf~KK47)qB@p)jFqWrDK$ zfjR{GSRr$)wxncnxdFq}(MB~;M(#Fo7#gg|)x6{0lO-mxMNqQ+q?F?t%k6_)ZaKfb zF(!_`$EAM{DK4v=%#DMpO&#TDq+n(;LBhbm?t(B0LXh?IN(1A7e%<~86@#n^+2mr~ z?YBV3<;1GvEPu>SXm%02X$me9_;h$oTM61-2zTZPrZ+LuT8Djp9dgSdq{b&GdyDZk zbpVpZ0<~)mPf9U9LN3nFz0TyhO1)>Q%-F;jzAGuM>Qsyh9S;Ui!0ClXDA-(UkMP&9kj5enQ8J$a<~o&L!}KZ{B}vsASUOb zK0k8;6&uxok@43AVw~HPuq$!5gh}TVV>jJ=B4~yUX@8!QjCmTf)^G*oLwWBDGDQ7h z6o$Ty_q->CI>*d=T#;_mV&TsM&<1lZsUs0y)X$NJLbI@C5==(46t+yevJg?kH6T&h z&TugU+IJGvv2nfsDX0OBqD%eXf>QYa0C4;ZK{*;ZnA`pNHe&tHUZ9D0yrAtG5pwXw zYlPZCf_VGM7h9S=J_O8L~TK?dJN2mJK2Oy0dijT0q#(KTQYZeHCs*Sv6=HGd2b z#_s^H(^JvA$_=pR9$f491=J}))TK?2V`+(a&BIxg*BjFf+4scR<%-pj)p3(V&_?DG zJ#Q*khS&?j(hwdL?M$2;dP5EzgmZFjW|ylsAB@~tz&g{bcMO+GU}~Mw!(e?xrK7}m zhw$ePxIc!Mzo?9nRf>Oapm@C|o-0@(ZFm397FCb#ygG(1j)<)3aw5>fULAFFC)I%@vW&C^vmE;%yRi`(l%R6wcN zGyl!@IZ0Q~$<5Cj6r>67n)c(uVXbt%yx1Qm2D6yjz#tadKI&n`O1>NyR23f22I?_a zH@7EZB{V#4WGw@_)5aJRvPyg3Siuua;gdXyqp~@|zfUdT_cZ`YkUK|)1_1U^0RXE1 z$En#FI5-;X{ngB+w{uTc)3QYqL-%>8PP4&qXK!TBQ+YuiPNtrYq?U|7l!BbDyNbz% zyeRS{E-WJxf^Gds3WLHbpoBUDY;6b=px^EKI=14T&!1;%;&P^=7q$%T>1r~;x%sp| zmgTtNTRrKT-ATND+P7~EiuLGAc~X!>4nlX=t+7TDXrnQScU6DaayT`W!+^EwDXv zOMVUQ7)D3rDi5y@11EkdNLQeEuhtz$4~(@6o4PnQkav@5y0r%#XhL` z`&;_r$Uj>q;>3N?Et!mxYX!-%6G*mH^!(U^s3yc8@+0L4-K_C5RH?KofnNb433DVt z)w{LheM-d>x&7`^eYxB*dkxKT&C+u0-gqTE4Y&yih`{oasUC&+H#RdwpLJ4C_Te=h z<}PF&b;NL=8h9}(l8o~Nb_*rLv>NUHoU~$6^Q}d8hV+H7^!=PEdA}jX)8c_?#$=dO z#kHEC3qAA(1TD@buGc^$!=sQ*rgR7_$n7q%W?!+6j>hOS{S(bgFKX<~!!wZ`^>qgg zRAw1wEP8DY+n53UUPY`Ja%c@c+ui`oynj(?i94a3_m~D=5#%Q%Yh?ZJ)d$gRQcAoo@|qar?|ddSP(zm%qh8`m*Ck&fnPMG z9Hw>9U?I%f2xn7GaL#bm&Oyaz$eAj8Ec?lgmL1W>deq523UBnmYEw!Si!d@6)7z>g z)`{l>&C_kGf9%T(^fa`1oUw*}EfhOsZsJr4j0u>3WZ&L;@EY7HR4cEX%Xu6SO+Y=B z7|YNz6z1pG6-f1ZC+B^4J7>JY+3Hksc}5jtme`rO^)$A{$pd20wh4%!M2|o13&^g1M zM8Vf0qbHZeo}mQE&L9=Eptc+LGcw*v2J)|^+pQ<+woi4RbTfvy@}2Bcn}5;@;6&n4 z6M_dB6OOZ6r5;4W3&);tt1GO3uR7?I@3DcpE`h3VMJmEBcf&-T$PDnBo{?b^CKrK~ zU~pej=%pnKc~9rsY@Nm2{UJ(a$B1)UrCg$yaQ8A_sdH`Dq<~1qtYS5)8HqoJ%0K$7 za3mlnLYpb!luHU3n0-?gsY1cO21h9Qsb#xC-Jz0JCHGBqpIm&8f%)oUI{R+rhZppz z-Qp7&gX#ohL((huPKcV7s6Q?wMB6eQY3 z7OKm*7vk`idGK&b?3K;#4&V5)Q#Ncu1}(WydH4#3cw#h5H%ZCbVCD5oRF<5~G&6>b ztDrw-iY2ngo~sPaF|l^Xk6L`AH3LLBm2fvo-y!Td-8g`sGJg4*ol`hPV9R!xMmbL- z^Gr2s7ycQ_fN*ZE<0|=k`-reZx5y6Vv`r+PTn=y*tXSBed}%9pPv4v?%}1n|4ec#z z&S~b*U9u&IjjZ>McEgOwH6WizU4eypjAk-0lfvLQI zuGbPW^s_pBq98?KA;Y&xaF2Xlwc>0$-q0{QI%01}xLXq8i{unEEB=! zKgdRR8PQ}?D6?J~CttDMDmYindQ0nuCqdKVc@?5T_KQ2SILWjVMFYdmiOur!n5KAZ z;Ifs+hcr9*gk8V7veUGxR-TPJ+*F@RTb$n>I6`$>oaZVASE`DR>lV=)AtaJlCacgJ z5O>fq_bx95_5mIIUynq8*Vg~D3jP0j{r?U~{~7&H9p!&u0|15ogujdVpV0rSzx>Zg zf69=5Bf0(_=Kcxk-$<1IO!B9&@i$35%AZO8&FJyJiT<|<{V$?3|G%cyfBKt$$CCat m%b!fs-z;qy|96)EVWH%uAb-!y0RX7q56f@YjDr8y?mqxEBaa6F literal 0 HcmV?d00001 diff --git a/.claude/skills/subagent-debug-logs/SKILL.md b/.claude/skills/subagent-debug-logs/SKILL.md new file mode 100644 index 0000000..dc89f09 --- /dev/null +++ b/.claude/skills/subagent-debug-logs/SKILL.md @@ -0,0 +1,192 @@ +--- +name: subagent-debug-logs +description: 帮助用户查看和分析子代理调试日志（/tmp/subagent-debug-logs/ 目录下的 JSONL 文件）。当用户需要调试子代理问题、查看发送给子代理的请求内容、复制完整命令到命令行调试、或分析子代理响应内容时触发。使用场景：调试子代理执行问题、检查请求/响应内容、验证命令正确性、分析子代理行为。 +--- + +# 子代理调试日志查看器 + +## 概述 + +子代理调试日志记录了每次子代理调用的完整生命周期，包括请求、命令、响应等关键信息。日志存储在 `/tmp/subagent-debug-logs/` 目录下，每个会话对应一个 JSONL 文件。 + +## 日志位置 + +``` +/tmp/subagent-debug-logs/subagent-debug-{timestamp}-{sessionId}.jsonl +``` + +## 使用 Python 脚本查看日志 + +使用技能中的 `parse_logs.py` 脚本快速分析日志： + +### 列出最新日志文件 + +```bash +python3 .claude/skills/subagent-debug-logs/scripts/parse_logs.py --list --limit 10 +``` + +输出示例： +``` +📁 找到 1 个日志文件（最新 1 个）： + +1. subagent-debug-2026-03-09T04-34-54-487Z-msg-1773030894487-jf3u52.jsonl + 时间: 2026-03-09 04:35:04 | 大小: 3654 字节 + 路径: /tmp/subagent-debug-logs/subagent-debug-2026-03-09T04-34-54-487Z-msg-1773030894487-jf3u52.jsonl +``` + +### 查看完整日志内容 + +```bash +python3 .claude/skills/subagent-debug-logs/scripts/parse_logs.py --file /tmp/subagent-debug-logs/xxx.jsonl +``` + +### 过滤特定类型 + +只查看请求： +```bash +python3 .claude/skills/subagent-debug-logs/scripts/parse_logs.py --file /tmp/subagent-debug-logs/xxx.jsonl --type request +``` + +只查看命令： +```bash +python3 .claude/skills/subagent-debug-logs/scripts/parse_logs.py --file /tmp/subagent-debug-logs/xxx.jsonl --type command +``` + +只查看响应： +```bash +python3 .claude/skills/subagent-debug-logs/scripts/parse_logs.py --file /tmp/subagent-debug-logs/xxx.jsonl --type response +``` + +### 搜索关键词 + +```bash +python3 .claude/skills/subagent-debug-logs/scripts/parse_logs.py --file /tmp/subagent-debug-logs/xxx.jsonl --search "错误" +``` + +--- + +## 日志类型说明 + +### request - 请求消息 + +记录发送给子代理的完整消息内容： + +```json +{ + "type": "request", + "timestamp": "2026-03-09T04:34:54.534Z", + "message": "请列出当前目录的所有文件", + "messageLength": 13, + "filePath": "/path/to/input/file.txt" +} +``` + +### command - 执行命令 + +记录完整的 shell 命令（可直接复制到命令行调试）： + +```json +{ + "type": "command", + "timestamp": "2026-03-09T04:34:54.535Z", + "command": "sh -c cd /workspace && claude --print ...", + "containerGroupName": "223-234-template-6-group", + "containerName": "d8d-ai-vscode", + "namespace": "d8d-dev", + "workDir": "/mnt/code/223-234-template-6" +} +``` + +### response - 响应内容 + +记录子代理返回的完整响应： + +```json +{ + "type": "response", + "timestamp": "2026-03-09T04:35:04.962Z", + "output": "完整的响应内容...", + "assistantUuid": "msg-xxx", + "outputLength": 1234, + "success": true +} +``` + +### 其他日志类型 + +| 类型 | 说明 | +|------|------| +| `namespace_debug` | 命名空间和容器组信息 | +| `host_work_dir` | 宿主机工作目录路径 | +| `container_work_dir` | 容器内工作目录路径 | +| `file_cleanup` | 临时文件清理记录 | + +--- + +## 直接查看日志文件 + +使用 `cat` 或 `jq` 直接查看 JSONL 文件： + +```bash +# 查看原始日志 +cat /tmp/subagent-debug-logs/xxx.jsonl + +# 格式化查看 +cat /tmp/subagent-debug-logs/xxx.jsonl | jq '.' + +# 只看特定类型 +cat /tmp/subagent-debug-logs/xxx.jsonl | jq 'select(.type=="command")' +``` + +--- + +## 调试技巧 + +### 1. 复制命令直接调试 + +从日志中提取 `command` 字段，可以直接在容器中执行相同命令来复现问题。 + +### 2. 检查请求内容 + +对比 `request` 日志中的消息与实际发送的内容，确认请求参数正确。 + +### 3. 分析响应内容 + +检查 `response` 日志，查看子代理是否返回了预期的结果。 + +### 4. 时间线分析 + +根据 `timestamp` 字段，可以分析整个调用的时间消耗： + +- 请求 → 命令执行：准备时间 +- 命令执行 → 响应：子代理处理时间 + +--- + +## 日志存储说明 + +- **临时目录**：`/tmp/subagent-debug-logs/` +- **自动清理**：容器重启后自动删除 +- **文件格式**：JSONL（每行一个 JSON 对象） +- **文件命名**：`subagent-debug-{timestamp}-{sessionId}.jsonl` + +--- + +## Scripts + +技能包含 Python 脚本用于解析和格式化日志： + +- **`parse_logs.py`** - 日志解析工具，支持列表查看、内容过滤、关键词搜索 + +使用方法： +```bash +python3 .claude/skills/subagent-debug-logs/scripts/parse_logs.py [选项] +``` + +选项： +- `--list` - 列出最新日志文件 +- `--file ` - 指定日志文件路径 +- `--type ` - 过滤日志类型 +- `--search ` - 搜索关键词 +- `--limit ` - 列出文件数量限制（默认 10） +- `--log-dir ` - 日志目录（默认 /tmp/subagent-debug-logs） diff --git a/.claude/skills/subagent-debug-logs/scripts/parse_logs.py b/.claude/skills/subagent-debug-logs/scripts/parse_logs.py new file mode 100755 index 0000000..39efca0 --- /dev/null +++ b/.claude/skills/subagent-debug-logs/scripts/parse_logs.py @@ -0,0 +1,149 @@ +#!/usr/bin/env python3 +""" +子代理调试日志解析工具 +解析 /tmp/subagent-debug-logs/ 目录下的 JSONL 日志文件 +""" + +import json +import sys +import argparse +from pathlib import Path +from datetime import datetime + + +def list_log_files(log_dir="/tmp/subagent-debug-logs", limit=10): + """列出最新的日志文件""" + path = Path(log_dir) + if not path.exists(): + return [] + + files = sorted(path.glob("*.jsonl"), key=lambda f: f.stat().st_mtime, reverse=True) + return files[:limit] + + +def parse_log_file(file_path): + """解析 JSONL 日志文件""" + entries = [] + with open(file_path, 'r') as f: + for line in f: + line = line.strip() + if line: + try: + entries.append(json.loads(line)) + except json.JSONDecodeError: + continue + return entries + + +def format_entry(entry): + """格式化单条日志条目""" + log_type = entry.get('type', 'unknown') + timestamp = entry.get('timestamp', '') + content = [] + + if log_type == 'request': + content = [ + f"📨 **请求消息** ({timestamp})", + f"```\n{entry.get('message', '')}\n```", + f"长度: {entry.get('messageLength', 0)} 字符" + ] + elif log_type == 'command': + content = [ + f"🔧 **执行命令** ({timestamp})", + f"```bash\n{entry.get('command', '')}\n```", + f"容器: {entry.get('containerName', '')}", + f"工作目录: {entry.get('workDir', '')}" + ] + elif log_type == 'response': + output = entry.get('output', '') + preview = output[:500] + "..." if len(output) > 500 else output + content = [ + f"📤 **响应内容** ({timestamp})", + f"```\n{preview}\n```", + f"长度: {entry.get('outputLength', 0)} 字符", + f"状态: {'✅ 成功' if entry.get('success') else '❌ 失败'}" + ] + elif log_type == 'namespace_debug': + content = [ + f"🔍 **命名空间信息** ({timestamp})", + f"命名空间: {entry.get('namespace', '')}", + f"容器组: {entry.get('containerGroup', '')}" + ] + elif log_type == 'file_cleanup': + content = [ + f"🧹 **清理文件** ({timestamp})", + f"文件: {entry.get('path', '')}" + ] + else: + content = [ + f"📋 **{log_type}** ({timestamp})", + json.dumps(entry, ensure_ascii=False, indent=2) + ] + + return "\n".join(content) + + +def filter_entries(entries, log_type=None): + """过滤特定类型的日志条目""" + if log_type: + return [e for e in entries if e.get('type') == log_type] + return entries + + +def search_entries(entries, keyword): + """搜索包含关键词的日志条目""" + results = [] + for entry in entries: + entry_str = json.dumps(entry, ensure_ascii=False).lower() + if keyword.lower() in entry_str: + results.append(entry) + return results + + +def main(): + parser = argparse.ArgumentParser(description='子代理调试日志解析工具') + parser.add_argument('--list', action='store_true', help='列出最新的日志文件') + parser.add_argument('--file', type=str, help='指定要解析的日志文件') + parser.add_argument('--type', type=str, help='过滤特定类型 (request, command, response等)') + parser.add_argument('--search', type=str, help='搜索关键词') + parser.add_argument('--limit', type=int, default=10, help='列出文件数量限制') + parser.add_argument('--log-dir', type=str, default='/tmp/subagent-debug-logs', help='日志目录') + + args = parser.parse_args() + + if args.list: + files = list_log_files(args.log_dir, args.limit) + if not files: + print("❌ 没有找到日志文件") + return + + print(f"📁 找到 {len(files)} 个日志文件（最新 {len(files)} 个）：\n") + for i, f in enumerate(files, 1): + mtime = datetime.fromtimestamp(f.stat().st_mtime).strftime('%Y-%m-%d %H:%M:%S') + size = f.stat().st_size + print(f"{i}. {f.name}") + print(f" 时间: {mtime} | 大小: {size} 字节") + print(f" 路径: {f}\n") + + elif args.file: + entries = parse_log_file(args.file) + + if args.type: + entries = filter_entries(entries, args.type) + if args.search: + entries = search_entries(entries, args.search) + + print(f"📋 日志文件: {args.file}") + print(f"📊 共 {len(entries)} 条记录\n") + print("=" * 60 + "\n") + + for entry in entries: + print(format_entry(entry)) + print("\n" + "-" * 60 + "\n") + + else: + parser.print_help() + + +if __name__ == '__main__': + main() diff --git a/.claude/skills/subagent-monitor.skill b/.claude/skills/subagent-monitor.skill new file mode 100644 index 0000000000000000000000000000000000000000..e4cb7d1a99f6240b214e1033d4627cd14d887818 GIT binary patch literal 3733 zcmZ|SbyO7Iwg>PTW+>?zq{AVVMj8F$(HX@&;rZb8t? z@80#^dVjoo_8)t#bJjlpe)d;g2?Qnw001}u88R2c>NNjMUn~H?kMN%x06xezIK*XI&nx1MH?l&bkhUGX%EJGLLD)bJ^KDi+(<_ zKQnfPX$taDYguw75qHH=EA}H)qBvem=%-rUkT!bVv*tvSa}7_N;ri5md40X>t5NP! z8#YOn058YmcbOQr@mrYu1DsKeFv2r`E`QROM;J8Bo&4 zE=!zklXi&w5-rHZeN{0mv+rc&A{a5qhZ66EL`O_;|LVJ{*Auc*&I%|nEi@jY>Dz~2 z3SXqFsx{uv&Yw%2OWW#A=|c ztmgkfz?qUgTh-aiVi82u1*Zvuv3?p#^r8dJ$!OKZj5!2p{ zt4Idi7TGUR!6%m$ez1uF};0a!bNUZ!$go znNg?fldS&I^!(R}+KEq-yM3;J3n_N(dI4%_dO4TWQ|_o!;urH8SlSiI*oUbYa4VdS zj|r2-5GXr4k8*<1u61uoGi%|g`D;hw#@-N7F)a%`f%o_Fp+&F=utGZ|@;YQ#k=#Oo zD{BfC{hDSPxtXVrCF(G`H^QGT2}Tcf%MR60iBg2o ze!$l5^lEMF3g;+`Gj&Udh>r~-XUkPSLEv*<-_!6Q&Pn(wMcNQuS;5y}eP)vrk zuzotiCjmn9xz=V-ONB!sKz#zRzNmv;GAEVNHiKhiWLZ9s$9Wf4q!gDltA7JBh>M4m z>PBj!bIYcwQ97M(*3nJ5QFJ&~gyx>rti*KWVbn;vVn{k>S4k-uFY^ce=nS*k{5rqvp8MeGky%EVGNRK)RqlYNCw7NC{J<{7`h^+n+3FEqofOJ3TxAaNid%r zgadk`2Dp<7f^nZb=fG)UHl}~4!7I@t1U#~H6J}aUCXFKv_>!B`P}E~iGEGB3bZzW9 zZX;wB9pa>I=T16}C=9mmB>Dh$^%Z~a=gfr7E$jFp9)Qt_>E`xn(aYA=4$(RAgE>+$ zhi3|wC(Sa;h?8W9H|$EqhQV|+y7we7Q1-Ri zqe$`cDQdJc*sq7)59E89 zIXVvGg0efS#XW?Egs5wPf#5pOVqUFRT6%8JirLKMw=r})YMfhKRz@%d`8Y~aw;^n7 z-(7FwQWjeYM8TxzW1Q`0E={n_kYaxHd6)P87tWjI=d&l0b8hia-QP(u6MVD_j+spB=>)B|*A5~?%ve>sUMS%%1{#bNr{JX2x6VC^$wzg41{Ch7s% z-4C=K7<4vSA@0jtm6gjJH+ z0v(NTjw)6xIK^|$9piJy5!GR>^PX^KLt(2^NW4`BxzJRjo^1k+8>T~5IMPTv@_f4 z@FNwBa_3VUTiX-Udffk85cyZ!%kzz|KsWCMe$OogH^FakH}N(kwJkb& zt9dQJIUe3Au*cjl6oK~FS?CC_7WsX;B8=aV79<4SiDSm@&5`2R+b~`Tsca8)h6f?v zz=Zv%;0XrDVyeka@{7LF??jMrNRoGHx-&6Ltbx5) z@LM@%F;08x{K+Bwswy&t>b99dY)uOsO<4l`;+@P;RSonO*w!PY;r)EcF)yH~6|kiq zR7LM9i}QV>)n_f3$nuY<0o79LZ-VS5a*9Nx+LAs>fDu#(-l59BO4suR(&av>&c@o2 zLV89XP4X;vD6x& z(ss$^u_j`Jky!vxA>nkG4b?a}H8pGFvORFj!m5tGj=0Ak*or6*j{n}N?88bH#lX|0 z`WK8y*c+GQNcsDN>1Uw(f=De^Y;$nx%G&`4N+E6VfQTJ9Q2G(*I!LzvOOGtm$tI0V z6E)@U-Mos=c&=(D-E`yh;rp(~`=J!=!>ip^65^nq-F=&t#!kYJ-7oZsg{n^Oh!hCLprfzy4{YxG{6YZF*Ax+p_p?H9A6zt7oy@!FPF3BqU(5r@poIEr;>k(4Mv|+i!mJ66h@` z^kz*PKKb@M8IeTKz6^|>>2MpFQ;WF+z8IV!s5~VdvzY_Pp#t1FWzvL>N+d}bfQ8JV z_G2Wt?tSoE846+D60}WKQ$OVD1%r&VpZ3f>xzt~>@~o^gHN(@IvLek@G}VvnTMmS! zO?YF@r~LTdPJGpEh4+K@f{d7oZDgV1pe=}AJZ~D!)*v;3rS(|Rb}BYw5NA(0XV@Q4 z=H1ymzFQl^Phl@fe!0k6s=YoL<;?n8b6>yxYWD9R*5%v4#Qi@n5^8^o2Z6YrYVVv_ zpEh0#W9hFwY$cg-00reo_0*c;6d_un z6b#NNErfAyHp`Oas=I~jfG?MHi_rQaJb~}~dDt`fXE2FhX?zfBSUeU?m&l@VUVl6t z({2H@D4aIrPt&RL?ub-$du#-kpdh4{^G<-Utz&npiYI=UM3nAv+jho(poHg1t05PK zH7>xNS44!=O5h*B>-3ZKOJUvG?}b`NW;o0ezt3lkO?k@oYN?msV_7gOZSHmGTyxBF zc19loNumaO@QvA}Pi3%y8ZuJ#gU2TaY()r7MLLF3_rPQ$stn?-#33BcyhB`V7s0gE z)q`_lbId;TCWOu0p?8Mog1HlMAw8;KUYxw;hMK44(nGuMavZtHo+{3+l0wMOQl+*1 z=fPJX207@zr@#kf|9$fP|7rh|3IFfZ|L5|5W&nVE|NMtU`CpV)SHgUF1OPA|3iZ&z J55W@v_!nL2<9+}D literal 0 HcmV?d00001 diff --git a/.claude/skills/subagent-monitor/SKILL.md b/.claude/skills/subagent-monitor/SKILL.md new file mode 100644 index 0000000..8d49d4a --- /dev/null +++ b/.claude/skills/subagent-monitor/SKILL.md @@ -0,0 +1,169 @@ +--- +name: subagent-monitor +description: 监控 D8D 开发容器中子代理的对话历史、工作状态和活动情况。当用户想要"查看子代理工作情况"、"检查子代理在做什么"、"显示子代理历史记录"、"子代理完成了吗"或类似请求时触发此技能。用于跟踪容器内子代理的会话进度、提取对话内容、分析工作状态。 +--- + +# 子代理监控 (Subagent Monitor) + +## 概述 + +此技能用于监控 D8D 开发容器内 Claude 子代理的工作状态和对话历史，帮助用户了解子代理正在执行的任务、已完成的工作以及当前会话状态。 + +## 监控工作流程 + +### 1. 检查容器状态 + +首先确认容器是否运行中： + +```bash +# 使用 D8D MCP 工具 +d8d_get_dev_container_status(workspace_id, item_id, item_type) +``` + +**状态说明**: +- `running` 🟢 - 容器运行中，可以执行命令 +- `starting` 🟡 - 容器启动中，需要等待 +- `stopped` ⏹️ - 容器已停止，需要启动 + +### 2. 获取对话历史 + +获取子代理的对话历史记录： + +```bash +# 使用 D8D MCP 工具 +d8d_get_dev_container_conversation_history(workspace_id, item_id, item_type, limit) +``` + +**返回信息**: +- 会话 ID (session_id) +- 会话标题 +- 创建时间 +- 消息数量 + +### 3. 查看容器内活动 + +执行容器内命令查看当前活动： + +```bash +# 检查输出文件 +ls -la /tmp/claude-output-*.txt + +# 查看最近修改的文件 +find /mnt/code/... -type f -mtime -1 -ls + +# 检查进程 +ps aux | grep -i claude +``` + +### 4. 分析工作进度 + +根据对话历史和文件变更分析子代理的工作进度： + +| 指标 | 说明 | +|------|------| +| Git 提交 | 查看最新提交了解已完成工作 | +| Story 文件 | 查看 `stories/` 目录了解规划进度 | +| 代码变更 | 查看 `src/` 目录了解实现进度 | + +## 常见监控场景 + +### 场景 1: 检查子代理是否还在工作 + +```bash +# 1. 检查容器状态 +d8d_get_dev_container_status(...) + +# 2. 检查输出文件修改时间 +ls -la /tmp/claude-output-*.txt + +# 3. 检查进程 +ps aux | grep claude +``` + +### 场景 2: 查看子代理历史记录 + +```bash +# 获取对话历史 +d8d_get_dev_container_conversation_history(..., limit=10) + +# 查看输出文件内容 +tail -100 /tmp/claude-output-*.txt +``` + +### 场景 3: 了解工作进度 + +```bash +# 查看 Git 状态 +git status -sb +git log --oneline -5 + +# 查看 Story 文件 +ls -la stories/ + +# 查看源代码目录 +ls -la src/ +``` + +## MCP 工具参考 + +完整 D8D MCP 工具文档见 [references/mcp-tools.md](references/mcp-tools.md)。 + +**核心工具**: + +| 工具 | 用途 | +|------|------| +| `d8d_get_dev_container_status` | 获取容器状态 | +| `d8d_get_dev_container_conversation_history` | 获取对话历史 | +| `d8d_exec_dev_container_command` | 执行容器命令 | +| `d8d_invoke_dev_container_subagent` | 调用子代理 | + +## 会话连续性 + +与子代理通信时，需要保持会话连续性： + +**首次调用**: 创建新会话 +``` +d8d_invoke_dev_container_subagent({ + workspace_id: 223, + item_id: 236, + item_type: "template", + message: "任务描述" +}) +``` + +**继续对话**: 使用返回的 `sessionId` 和 `assistantMessageUuid` +``` +d8d_invoke_dev_container_subagent({ + workspace_id: 223, + item_id: 236, + item_type: "template", + message: "继续任务", + session_id: "xxx", + assistant_message_uuid: "yyy" +}) +``` + +## 报告格式 + +监控报告应包含以下部分： + +```markdown +## 📊 子代理工作状态报告 + +### 🔄 会话信息 +- Session ID: xxx +- 消息数量: xx +- 输出文件: xxx + +### 📝 最近工作内容 +- [任务1] +- [任务2] +- [任务3] + +### 📁 已创建文件 +- 文件1 +- 文件2 + +### 🎯 当前状态 +[状态描述] +``` diff --git a/.claude/skills/subagent-monitor/references/mcp-tools.md b/.claude/skills/subagent-monitor/references/mcp-tools.md new file mode 100644 index 0000000..6f6336d --- /dev/null +++ b/.claude/skills/subagent-monitor/references/mcp-tools.md @@ -0,0 +1,185 @@ +# D8D MCP 工具参考 + +用于监控和管理 D8D 开发容器的 MCP 工具集合。 + +## 容器状态工具 + +### d8d_get_dev_container_status + +获取开发容器的详细运行状态。 + +**参数**: +- `workspace_id` (number, 必需): 工作空间 ID +- `item_id` (number, 必需): 项目或模板 ID +- `item_type` (string, 必需): "project" 或 "template" +- `response_format` (string, 可选): "markdown" 或 "json"，默认 "markdown" + +**返回信息**: +- 状态: running, starting, stopped +- 容器 ID +- 启动时间 +- 访问地址列表 + +### d8d_list_dev_containers + +获取所有开发环境容器列表，支持分页。 + +**参数**: +- `limit` (number, 可选): 最大返回数量，范围 1-100，默认 20 +- `offset` (number, 可选): 分页偏移量，默认 0 +- `response_format` (string, 可选): "markdown" 或 "json"，默认 "markdown" + +### d8d_start_dev_container + +启动指定项目的开发环境容器。 + +**参数**: +- `workspace_id` (number, 必需): 工作空间 ID +- `item_id` (number, 必需): 项目或模板 ID +- `item_type` (string, 必需): "project" 或 "template" +- `container_group_id` (number, 可选): 覆盖默认配置的容器组配置 ID +- `response_format` (string, 可选): "markdown" 或 "json"，默认 "markdown" + +### d8d_stop_dev_container + +停止指定项目的开发环境容器。 + +**参数**: +- `workspace_id` (number, 必需) +- `item_id` (number, 必需) +- `item_type` (string, 必需): "project" 或 "template" +- `response_format` (string, 可选): "markdown" 或 "json"，默认 "markdown" + +### d8d_restart_dev_container + +重启开发环境容器（等同于停止后启动）。 + +**参数**: 同 `d8d_start_dev_container` + +## 对话历史工具 + +### d8d_get_dev_container_conversation_history + +获取开发容器中 Claude CLI 的对话历史列表。 + +**参数**: +- `workspace_id` (number, 必需) +- `item_id` (number, 必需) +- `item_type` (string, 必需): "project" 或 "template" +- `limit` (number, 可选): 最大返回数量，范围 1-100，默认 10 +- `response_format` (string, 可选): "markdown" 或 "json"，默认 "markdown" + +**返回信息**: +- 会话 ID +- 会话标题 +- 创建时间 +- 消息数量 + +## 子代理通信工具 + +### d8d_invoke_dev_container_subagent + +调用开发容器中的 Claude AI 子代理进行对话。 + +**参数**: +- `workspace_id` (number, 必需) +- `item_id` (number, 必需) +- `item_type` (string, 必需): "project" 或 "template" +- `message` (string, 必需): 发送给 Claude 的消息 +- `session_id` (string, 可选): 会话 ID，用于继续对话 +- `assistant_message_uuid` (string, 可选): 助手消息 UUID，用于继续对话 +- `timeout` (number, 可选): 超时时间（毫秒），默认 300000（5分钟） +- `skip_permissions` (boolean/string, 可选): 跳过权限检查 +- `response_format` (string, 可选): "markdown" 或 "json"，默认 "markdown" + +**⚠️ 会话连续性关键**: +- **首次调用**: 不提供 `session_id` 和 `assistant_message_uuid` +- **继续对话**: 必须同时提供 `session_id` 和 `assistant_message_uuid`，否则会创建新对话 + +**返回数据**: +```json +{ + "success": true, + "data": { + "output": "Claude 的响应内容", + "sessionId": "会话 ID（用于继续对话）", + "assistantMessageUuid": "助手消息 UUID（用于继续对话）" + } +} +``` + +## 容器命令执行工具 + +### d8d_exec_dev_container_command + +在开发容器的指定容器中执行命令并返回输出。 + +**参数**: +- `workspace_id` (number, 必需) +- `item_id` (number, 必需) +- `item_type` (string, 必需): "project" 或 "template" +- `command` (string[], 必需): 命令数组，如 `["/bin/sh", "-c", "ls -a"]` +- `container_name` (string, 可选): 容器名称，默认 "d8d-ai-vscode" +- `timeout` (number, 可选): 超时时间（毫秒），默认 300000 +- `response_format` (string, 可选): "markdown" 或 "json"，默认 "markdown" + +**⚠️ 重要**: +- 这是执行容器内命令的唯一方式 +- 当前环境不支持 ssh 或 kubectl exec + +**容器工作目录说明**: +- 工作目录: `/mnt/code/{workspace_id}-{item_id}-{item_type}-{group}/` +- 此目录是持久化挂载的，容器重启后数据保留 +- 其他目录（如 /root、/tmp、/home）是容器内部存储，容器停止后数据丢失 + +## 常用监控命令 + +### 查看容器状态 +```bash +# 检查 Claude 进程 +ps aux | grep -i claude | grep -v grep + +# 查看输出文件 +ls -la /tmp/claude-output-*.txt + +# 检查 PID 文件 +cat /tmp/claude-wrapper-*.pid +``` + +### 查看工作进度 +```bash +# 查看 Git 状态 +git status -sb +git log --oneline -5 + +# 查看项目文件 +ls -la stories/ +ls -la src/ + +# 查看最近修改 +find . -type f -mtime -1 -ls +``` + +### 查看对话记录 +```bash +# 输出文件位置 +/tmp/claude-output-*.txt + +# 查看最近内容 +tail -100 /tmp/claude-output-*.txt + +# 统计信息 +wc -l /tmp/claude-output-*.txt +``` + +## 错误处理 + +### 404 错误 +容器已停止或服务不可用。解决方案： +1. 检查容器状态 +2. 如已停止，使用 `d8d_start_dev_container` 重启 + +### API 超时 +命令执行时间过长。解决方案： +1. 增加 `timeout` 参数 +2. 检查命令是否卡死 diff --git a/.claude/skills/xlsx/LICENSE.txt b/.claude/skills/xlsx/LICENSE.txt new file mode 100644 index 0000000..c55ab42 --- /dev/null +++ b/.claude/skills/xlsx/LICENSE.txt @@ -0,0 +1,30 @@ +© 2025 Anthropic, PBC. All rights reserved. + +LICENSE: Use of these materials (including all code, prompts, assets, files, +and other components of this Skill) is governed by your agreement with +Anthropic regarding use of Anthropic's services. If no separate agreement +exists, use is governed by Anthropic's Consumer Terms of Service or +Commercial Terms of Service, as applicable: +https://www.anthropic.com/legal/consumer-terms +https://www.anthropic.com/legal/commercial-terms +Your applicable agreement is referred to as the "Agreement." "Services" are +as defined in the Agreement. + +ADDITIONAL RESTRICTIONS: Notwithstanding anything in the Agreement to the +contrary, users may not: + +- Extract these materials from the Services or retain copies of these + materials outside the Services +- Reproduce or copy these materials, except for temporary copies created + automatically during authorized use of the Services +- Create derivative works based on these materials +- Distribute, sublicense, or transfer these materials to any third party +- Make, offer to sell, sell, or import any inventions embodied in these + materials +- Reverse engineer, decompile, or disassemble these materials + +The receipt, viewing, or possession of these materials does not convey or +imply any license or right beyond those expressly granted above. + +Anthropic retains all right, title, and interest in these materials, +including all copyrights, patents, and other intellectual property rights. diff --git a/.claude/skills/xlsx/SKILL.md b/.claude/skills/xlsx/SKILL.md new file mode 100644 index 0000000..c5c881b --- /dev/null +++ b/.claude/skills/xlsx/SKILL.md @@ -0,0 +1,292 @@ +--- +name: xlsx +description: "Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved." +license: Proprietary. LICENSE.txt has complete terms +--- + +# Requirements for Outputs + +## All Excel files + +### Professional Font +- Use a consistent, professional font (e.g., Arial, Times New Roman) for all deliverables unless otherwise instructed by the user + +### Zero Formula Errors +- Every Excel model MUST be delivered with ZERO formula errors (#REF!, #DIV/0!, #VALUE!, #N/A, #NAME?) + +### Preserve Existing Templates (when updating templates) +- Study and EXACTLY match existing format, style, and conventions when modifying files +- Never impose standardized formatting on files with established patterns +- Existing template conventions ALWAYS override these guidelines + +## Financial models + +### Color Coding Standards +Unless otherwise stated by the user or existing template + +#### Industry-Standard Color Conventions +- **Blue text (RGB: 0,0,255)**: Hardcoded inputs, and numbers users will change for scenarios +- **Black text (RGB: 0,0,0)**: ALL formulas and calculations +- **Green text (RGB: 0,128,0)**: Links pulling from other worksheets within same workbook +- **Red text (RGB: 255,0,0)**: External links to other files +- **Yellow background (RGB: 255,255,0)**: Key assumptions needing attention or cells that need to be updated + +### Number Formatting Standards + +#### Required Format Rules +- **Years**: Format as text strings (e.g., "2024" not "2,024") +- **Currency**: Use $#,##0 format; ALWAYS specify units in headers ("Revenue ($mm)") +- **Zeros**: Use number formatting to make all zeros "-", including percentages (e.g., "$#,##0;($#,##0);-") +- **Percentages**: Default to 0.0% format (one decimal) +- **Multiples**: Format as 0.0x for valuation multiples (EV/EBITDA, P/E) +- **Negative numbers**: Use parentheses (123) not minus -123 + +### Formula Construction Rules + +#### Assumptions Placement +- Place ALL assumptions (growth rates, margins, multiples, etc.) in separate assumption cells +- Use cell references instead of hardcoded values in formulas +- Example: Use =B5*(1+$B$6) instead of =B5*1.05 + +#### Formula Error Prevention +- Verify all cell references are correct +- Check for off-by-one errors in ranges +- Ensure consistent formulas across all projection periods +- Test with edge cases (zero values, negative numbers) +- Verify no unintended circular references + +#### Documentation Requirements for Hardcodes +- Comment or in cells beside (if end of table). Format: "Source: [System/Document], [Date], [Specific Reference], [URL if applicable]" +- Examples: + - "Source: Company 10-K, FY2024, Page 45, Revenue Note, [SEC EDGAR URL]" + - "Source: Company 10-Q, Q2 2025, Exhibit 99.1, [SEC EDGAR URL]" + - "Source: Bloomberg Terminal, 8/15/2025, AAPL US Equity" + - "Source: FactSet, 8/20/2025, Consensus Estimates Screen" + +# XLSX creation, editing, and analysis + +## Overview + +A user may ask you to create, edit, or analyze the contents of an .xlsx file. You have different tools and workflows available for different tasks. + +## Important Requirements + +**LibreOffice Required for Formula Recalculation**: You can assume LibreOffice is installed for recalculating formula values using the `scripts/recalc.py` script. The script automatically configures LibreOffice on first run, including in sandboxed environments where Unix sockets are restricted (handled by `scripts/office/soffice.py`) + +## Reading and analyzing data + +### Data analysis with pandas +For data analysis, visualization, and basic operations, use **pandas** which provides powerful data manipulation capabilities: + +```python +import pandas as pd + +# Read Excel +df = pd.read_excel('file.xlsx') # Default: first sheet +all_sheets = pd.read_excel('file.xlsx', sheet_name=None) # All sheets as dict + +# Analyze +df.head() # Preview data +df.info() # Column info +df.describe() # Statistics + +# Write Excel +df.to_excel('output.xlsx', index=False) +``` + +## Excel File Workflows + +## CRITICAL: Use Formulas, Not Hardcoded Values + +**Always use Excel formulas instead of calculating values in Python and hardcoding them.** This ensures the spreadsheet remains dynamic and updateable. + +### ❌ WRONG - Hardcoding Calculated Values +```python +# Bad: Calculating in Python and hardcoding result +total = df['Sales'].sum() +sheet['B10'] = total # Hardcodes 5000 + +# Bad: Computing growth rate in Python +growth = (df.iloc[-1]['Revenue'] - df.iloc[0]['Revenue']) / df.iloc[0]['Revenue'] +sheet['C5'] = growth # Hardcodes 0.15 + +# Bad: Python calculation for average +avg = sum(values) / len(values) +sheet['D20'] = avg # Hardcodes 42.5 +``` + +### ✅ CORRECT - Using Excel Formulas +```python +# Good: Let Excel calculate the sum +sheet['B10'] = '=SUM(B2:B9)' + +# Good: Growth rate as Excel formula +sheet['C5'] = '=(C4-C2)/C2' + +# Good: Average using Excel function +sheet['D20'] = '=AVERAGE(D2:D19)' +``` + +This applies to ALL calculations - totals, percentages, ratios, differences, etc. The spreadsheet should be able to recalculate when source data changes. + +## Common Workflow +1. **Choose tool**: pandas for data, openpyxl for formulas/formatting +2. **Create/Load**: Create new workbook or load existing file +3. **Modify**: Add/edit data, formulas, and formatting +4. **Save**: Write to file +5. **Recalculate formulas (MANDATORY IF USING FORMULAS)**: Use the scripts/recalc.py script + ```bash + python scripts/recalc.py output.xlsx + ``` +6. **Verify and fix any errors**: + - The script returns JSON with error details + - If `status` is `errors_found`, check `error_summary` for specific error types and locations + - Fix the identified errors and recalculate again + - Common errors to fix: + - `#REF!`: Invalid cell references + - `#DIV/0!`: Division by zero + - `#VALUE!`: Wrong data type in formula + - `#NAME?`: Unrecognized formula name + +### Creating new Excel files + +```python +# Using openpyxl for formulas and formatting +from openpyxl import Workbook +from openpyxl.styles import Font, PatternFill, Alignment + +wb = Workbook() +sheet = wb.active + +# Add data +sheet['A1'] = 'Hello' +sheet['B1'] = 'World' +sheet.append(['Row', 'of', 'data']) + +# Add formula +sheet['B2'] = '=SUM(A1:A10)' + +# Formatting +sheet['A1'].font = Font(bold=True, color='FF0000') +sheet['A1'].fill = PatternFill('solid', start_color='FFFF00') +sheet['A1'].alignment = Alignment(horizontal='center') + +# Column width +sheet.column_dimensions['A'].width = 20 + +wb.save('output.xlsx') +``` + +### Editing existing Excel files + +```python +# Using openpyxl to preserve formulas and formatting +from openpyxl import load_workbook + +# Load existing file +wb = load_workbook('existing.xlsx') +sheet = wb.active # or wb['SheetName'] for specific sheet + +# Working with multiple sheets +for sheet_name in wb.sheetnames: + sheet = wb[sheet_name] + print(f"Sheet: {sheet_name}") + +# Modify cells +sheet['A1'] = 'New Value' +sheet.insert_rows(2) # Insert row at position 2 +sheet.delete_cols(3) # Delete column 3 + +# Add new sheet +new_sheet = wb.create_sheet('NewSheet') +new_sheet['A1'] = 'Data' + +wb.save('modified.xlsx') +``` + +## Recalculating formulas + +Excel files created or modified by openpyxl contain formulas as strings but not calculated values. Use the provided `scripts/recalc.py` script to recalculate formulas: + +```bash +python scripts/recalc.py [timeout_seconds] +``` + +Example: +```bash +python scripts/recalc.py output.xlsx 30 +``` + +The script: +- Automatically sets up LibreOffice macro on first run +- Recalculates all formulas in all sheets +- Scans ALL cells for Excel errors (#REF!, #DIV/0!, etc.) +- Returns JSON with detailed error locations and counts +- Works on both Linux and macOS + +## Formula Verification Checklist + +Quick checks to ensure formulas work correctly: + +### Essential Verification +- [ ] **Test 2-3 sample references**: Verify they pull correct values before building full model +- [ ] **Column mapping**: Confirm Excel columns match (e.g., column 64 = BL, not BK) +- [ ] **Row offset**: Remember Excel rows are 1-indexed (DataFrame row 5 = Excel row 6) + +### Common Pitfalls +- [ ] **NaN handling**: Check for null values with `pd.notna()` +- [ ] **Far-right columns**: FY data often in columns 50+ +- [ ] **Multiple matches**: Search all occurrences, not just first +- [ ] **Division by zero**: Check denominators before using `/` in formulas (#DIV/0!) +- [ ] **Wrong references**: Verify all cell references point to intended cells (#REF!) +- [ ] **Cross-sheet references**: Use correct format (Sheet1!A1) for linking sheets + +### Formula Testing Strategy +- [ ] **Start small**: Test formulas on 2-3 cells before applying broadly +- [ ] **Verify dependencies**: Check all cells referenced in formulas exist +- [ ] **Test edge cases**: Include zero, negative, and very large values + +### Interpreting scripts/recalc.py Output +The script returns JSON with error details: +```json +{ + "status": "success", // or "errors_found" + "total_errors": 0, // Total error count + "total_formulas": 42, // Number of formulas in file + "error_summary": { // Only present if errors found + "#REF!": { + "count": 2, + "locations": ["Sheet1!B5", "Sheet1!C10"] + } + } +} +``` + +## Best Practices + +### Library Selection +- **pandas**: Best for data analysis, bulk operations, and simple data export +- **openpyxl**: Best for complex formatting, formulas, and Excel-specific features + +### Working with openpyxl +- Cell indices are 1-based (row=1, column=1 refers to cell A1) +- Use `data_only=True` to read calculated values: `load_workbook('file.xlsx', data_only=True)` +- **Warning**: If opened with `data_only=True` and saved, formulas are replaced with values and permanently lost +- For large files: Use `read_only=True` for reading or `write_only=True` for writing +- Formulas are preserved but not evaluated - use scripts/recalc.py to update values + +### Working with pandas +- Specify data types to avoid inference issues: `pd.read_excel('file.xlsx', dtype={'id': str})` +- For large files, read specific columns: `pd.read_excel('file.xlsx', usecols=['A', 'C', 'E'])` +- Handle dates properly: `pd.read_excel('file.xlsx', parse_dates=['date_column'])` + +## Code Style Guidelines +**IMPORTANT**: When generating Python code for Excel operations: +- Write minimal, concise Python code without unnecessary comments +- Avoid verbose variable names and redundant operations +- Avoid unnecessary print statements + +**For Excel files themselves**: +- Add comments to cells with complex formulas or important assumptions +- Document data sources for hardcoded values +- Include notes for key calculations and model sections \ No newline at end of file diff --git a/.claude/skills/xlsx/scripts/office/helpers/__init__.py b/.claude/skills/xlsx/scripts/office/helpers/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/.claude/skills/xlsx/scripts/office/helpers/merge_runs.py b/.claude/skills/xlsx/scripts/office/helpers/merge_runs.py new file mode 100644 index 0000000..ad7c25e --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/helpers/merge_runs.py @@ -0,0 +1,199 @@ +"""Merge adjacent runs with identical formatting in DOCX. + +Merges adjacent elements that have identical properties. +Works on runs in paragraphs and inside tracked changes (, ). + +Also: +- Removes rsid attributes from runs (revision metadata that doesn't affect rendering) +- Removes proofErr elements (spell/grammar markers that block merging) +""" + +from pathlib import Path + +import defusedxml.minidom + + +def merge_runs(input_dir: str) -> tuple[int, str]: + doc_xml = Path(input_dir) / "word" / "document.xml" + + if not doc_xml.exists(): + return 0, f"Error: {doc_xml} not found" + + try: + dom = defusedxml.minidom.parseString(doc_xml.read_text(encoding="utf-8")) + root = dom.documentElement + + _remove_elements(root, "proofErr") + _strip_run_rsid_attrs(root) + + containers = {run.parentNode for run in _find_elements(root, "r")} + + merge_count = 0 + for container in containers: + merge_count += _merge_runs_in(container) + + doc_xml.write_bytes(dom.toxml(encoding="UTF-8")) + return merge_count, f"Merged {merge_count} runs" + + except Exception as e: + return 0, f"Error: {e}" + + + + +def _find_elements(root, tag: str) -> list: + results = [] + + def traverse(node): + if node.nodeType == node.ELEMENT_NODE: + name = node.localName or node.tagName + if name == tag or name.endswith(f":{tag}"): + results.append(node) + for child in node.childNodes: + traverse(child) + + traverse(root) + return results + + +def _get_child(parent, tag: str): + for child in parent.childNodes: + if child.nodeType == child.ELEMENT_NODE: + name = child.localName or child.tagName + if name == tag or name.endswith(f":{tag}"): + return child + return None + + +def _get_children(parent, tag: str) -> list: + results = [] + for child in parent.childNodes: + if child.nodeType == child.ELEMENT_NODE: + name = child.localName or child.tagName + if name == tag or name.endswith(f":{tag}"): + results.append(child) + return results + + +def _is_adjacent(elem1, elem2) -> bool: + node = elem1.nextSibling + while node: + if node == elem2: + return True + if node.nodeType == node.ELEMENT_NODE: + return False + if node.nodeType == node.TEXT_NODE and node.data.strip(): + return False + node = node.nextSibling + return False + + + + +def _remove_elements(root, tag: str): + for elem in _find_elements(root, tag): + if elem.parentNode: + elem.parentNode.removeChild(elem) + + +def _strip_run_rsid_attrs(root): + for run in _find_elements(root, "r"): + for attr in list(run.attributes.values()): + if "rsid" in attr.name.lower(): + run.removeAttribute(attr.name) + + + + +def _merge_runs_in(container) -> int: + merge_count = 0 + run = _first_child_run(container) + + while run: + while True: + next_elem = _next_element_sibling(run) + if next_elem and _is_run(next_elem) and _can_merge(run, next_elem): + _merge_run_content(run, next_elem) + container.removeChild(next_elem) + merge_count += 1 + else: + break + + _consolidate_text(run) + run = _next_sibling_run(run) + + return merge_count + + +def _first_child_run(container): + for child in container.childNodes: + if child.nodeType == child.ELEMENT_NODE and _is_run(child): + return child + return None + + +def _next_element_sibling(node): + sibling = node.nextSibling + while sibling: + if sibling.nodeType == sibling.ELEMENT_NODE: + return sibling + sibling = sibling.nextSibling + return None + + +def _next_sibling_run(node): + sibling = node.nextSibling + while sibling: + if sibling.nodeType == sibling.ELEMENT_NODE: + if _is_run(sibling): + return sibling + sibling = sibling.nextSibling + return None + + +def _is_run(node) -> bool: + name = node.localName or node.tagName + return name == "r" or name.endswith(":r") + + +def _can_merge(run1, run2) -> bool: + rpr1 = _get_child(run1, "rPr") + rpr2 = _get_child(run2, "rPr") + + if (rpr1 is None) != (rpr2 is None): + return False + if rpr1 is None: + return True + return rpr1.toxml() == rpr2.toxml() + + +def _merge_run_content(target, source): + for child in list(source.childNodes): + if child.nodeType == child.ELEMENT_NODE: + name = child.localName or child.tagName + if name != "rPr" and not name.endswith(":rPr"): + target.appendChild(child) + + +def _consolidate_text(run): + t_elements = _get_children(run, "t") + + for i in range(len(t_elements) - 1, 0, -1): + curr, prev = t_elements[i], t_elements[i - 1] + + if _is_adjacent(prev, curr): + prev_text = prev.firstChild.data if prev.firstChild else "" + curr_text = curr.firstChild.data if curr.firstChild else "" + merged = prev_text + curr_text + + if prev.firstChild: + prev.firstChild.data = merged + else: + prev.appendChild(run.ownerDocument.createTextNode(merged)) + + if merged.startswith(" ") or merged.endswith(" "): + prev.setAttribute("xml:space", "preserve") + elif prev.hasAttribute("xml:space"): + prev.removeAttribute("xml:space") + + run.removeChild(curr) diff --git a/.claude/skills/xlsx/scripts/office/helpers/simplify_redlines.py b/.claude/skills/xlsx/scripts/office/helpers/simplify_redlines.py new file mode 100644 index 0000000..db963bb --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/helpers/simplify_redlines.py @@ -0,0 +1,197 @@ +"""Simplify tracked changes by merging adjacent w:ins or w:del elements. + +Merges adjacent elements from the same author into a single element. +Same for elements. This makes heavily-redlined documents easier to +work with by reducing the number of tracked change wrappers. + +Rules: +- Only merges w:ins with w:ins, w:del with w:del (same element type) +- Only merges if same author (ignores timestamp differences) +- Only merges if truly adjacent (only whitespace between them) +""" + +import xml.etree.ElementTree as ET +import zipfile +from pathlib import Path + +import defusedxml.minidom + +WORD_NS = "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + + +def simplify_redlines(input_dir: str) -> tuple[int, str]: + doc_xml = Path(input_dir) / "word" / "document.xml" + + if not doc_xml.exists(): + return 0, f"Error: {doc_xml} not found" + + try: + dom = defusedxml.minidom.parseString(doc_xml.read_text(encoding="utf-8")) + root = dom.documentElement + + merge_count = 0 + + containers = _find_elements(root, "p") + _find_elements(root, "tc") + + for container in containers: + merge_count += _merge_tracked_changes_in(container, "ins") + merge_count += _merge_tracked_changes_in(container, "del") + + doc_xml.write_bytes(dom.toxml(encoding="UTF-8")) + return merge_count, f"Simplified {merge_count} tracked changes" + + except Exception as e: + return 0, f"Error: {e}" + + +def _merge_tracked_changes_in(container, tag: str) -> int: + merge_count = 0 + + tracked = [ + child + for child in container.childNodes + if child.nodeType == child.ELEMENT_NODE and _is_element(child, tag) + ] + + if len(tracked) < 2: + return 0 + + i = 0 + while i < len(tracked) - 1: + curr = tracked[i] + next_elem = tracked[i + 1] + + if _can_merge_tracked(curr, next_elem): + _merge_tracked_content(curr, next_elem) + container.removeChild(next_elem) + tracked.pop(i + 1) + merge_count += 1 + else: + i += 1 + + return merge_count + + +def _is_element(node, tag: str) -> bool: + name = node.localName or node.tagName + return name == tag or name.endswith(f":{tag}") + + +def _get_author(elem) -> str: + author = elem.getAttribute("w:author") + if not author: + for attr in elem.attributes.values(): + if attr.localName == "author" or attr.name.endswith(":author"): + return attr.value + return author + + +def _can_merge_tracked(elem1, elem2) -> bool: + if _get_author(elem1) != _get_author(elem2): + return False + + node = elem1.nextSibling + while node and node != elem2: + if node.nodeType == node.ELEMENT_NODE: + return False + if node.nodeType == node.TEXT_NODE and node.data.strip(): + return False + node = node.nextSibling + + return True + + +def _merge_tracked_content(target, source): + while source.firstChild: + child = source.firstChild + source.removeChild(child) + target.appendChild(child) + + +def _find_elements(root, tag: str) -> list: + results = [] + + def traverse(node): + if node.nodeType == node.ELEMENT_NODE: + name = node.localName or node.tagName + if name == tag or name.endswith(f":{tag}"): + results.append(node) + for child in node.childNodes: + traverse(child) + + traverse(root) + return results + + +def get_tracked_change_authors(doc_xml_path: Path) -> dict[str, int]: + if not doc_xml_path.exists(): + return {} + + try: + tree = ET.parse(doc_xml_path) + root = tree.getroot() + except ET.ParseError: + return {} + + namespaces = {"w": WORD_NS} + author_attr = f"{{{WORD_NS}}}author" + + authors: dict[str, int] = {} + for tag in ["ins", "del"]: + for elem in root.findall(f".//w:{tag}", namespaces): + author = elem.get(author_attr) + if author: + authors[author] = authors.get(author, 0) + 1 + + return authors + + +def _get_authors_from_docx(docx_path: Path) -> dict[str, int]: + try: + with zipfile.ZipFile(docx_path, "r") as zf: + if "word/document.xml" not in zf.namelist(): + return {} + with zf.open("word/document.xml") as f: + tree = ET.parse(f) + root = tree.getroot() + + namespaces = {"w": WORD_NS} + author_attr = f"{{{WORD_NS}}}author" + + authors: dict[str, int] = {} + for tag in ["ins", "del"]: + for elem in root.findall(f".//w:{tag}", namespaces): + author = elem.get(author_attr) + if author: + authors[author] = authors.get(author, 0) + 1 + return authors + except (zipfile.BadZipFile, ET.ParseError): + return {} + + +def infer_author(modified_dir: Path, original_docx: Path, default: str = "Claude") -> str: + modified_xml = modified_dir / "word" / "document.xml" + modified_authors = get_tracked_change_authors(modified_xml) + + if not modified_authors: + return default + + original_authors = _get_authors_from_docx(original_docx) + + new_changes: dict[str, int] = {} + for author, count in modified_authors.items(): + original_count = original_authors.get(author, 0) + diff = count - original_count + if diff > 0: + new_changes[author] = diff + + if not new_changes: + return default + + if len(new_changes) == 1: + return next(iter(new_changes)) + + raise ValueError( + f"Multiple authors added new changes: {new_changes}. " + "Cannot infer which author to validate." + ) diff --git a/.claude/skills/xlsx/scripts/office/pack.py b/.claude/skills/xlsx/scripts/office/pack.py new file mode 100755 index 0000000..db29ed8 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/pack.py @@ -0,0 +1,159 @@ +"""Pack a directory into a DOCX, PPTX, or XLSX file. + +Validates with auto-repair, condenses XML formatting, and creates the Office file. + +Usage: + python pack.py [--original ] [--validate true|false] + +Examples: + python pack.py unpacked/ output.docx --original input.docx + python pack.py unpacked/ output.pptx --validate false +""" + +import argparse +import sys +import shutil +import tempfile +import zipfile +from pathlib import Path + +import defusedxml.minidom + +from validators import DOCXSchemaValidator, PPTXSchemaValidator, RedliningValidator + +def pack( + input_directory: str, + output_file: str, + original_file: str | None = None, + validate: bool = True, + infer_author_func=None, +) -> tuple[None, str]: + input_dir = Path(input_directory) + output_path = Path(output_file) + suffix = output_path.suffix.lower() + + if not input_dir.is_dir(): + return None, f"Error: {input_dir} is not a directory" + + if suffix not in {".docx", ".pptx", ".xlsx"}: + return None, f"Error: {output_file} must be a .docx, .pptx, or .xlsx file" + + if validate and original_file: + original_path = Path(original_file) + if original_path.exists(): + success, output = _run_validation( + input_dir, original_path, suffix, infer_author_func + ) + if output: + print(output) + if not success: + return None, f"Error: Validation failed for {input_dir}" + + with tempfile.TemporaryDirectory() as temp_dir: + temp_content_dir = Path(temp_dir) / "content" + shutil.copytree(input_dir, temp_content_dir) + + for pattern in ["*.xml", "*.rels"]: + for xml_file in temp_content_dir.rglob(pattern): + _condense_xml(xml_file) + + output_path.parent.mkdir(parents=True, exist_ok=True) + with zipfile.ZipFile(output_path, "w", zipfile.ZIP_DEFLATED) as zf: + for f in temp_content_dir.rglob("*"): + if f.is_file(): + zf.write(f, f.relative_to(temp_content_dir)) + + return None, f"Successfully packed {input_dir} to {output_file}" + + +def _run_validation( + unpacked_dir: Path, + original_file: Path, + suffix: str, + infer_author_func=None, +) -> tuple[bool, str | None]: + output_lines = [] + validators = [] + + if suffix == ".docx": + author = "Claude" + if infer_author_func: + try: + author = infer_author_func(unpacked_dir, original_file) + except ValueError as e: + print(f"Warning: {e} Using default author 'Claude'.", file=sys.stderr) + + validators = [ + DOCXSchemaValidator(unpacked_dir, original_file), + RedliningValidator(unpacked_dir, original_file, author=author), + ] + elif suffix == ".pptx": + validators = [PPTXSchemaValidator(unpacked_dir, original_file)] + + if not validators: + return True, None + + total_repairs = sum(v.repair() for v in validators) + if total_repairs: + output_lines.append(f"Auto-repaired {total_repairs} issue(s)") + + success = all(v.validate() for v in validators) + + if success: + output_lines.append("All validations PASSED!") + + return success, "\n".join(output_lines) if output_lines else None + + +def _condense_xml(xml_file: Path) -> None: + try: + with open(xml_file, encoding="utf-8") as f: + dom = defusedxml.minidom.parse(f) + + for element in dom.getElementsByTagName("*"): + if element.tagName.endswith(":t"): + continue + + for child in list(element.childNodes): + if ( + child.nodeType == child.TEXT_NODE + and child.nodeValue + and child.nodeValue.strip() == "" + ) or child.nodeType == child.COMMENT_NODE: + element.removeChild(child) + + xml_file.write_bytes(dom.toxml(encoding="UTF-8")) + except Exception as e: + print(f"ERROR: Failed to parse {xml_file.name}: {e}", file=sys.stderr) + raise + + +if __name__ == "__main__": + parser = argparse.ArgumentParser( + description="Pack a directory into a DOCX, PPTX, or XLSX file" + ) + parser.add_argument("input_directory", help="Unpacked Office document directory") + parser.add_argument("output_file", help="Output Office file (.docx/.pptx/.xlsx)") + parser.add_argument( + "--original", + help="Original file for validation comparison", + ) + parser.add_argument( + "--validate", + type=lambda x: x.lower() == "true", + default=True, + metavar="true|false", + help="Run validation with auto-repair (default: true)", + ) + args = parser.parse_args() + + _, message = pack( + args.input_directory, + args.output_file, + original_file=args.original, + validate=args.validate, + ) + print(message) + + if "Error" in message: + sys.exit(1) diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd new file mode 100644 index 0000000..6454ef9 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd @@ -0,0 +1,1499 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd new file mode 100644 index 0000000..afa4f46 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd @@ -0,0 +1,146 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd new file mode 100644 index 0000000..64e66b8 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd @@ -0,0 +1,1085 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd new file mode 100644 index 0000000..687eea8 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd @@ -0,0 +1,11 @@ + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd new file mode 100644 index 0000000..6ac81b0 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd @@ -0,0 +1,3081 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd new file mode 100644 index 0000000..1dbf051 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd @@ -0,0 +1,23 @@ + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd new file mode 100644 index 0000000..f1af17d --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd @@ -0,0 +1,185 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd new file mode 100644 index 0000000..0a185ab --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd @@ -0,0 +1,287 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd new file mode 100644 index 0000000..14ef488 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd @@ -0,0 +1,1676 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd new file mode 100644 index 0000000..c20f3bf --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd @@ -0,0 +1,28 @@ + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd new file mode 100644 index 0000000..ac60252 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd @@ -0,0 +1,144 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd new file mode 100644 index 0000000..424b8ba --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd @@ -0,0 +1,174 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd new file mode 100644 index 0000000..2bddce2 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd @@ -0,0 +1,25 @@ + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd new file mode 100644 index 0000000..8a8c18b --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd @@ -0,0 +1,18 @@ + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd new file mode 100644 index 0000000..5c42706 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd @@ -0,0 +1,59 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd new file mode 100644 index 0000000..853c341 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd @@ -0,0 +1,56 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd new file mode 100644 index 0000000..da835ee --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd @@ -0,0 +1,195 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd new file mode 100644 index 0000000..87ad265 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd @@ -0,0 +1,582 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd new file mode 100644 index 0000000..9e86f1b --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd @@ -0,0 +1,25 @@ + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd new file mode 100644 index 0000000..d0be42e --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd @@ -0,0 +1,4439 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd new file mode 100644 index 0000000..8821dd1 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd @@ -0,0 +1,570 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd new file mode 100644 index 0000000..ca2575c --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd @@ -0,0 +1,509 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd new file mode 100644 index 0000000..dd079e6 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd @@ -0,0 +1,12 @@ + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd new file mode 100644 index 0000000..3dd6cf6 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd @@ -0,0 +1,108 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd new file mode 100644 index 0000000..f1041e3 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd @@ -0,0 +1,96 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd new file mode 100644 index 0000000..9c5b7a6 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd @@ -0,0 +1,3646 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd new file mode 100644 index 0000000..0f13678 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd @@ -0,0 +1,116 @@ + + + + + + See http://www.w3.org/XML/1998/namespace.html and + http://www.w3.org/TR/REC-xml for information about this namespace. + + This schema document describes the XML namespace, in a form + suitable for import by other schema documents. + + Note that local names in this namespace are intended to be defined + only by the World Wide Web Consortium or its subgroups. The + following names are currently defined in this namespace and should + not be used with conflicting semantics by any Working Group, + specification, or document instance: + + base (as an attribute name): denotes an attribute whose value + provides a URI to be used as the base for interpreting any + relative URIs in the scope of the element on which it + appears; its value is inherited. This name is reserved + by virtue of its definition in the XML Base specification. + + lang (as an attribute name): denotes an attribute whose value + is a language code for the natural language of the content of + any element; its value is inherited. This name is reserved + by virtue of its definition in the XML specification. + + space (as an attribute name): denotes an attribute whose + value is a keyword indicating what whitespace processing + discipline is intended for the content of the element; its + value is inherited. This name is reserved by virtue of its + definition in the XML specification. + + Father (in any context at all): denotes Jon Bosak, the chair of + the original XML Working Group. This name is reserved by + the following decision of the W3C XML Plenary and + XML Coordination groups: + + In appreciation for his vision, leadership and dedication + the W3C XML Plenary on this 10th day of February, 2000 + reserves for Jon Bosak in perpetuity the XML name + xml:Father + + + + + This schema defines attributes and an attribute group + suitable for use by + schemas wishing to allow xml:base, xml:lang or xml:space attributes + on elements they define. + + To enable this, such a schema must import this schema + for the XML namespace, e.g. as follows: + <schema . . .> + . . . + <import namespace="http://www.w3.org/XML/1998/namespace" + schemaLocation="http://www.w3.org/2001/03/xml.xsd"/> + + Subsequently, qualified reference to any of the attributes + or the group defined below will have the desired effect, e.g. + + <type . . .> + . . . + <attributeGroup ref="xml:specialAttrs"/> + + will define a type which will schema-validate an instance + element with any of those attributes + + + + In keeping with the XML Schema WG's standard versioning + policy, this schema document will persist at + http://www.w3.org/2001/03/xml.xsd. + At the date of issue it can also be found at + http://www.w3.org/2001/xml.xsd. + The schema document at that URI may however change in the future, + in order to remain compatible with the latest version of XML Schema + itself. In other words, if the XML Schema namespace changes, the version + of this document at + http://www.w3.org/2001/xml.xsd will change + accordingly; the version at + http://www.w3.org/2001/03/xml.xsd will not change. + + + + + + In due course, we should install the relevant ISO 2- and 3-letter + codes as the enumerated possible values . . . + + + + + + + + + + + + + + + See http://www.w3.org/TR/xmlbase/ for + information about this attribute. + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd b/.claude/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd new file mode 100644 index 0000000..a6de9d2 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd @@ -0,0 +1,42 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd b/.claude/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd new file mode 100644 index 0000000..10e978b --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd @@ -0,0 +1,50 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd b/.claude/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd new file mode 100644 index 0000000..4248bf7 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd @@ -0,0 +1,49 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd b/.claude/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd new file mode 100644 index 0000000..5649746 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd @@ -0,0 +1,33 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/mce/mc.xsd b/.claude/skills/xlsx/scripts/office/schemas/mce/mc.xsd new file mode 100644 index 0000000..ef72545 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/mce/mc.xsd @@ -0,0 +1,75 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/microsoft/wml-2010.xsd b/.claude/skills/xlsx/scripts/office/schemas/microsoft/wml-2010.xsd new file mode 100644 index 0000000..f65f777 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/microsoft/wml-2010.xsd @@ -0,0 +1,560 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/microsoft/wml-2012.xsd b/.claude/skills/xlsx/scripts/office/schemas/microsoft/wml-2012.xsd new file mode 100644 index 0000000..6b00755 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/microsoft/wml-2012.xsd @@ -0,0 +1,67 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/microsoft/wml-2018.xsd b/.claude/skills/xlsx/scripts/office/schemas/microsoft/wml-2018.xsd new file mode 100644 index 0000000..f321d33 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/microsoft/wml-2018.xsd @@ -0,0 +1,14 @@ + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/microsoft/wml-cex-2018.xsd b/.claude/skills/xlsx/scripts/office/schemas/microsoft/wml-cex-2018.xsd new file mode 100644 index 0000000..364c6a9 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/microsoft/wml-cex-2018.xsd @@ -0,0 +1,20 @@ + + + + + + + + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/microsoft/wml-cid-2016.xsd b/.claude/skills/xlsx/scripts/office/schemas/microsoft/wml-cid-2016.xsd new file mode 100644 index 0000000..fed9d15 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/microsoft/wml-cid-2016.xsd @@ -0,0 +1,13 @@ + + + + + + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd b/.claude/skills/xlsx/scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd new file mode 100644 index 0000000..680cf15 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd @@ -0,0 +1,4 @@ + + + + diff --git a/.claude/skills/xlsx/scripts/office/schemas/microsoft/wml-symex-2015.xsd b/.claude/skills/xlsx/scripts/office/schemas/microsoft/wml-symex-2015.xsd new file mode 100644 index 0000000..89ada90 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/schemas/microsoft/wml-symex-2015.xsd @@ -0,0 +1,8 @@ + + + + + + + + diff --git a/.claude/skills/xlsx/scripts/office/soffice.py b/.claude/skills/xlsx/scripts/office/soffice.py new file mode 100644 index 0000000..c7f7e32 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/soffice.py @@ -0,0 +1,183 @@ +""" +Helper for running LibreOffice (soffice) in environments where AF_UNIX +sockets may be blocked (e.g., sandboxed VMs). Detects the restriction +at runtime and applies an LD_PRELOAD shim if needed. + +Usage: + from office.soffice import run_soffice, get_soffice_env + + # Option 1 – run soffice directly + result = run_soffice(["--headless", "--convert-to", "pdf", "input.docx"]) + + # Option 2 – get env dict for your own subprocess calls + env = get_soffice_env() + subprocess.run(["soffice", ...], env=env) +""" + +import os +import socket +import subprocess +import tempfile +from pathlib import Path + + +def get_soffice_env() -> dict: + env = os.environ.copy() + env["SAL_USE_VCLPLUGIN"] = "svp" + + if _needs_shim(): + shim = _ensure_shim() + env["LD_PRELOAD"] = str(shim) + + return env + + +def run_soffice(args: list[str], **kwargs) -> subprocess.CompletedProcess: + env = get_soffice_env() + return subprocess.run(["soffice"] + args, env=env, **kwargs) + + + +_SHIM_SO = Path(tempfile.gettempdir()) / "lo_socket_shim.so" + + +def _needs_shim() -> bool: + try: + s = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM) + s.close() + return False + except OSError: + return True + + +def _ensure_shim() -> Path: + if _SHIM_SO.exists(): + return _SHIM_SO + + src = Path(tempfile.gettempdir()) / "lo_socket_shim.c" + src.write_text(_SHIM_SOURCE) + subprocess.run( + ["gcc", "-shared", "-fPIC", "-o", str(_SHIM_SO), str(src), "-ldl"], + check=True, + capture_output=True, + ) + src.unlink() + return _SHIM_SO + + + +_SHIM_SOURCE = r""" +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include + +static int (*real_socket)(int, int, int); +static int (*real_socketpair)(int, int, int, int[2]); +static int (*real_listen)(int, int); +static int (*real_accept)(int, struct sockaddr *, socklen_t *); +static int (*real_close)(int); +static int (*real_read)(int, void *, size_t); + +/* Per-FD bookkeeping (FDs >= 1024 are passed through unshimmed). */ +static int is_shimmed[1024]; +static int peer_of[1024]; +static int wake_r[1024]; /* accept() blocks reading this */ +static int wake_w[1024]; /* close() writes to this */ +static int listener_fd = -1; /* FD that received listen() */ + +__attribute__((constructor)) +static void init(void) { + real_socket = dlsym(RTLD_NEXT, "socket"); + real_socketpair = dlsym(RTLD_NEXT, "socketpair"); + real_listen = dlsym(RTLD_NEXT, "listen"); + real_accept = dlsym(RTLD_NEXT, "accept"); + real_close = dlsym(RTLD_NEXT, "close"); + real_read = dlsym(RTLD_NEXT, "read"); + for (int i = 0; i < 1024; i++) { + peer_of[i] = -1; + wake_r[i] = -1; + wake_w[i] = -1; + } +} + +/* ---- socket ---------------------------------------------------------- */ +int socket(int domain, int type, int protocol) { + if (domain == AF_UNIX) { + int fd = real_socket(domain, type, protocol); + if (fd >= 0) return fd; + /* socket(AF_UNIX) blocked – fall back to socketpair(). */ + int sv[2]; + if (real_socketpair(domain, type, protocol, sv) == 0) { + if (sv[0] >= 0 && sv[0] < 1024) { + is_shimmed[sv[0]] = 1; + peer_of[sv[0]] = sv[1]; + int wp[2]; + if (pipe(wp) == 0) { + wake_r[sv[0]] = wp[0]; + wake_w[sv[0]] = wp[1]; + } + } + return sv[0]; + } + errno = EPERM; + return -1; + } + return real_socket(domain, type, protocol); +} + +/* ---- listen ---------------------------------------------------------- */ +int listen(int sockfd, int backlog) { + if (sockfd >= 0 && sockfd < 1024 && is_shimmed[sockfd]) { + listener_fd = sockfd; + return 0; + } + return real_listen(sockfd, backlog); +} + +/* ---- accept ---------------------------------------------------------- */ +int accept(int sockfd, struct sockaddr *addr, socklen_t *addrlen) { + if (sockfd >= 0 && sockfd < 1024 && is_shimmed[sockfd]) { + /* Block until close() writes to the wake pipe. */ + if (wake_r[sockfd] >= 0) { + char buf; + real_read(wake_r[sockfd], &buf, 1); + } + errno = ECONNABORTED; + return -1; + } + return real_accept(sockfd, addr, addrlen); +} + +/* ---- close ----------------------------------------------------------- */ +int close(int fd) { + if (fd >= 0 && fd < 1024 && is_shimmed[fd]) { + int was_listener = (fd == listener_fd); + is_shimmed[fd] = 0; + + if (wake_w[fd] >= 0) { /* unblock accept() */ + char c = 0; + write(wake_w[fd], &c, 1); + real_close(wake_w[fd]); + wake_w[fd] = -1; + } + if (wake_r[fd] >= 0) { real_close(wake_r[fd]); wake_r[fd] = -1; } + if (peer_of[fd] >= 0) { real_close(peer_of[fd]); peer_of[fd] = -1; } + + if (was_listener) + _exit(0); /* conversion done – exit */ + } + return real_close(fd); +} +""" + + + +if __name__ == "__main__": + import sys + result = run_soffice(sys.argv[1:]) + sys.exit(result.returncode) diff --git a/.claude/skills/xlsx/scripts/office/unpack.py b/.claude/skills/xlsx/scripts/office/unpack.py new file mode 100755 index 0000000..0015253 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/unpack.py @@ -0,0 +1,132 @@ +"""Unpack Office files (DOCX, PPTX, XLSX) for editing. + +Extracts the ZIP archive, pretty-prints XML files, and optionally: +- Merges adjacent runs with identical formatting (DOCX only) +- Simplifies adjacent tracked changes from same author (DOCX only) + +Usage: + python unpack.py [options] + +Examples: + python unpack.py document.docx unpacked/ + python unpack.py presentation.pptx unpacked/ + python unpack.py document.docx unpacked/ --merge-runs false +""" + +import argparse +import sys +import zipfile +from pathlib import Path + +import defusedxml.minidom + +from helpers.merge_runs import merge_runs as do_merge_runs +from helpers.simplify_redlines import simplify_redlines as do_simplify_redlines + +SMART_QUOTE_REPLACEMENTS = { + "\u201c": "“", + "\u201d": "”", + "\u2018": "‘", + "\u2019": "’", +} + + +def unpack( + input_file: str, + output_directory: str, + merge_runs: bool = True, + simplify_redlines: bool = True, +) -> tuple[None, str]: + input_path = Path(input_file) + output_path = Path(output_directory) + suffix = input_path.suffix.lower() + + if not input_path.exists(): + return None, f"Error: {input_file} does not exist" + + if suffix not in {".docx", ".pptx", ".xlsx"}: + return None, f"Error: {input_file} must be a .docx, .pptx, or .xlsx file" + + try: + output_path.mkdir(parents=True, exist_ok=True) + + with zipfile.ZipFile(input_path, "r") as zf: + zf.extractall(output_path) + + xml_files = list(output_path.rglob("*.xml")) + list(output_path.rglob("*.rels")) + for xml_file in xml_files: + _pretty_print_xml(xml_file) + + message = f"Unpacked {input_file} ({len(xml_files)} XML files)" + + if suffix == ".docx": + if simplify_redlines: + simplify_count, _ = do_simplify_redlines(str(output_path)) + message += f", simplified {simplify_count} tracked changes" + + if merge_runs: + merge_count, _ = do_merge_runs(str(output_path)) + message += f", merged {merge_count} runs" + + for xml_file in xml_files: + _escape_smart_quotes(xml_file) + + return None, message + + except zipfile.BadZipFile: + return None, f"Error: {input_file} is not a valid Office file" + except Exception as e: + return None, f"Error unpacking: {e}" + + +def _pretty_print_xml(xml_file: Path) -> None: + try: + content = xml_file.read_text(encoding="utf-8") + dom = defusedxml.minidom.parseString(content) + xml_file.write_bytes(dom.toprettyxml(indent=" ", encoding="utf-8")) + except Exception: + pass + + +def _escape_smart_quotes(xml_file: Path) -> None: + try: + content = xml_file.read_text(encoding="utf-8") + for char, entity in SMART_QUOTE_REPLACEMENTS.items(): + content = content.replace(char, entity) + xml_file.write_text(content, encoding="utf-8") + except Exception: + pass + + +if __name__ == "__main__": + parser = argparse.ArgumentParser( + description="Unpack an Office file (DOCX, PPTX, XLSX) for editing" + ) + parser.add_argument("input_file", help="Office file to unpack") + parser.add_argument("output_directory", help="Output directory") + parser.add_argument( + "--merge-runs", + type=lambda x: x.lower() == "true", + default=True, + metavar="true|false", + help="Merge adjacent runs with identical formatting (DOCX only, default: true)", + ) + parser.add_argument( + "--simplify-redlines", + type=lambda x: x.lower() == "true", + default=True, + metavar="true|false", + help="Merge adjacent tracked changes from same author (DOCX only, default: true)", + ) + args = parser.parse_args() + + _, message = unpack( + args.input_file, + args.output_directory, + merge_runs=args.merge_runs, + simplify_redlines=args.simplify_redlines, + ) + print(message) + + if "Error" in message: + sys.exit(1) diff --git a/.claude/skills/xlsx/scripts/office/validate.py b/.claude/skills/xlsx/scripts/office/validate.py new file mode 100755 index 0000000..03b01f6 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/validate.py @@ -0,0 +1,111 @@ +""" +Command line tool to validate Office document XML files against XSD schemas and tracked changes. + +Usage: + python validate.py [--original ] [--auto-repair] [--author NAME] + +The first argument can be either: +- An unpacked directory containing the Office document XML files +- A packed Office file (.docx/.pptx/.xlsx) which will be unpacked to a temp directory + +Auto-repair fixes: +- paraId/durableId values that exceed OOXML limits +- Missing xml:space="preserve" on w:t elements with whitespace +""" + +import argparse +import sys +import tempfile +import zipfile +from pathlib import Path + +from validators import DOCXSchemaValidator, PPTXSchemaValidator, RedliningValidator + + +def main(): + parser = argparse.ArgumentParser(description="Validate Office document XML files") + parser.add_argument( + "path", + help="Path to unpacked directory or packed Office file (.docx/.pptx/.xlsx)", + ) + parser.add_argument( + "--original", + required=False, + default=None, + help="Path to original file (.docx/.pptx/.xlsx). If omitted, all XSD errors are reported and redlining validation is skipped.", + ) + parser.add_argument( + "-v", + "--verbose", + action="store_true", + help="Enable verbose output", + ) + parser.add_argument( + "--auto-repair", + action="store_true", + help="Automatically repair common issues (hex IDs, whitespace preservation)", + ) + parser.add_argument( + "--author", + default="Claude", + help="Author name for redlining validation (default: Claude)", + ) + args = parser.parse_args() + + path = Path(args.path) + assert path.exists(), f"Error: {path} does not exist" + + original_file = None + if args.original: + original_file = Path(args.original) + assert original_file.is_file(), f"Error: {original_file} is not a file" + assert original_file.suffix.lower() in [".docx", ".pptx", ".xlsx"], ( + f"Error: {original_file} must be a .docx, .pptx, or .xlsx file" + ) + + file_extension = (original_file or path).suffix.lower() + assert file_extension in [".docx", ".pptx", ".xlsx"], ( + f"Error: Cannot determine file type from {path}. Use --original or provide a .docx/.pptx/.xlsx file." + ) + + if path.is_file() and path.suffix.lower() in [".docx", ".pptx", ".xlsx"]: + temp_dir = tempfile.mkdtemp() + with zipfile.ZipFile(path, "r") as zf: + zf.extractall(temp_dir) + unpacked_dir = Path(temp_dir) + else: + assert path.is_dir(), f"Error: {path} is not a directory or Office file" + unpacked_dir = path + + match file_extension: + case ".docx": + validators = [ + DOCXSchemaValidator(unpacked_dir, original_file, verbose=args.verbose), + ] + if original_file: + validators.append( + RedliningValidator(unpacked_dir, original_file, verbose=args.verbose, author=args.author) + ) + case ".pptx": + validators = [ + PPTXSchemaValidator(unpacked_dir, original_file, verbose=args.verbose), + ] + case _: + print(f"Error: Validation not supported for file type {file_extension}") + sys.exit(1) + + if args.auto_repair: + total_repairs = sum(v.repair() for v in validators) + if total_repairs: + print(f"Auto-repaired {total_repairs} issue(s)") + + success = all(v.validate() for v in validators) + + if success: + print("All validations PASSED!") + + sys.exit(0 if success else 1) + + +if __name__ == "__main__": + main() diff --git a/.claude/skills/xlsx/scripts/office/validators/__init__.py b/.claude/skills/xlsx/scripts/office/validators/__init__.py new file mode 100644 index 0000000..db092ec --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/validators/__init__.py @@ -0,0 +1,15 @@ +""" +Validation modules for Word document processing. +""" + +from .base import BaseSchemaValidator +from .docx import DOCXSchemaValidator +from .pptx import PPTXSchemaValidator +from .redlining import RedliningValidator + +__all__ = [ + "BaseSchemaValidator", + "DOCXSchemaValidator", + "PPTXSchemaValidator", + "RedliningValidator", +] diff --git a/.claude/skills/xlsx/scripts/office/validators/base.py b/.claude/skills/xlsx/scripts/office/validators/base.py new file mode 100644 index 0000000..db4a06a --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/validators/base.py @@ -0,0 +1,847 @@ +""" +Base validator with common validation logic for document files. +""" + +import re +from pathlib import Path + +import defusedxml.minidom +import lxml.etree + + +class BaseSchemaValidator: + + IGNORED_VALIDATION_ERRORS = [ + "hyphenationZone", + "purl.org/dc/terms", + ] + + UNIQUE_ID_REQUIREMENTS = { + "comment": ("id", "file"), + "commentrangestart": ("id", "file"), + "commentrangeend": ("id", "file"), + "bookmarkstart": ("id", "file"), + "bookmarkend": ("id", "file"), + "sldid": ("id", "file"), + "sldmasterid": ("id", "global"), + "sldlayoutid": ("id", "global"), + "cm": ("authorid", "file"), + "sheet": ("sheetid", "file"), + "definedname": ("id", "file"), + "cxnsp": ("id", "file"), + "sp": ("id", "file"), + "pic": ("id", "file"), + "grpsp": ("id", "file"), + } + + EXCLUDED_ID_CONTAINERS = { + "sectionlst", + } + + ELEMENT_RELATIONSHIP_TYPES = {} + + SCHEMA_MAPPINGS = { + "word": "ISO-IEC29500-4_2016/wml.xsd", + "ppt": "ISO-IEC29500-4_2016/pml.xsd", + "xl": "ISO-IEC29500-4_2016/sml.xsd", + "[Content_Types].xml": "ecma/fouth-edition/opc-contentTypes.xsd", + "app.xml": "ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd", + "core.xml": "ecma/fouth-edition/opc-coreProperties.xsd", + "custom.xml": "ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd", + ".rels": "ecma/fouth-edition/opc-relationships.xsd", + "people.xml": "microsoft/wml-2012.xsd", + "commentsIds.xml": "microsoft/wml-cid-2016.xsd", + "commentsExtensible.xml": "microsoft/wml-cex-2018.xsd", + "commentsExtended.xml": "microsoft/wml-2012.xsd", + "chart": "ISO-IEC29500-4_2016/dml-chart.xsd", + "theme": "ISO-IEC29500-4_2016/dml-main.xsd", + "drawing": "ISO-IEC29500-4_2016/dml-main.xsd", + } + + MC_NAMESPACE = "http://schemas.openxmlformats.org/markup-compatibility/2006" + XML_NAMESPACE = "http://www.w3.org/XML/1998/namespace" + + PACKAGE_RELATIONSHIPS_NAMESPACE = ( + "http://schemas.openxmlformats.org/package/2006/relationships" + ) + OFFICE_RELATIONSHIPS_NAMESPACE = ( + "http://schemas.openxmlformats.org/officeDocument/2006/relationships" + ) + CONTENT_TYPES_NAMESPACE = ( + "http://schemas.openxmlformats.org/package/2006/content-types" + ) + + MAIN_CONTENT_FOLDERS = {"word", "ppt", "xl"} + + OOXML_NAMESPACES = { + "http://schemas.openxmlformats.org/officeDocument/2006/math", + "http://schemas.openxmlformats.org/officeDocument/2006/relationships", + "http://schemas.openxmlformats.org/schemaLibrary/2006/main", + "http://schemas.openxmlformats.org/drawingml/2006/main", + "http://schemas.openxmlformats.org/drawingml/2006/chart", + "http://schemas.openxmlformats.org/drawingml/2006/chartDrawing", + "http://schemas.openxmlformats.org/drawingml/2006/diagram", + "http://schemas.openxmlformats.org/drawingml/2006/picture", + "http://schemas.openxmlformats.org/drawingml/2006/spreadsheetDrawing", + "http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing", + "http://schemas.openxmlformats.org/wordprocessingml/2006/main", + "http://schemas.openxmlformats.org/presentationml/2006/main", + "http://schemas.openxmlformats.org/spreadsheetml/2006/main", + "http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes", + "http://www.w3.org/XML/1998/namespace", + } + + def __init__(self, unpacked_dir, original_file=None, verbose=False): + self.unpacked_dir = Path(unpacked_dir).resolve() + self.original_file = Path(original_file) if original_file else None + self.verbose = verbose + + self.schemas_dir = Path(__file__).parent.parent / "schemas" + + patterns = ["*.xml", "*.rels"] + self.xml_files = [ + f for pattern in patterns for f in self.unpacked_dir.rglob(pattern) + ] + + if not self.xml_files: + print(f"Warning: No XML files found in {self.unpacked_dir}") + + def validate(self): + raise NotImplementedError("Subclasses must implement the validate method") + + def repair(self) -> int: + return self.repair_whitespace_preservation() + + def repair_whitespace_preservation(self) -> int: + repairs = 0 + + for xml_file in self.xml_files: + try: + content = xml_file.read_text(encoding="utf-8") + dom = defusedxml.minidom.parseString(content) + modified = False + + for elem in dom.getElementsByTagName("*"): + if elem.tagName.endswith(":t") and elem.firstChild: + text = elem.firstChild.nodeValue + if text and (text.startswith((' ', '\t')) or text.endswith((' ', '\t'))): + if elem.getAttribute("xml:space") != "preserve": + elem.setAttribute("xml:space", "preserve") + text_preview = repr(text[:30]) + "..." if len(text) > 30 else repr(text) + print(f" Repaired: {xml_file.name}: Added xml:space='preserve' to {elem.tagName}: {text_preview}") + repairs += 1 + modified = True + + if modified: + xml_file.write_bytes(dom.toxml(encoding="UTF-8")) + + except Exception: + pass + + return repairs + + def validate_xml(self): + errors = [] + + for xml_file in self.xml_files: + try: + lxml.etree.parse(str(xml_file)) + except lxml.etree.XMLSyntaxError as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {e.lineno}: {e.msg}" + ) + except Exception as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Unexpected error: {str(e)}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} XML violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All XML files are well-formed") + return True + + def validate_namespaces(self): + errors = [] + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + declared = set(root.nsmap.keys()) - {None} + + for attr_val in [ + v for k, v in root.attrib.items() if k.endswith("Ignorable") + ]: + undeclared = set(attr_val.split()) - declared + errors.extend( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Namespace '{ns}' in Ignorable but not declared" + for ns in undeclared + ) + except lxml.etree.XMLSyntaxError: + continue + + if errors: + print(f"FAILED - {len(errors)} namespace issues:") + for error in errors: + print(error) + return False + if self.verbose: + print("PASSED - All namespace prefixes properly declared") + return True + + def validate_unique_ids(self): + errors = [] + global_ids = {} + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + file_ids = {} + + mc_elements = root.xpath( + ".//mc:AlternateContent", namespaces={"mc": self.MC_NAMESPACE} + ) + for elem in mc_elements: + elem.getparent().remove(elem) + + for elem in root.iter(): + tag = ( + elem.tag.split("}")[-1].lower() + if "}" in elem.tag + else elem.tag.lower() + ) + + if tag in self.UNIQUE_ID_REQUIREMENTS: + in_excluded_container = any( + ancestor.tag.split("}")[-1].lower() in self.EXCLUDED_ID_CONTAINERS + for ancestor in elem.iterancestors() + ) + if in_excluded_container: + continue + + attr_name, scope = self.UNIQUE_ID_REQUIREMENTS[tag] + + id_value = None + for attr, value in elem.attrib.items(): + attr_local = ( + attr.split("}")[-1].lower() + if "}" in attr + else attr.lower() + ) + if attr_local == attr_name: + id_value = value + break + + if id_value is not None: + if scope == "global": + if id_value in global_ids: + prev_file, prev_line, prev_tag = global_ids[ + id_value + ] + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: Global ID '{id_value}' in <{tag}> " + f"already used in {prev_file} at line {prev_line} in <{prev_tag}>" + ) + else: + global_ids[id_value] = ( + xml_file.relative_to(self.unpacked_dir), + elem.sourceline, + tag, + ) + elif scope == "file": + key = (tag, attr_name) + if key not in file_ids: + file_ids[key] = {} + + if id_value in file_ids[key]: + prev_line = file_ids[key][id_value] + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: Duplicate {attr_name}='{id_value}' in <{tag}> " + f"(first occurrence at line {prev_line})" + ) + else: + file_ids[key][id_value] = elem.sourceline + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} ID uniqueness violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All required IDs are unique") + return True + + def validate_file_references(self): + errors = [] + + rels_files = list(self.unpacked_dir.rglob("*.rels")) + + if not rels_files: + if self.verbose: + print("PASSED - No .rels files found") + return True + + all_files = [] + for file_path in self.unpacked_dir.rglob("*"): + if ( + file_path.is_file() + and file_path.name != "[Content_Types].xml" + and not file_path.name.endswith(".rels") + ): + all_files.append(file_path.resolve()) + + all_referenced_files = set() + + if self.verbose: + print( + f"Found {len(rels_files)} .rels files and {len(all_files)} target files" + ) + + for rels_file in rels_files: + try: + rels_root = lxml.etree.parse(str(rels_file)).getroot() + + rels_dir = rels_file.parent + + referenced_files = set() + broken_refs = [] + + for rel in rels_root.findall( + ".//ns:Relationship", + namespaces={"ns": self.PACKAGE_RELATIONSHIPS_NAMESPACE}, + ): + target = rel.get("Target") + if target and not target.startswith( + ("http", "mailto:") + ): + if target.startswith("/"): + target_path = self.unpacked_dir / target.lstrip("/") + elif rels_file.name == ".rels": + target_path = self.unpacked_dir / target + else: + base_dir = rels_dir.parent + target_path = base_dir / target + + try: + target_path = target_path.resolve() + if target_path.exists() and target_path.is_file(): + referenced_files.add(target_path) + all_referenced_files.add(target_path) + else: + broken_refs.append((target, rel.sourceline)) + except (OSError, ValueError): + broken_refs.append((target, rel.sourceline)) + + if broken_refs: + rel_path = rels_file.relative_to(self.unpacked_dir) + for broken_ref, line_num in broken_refs: + errors.append( + f" {rel_path}: Line {line_num}: Broken reference to {broken_ref}" + ) + + except Exception as e: + rel_path = rels_file.relative_to(self.unpacked_dir) + errors.append(f" Error parsing {rel_path}: {e}") + + unreferenced_files = set(all_files) - all_referenced_files + + if unreferenced_files: + for unref_file in sorted(unreferenced_files): + unref_rel_path = unref_file.relative_to(self.unpacked_dir) + errors.append(f" Unreferenced file: {unref_rel_path}") + + if errors: + print(f"FAILED - Found {len(errors)} relationship validation errors:") + for error in errors: + print(error) + print( + "CRITICAL: These errors will cause the document to appear corrupt. " + + "Broken references MUST be fixed, " + + "and unreferenced files MUST be referenced or removed." + ) + return False + else: + if self.verbose: + print( + "PASSED - All references are valid and all files are properly referenced" + ) + return True + + def validate_all_relationship_ids(self): + import lxml.etree + + errors = [] + + for xml_file in self.xml_files: + if xml_file.suffix == ".rels": + continue + + rels_dir = xml_file.parent / "_rels" + rels_file = rels_dir / f"{xml_file.name}.rels" + + if not rels_file.exists(): + continue + + try: + rels_root = lxml.etree.parse(str(rels_file)).getroot() + rid_to_type = {} + + for rel in rels_root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rid = rel.get("Id") + rel_type = rel.get("Type", "") + if rid: + if rid in rid_to_type: + rels_rel_path = rels_file.relative_to(self.unpacked_dir) + errors.append( + f" {rels_rel_path}: Line {rel.sourceline}: " + f"Duplicate relationship ID '{rid}' (IDs must be unique)" + ) + type_name = ( + rel_type.split("/")[-1] if "/" in rel_type else rel_type + ) + rid_to_type[rid] = type_name + + xml_root = lxml.etree.parse(str(xml_file)).getroot() + + r_ns = self.OFFICE_RELATIONSHIPS_NAMESPACE + rid_attrs_to_check = ["id", "embed", "link"] + for elem in xml_root.iter(): + for attr_name in rid_attrs_to_check: + rid_attr = elem.get(f"{{{r_ns}}}{attr_name}") + if not rid_attr: + continue + xml_rel_path = xml_file.relative_to(self.unpacked_dir) + elem_name = ( + elem.tag.split("}")[-1] if "}" in elem.tag else elem.tag + ) + + if rid_attr not in rid_to_type: + errors.append( + f" {xml_rel_path}: Line {elem.sourceline}: " + f"<{elem_name}> r:{attr_name} references non-existent relationship '{rid_attr}' " + f"(valid IDs: {', '.join(sorted(rid_to_type.keys())[:5])}{'...' if len(rid_to_type) > 5 else ''})" + ) + elif attr_name == "id" and self.ELEMENT_RELATIONSHIP_TYPES: + expected_type = self._get_expected_relationship_type( + elem_name + ) + if expected_type: + actual_type = rid_to_type[rid_attr] + if expected_type not in actual_type.lower(): + errors.append( + f" {xml_rel_path}: Line {elem.sourceline}: " + f"<{elem_name}> references '{rid_attr}' which points to '{actual_type}' " + f"but should point to a '{expected_type}' relationship" + ) + + except Exception as e: + xml_rel_path = xml_file.relative_to(self.unpacked_dir) + errors.append(f" Error processing {xml_rel_path}: {e}") + + if errors: + print(f"FAILED - Found {len(errors)} relationship ID reference errors:") + for error in errors: + print(error) + print("\nThese ID mismatches will cause the document to appear corrupt!") + return False + else: + if self.verbose: + print("PASSED - All relationship ID references are valid") + return True + + def _get_expected_relationship_type(self, element_name): + elem_lower = element_name.lower() + + if elem_lower in self.ELEMENT_RELATIONSHIP_TYPES: + return self.ELEMENT_RELATIONSHIP_TYPES[elem_lower] + + if elem_lower.endswith("id") and len(elem_lower) > 2: + prefix = elem_lower[:-2] + if prefix.endswith("master"): + return prefix.lower() + elif prefix.endswith("layout"): + return prefix.lower() + else: + if prefix == "sld": + return "slide" + return prefix.lower() + + if elem_lower.endswith("reference") and len(elem_lower) > 9: + prefix = elem_lower[:-9] + return prefix.lower() + + return None + + def validate_content_types(self): + errors = [] + + content_types_file = self.unpacked_dir / "[Content_Types].xml" + if not content_types_file.exists(): + print("FAILED - [Content_Types].xml file not found") + return False + + try: + root = lxml.etree.parse(str(content_types_file)).getroot() + declared_parts = set() + declared_extensions = set() + + for override in root.findall( + f".//{{{self.CONTENT_TYPES_NAMESPACE}}}Override" + ): + part_name = override.get("PartName") + if part_name is not None: + declared_parts.add(part_name.lstrip("/")) + + for default in root.findall( + f".//{{{self.CONTENT_TYPES_NAMESPACE}}}Default" + ): + extension = default.get("Extension") + if extension is not None: + declared_extensions.add(extension.lower()) + + declarable_roots = { + "sld", + "sldLayout", + "sldMaster", + "presentation", + "document", + "workbook", + "worksheet", + "theme", + } + + media_extensions = { + "png": "image/png", + "jpg": "image/jpeg", + "jpeg": "image/jpeg", + "gif": "image/gif", + "bmp": "image/bmp", + "tiff": "image/tiff", + "wmf": "image/x-wmf", + "emf": "image/x-emf", + } + + all_files = list(self.unpacked_dir.rglob("*")) + all_files = [f for f in all_files if f.is_file()] + + for xml_file in self.xml_files: + path_str = str(xml_file.relative_to(self.unpacked_dir)).replace( + "\\", "/" + ) + + if any( + skip in path_str + for skip in [".rels", "[Content_Types]", "docProps/", "_rels/"] + ): + continue + + try: + root_tag = lxml.etree.parse(str(xml_file)).getroot().tag + root_name = root_tag.split("}")[-1] if "}" in root_tag else root_tag + + if root_name in declarable_roots and path_str not in declared_parts: + errors.append( + f" {path_str}: File with <{root_name}> root not declared in [Content_Types].xml" + ) + + except Exception: + continue + + for file_path in all_files: + if file_path.suffix.lower() in {".xml", ".rels"}: + continue + if file_path.name == "[Content_Types].xml": + continue + if "_rels" in file_path.parts or "docProps" in file_path.parts: + continue + + extension = file_path.suffix.lstrip(".").lower() + if extension and extension not in declared_extensions: + if extension in media_extensions: + relative_path = file_path.relative_to(self.unpacked_dir) + errors.append( + f' {relative_path}: File with extension \'{extension}\' not declared in [Content_Types].xml - should add: ' + ) + + except Exception as e: + errors.append(f" Error parsing [Content_Types].xml: {e}") + + if errors: + print(f"FAILED - Found {len(errors)} content type declaration errors:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print( + "PASSED - All content files are properly declared in [Content_Types].xml" + ) + return True + + def validate_file_against_xsd(self, xml_file, verbose=False): + xml_file = Path(xml_file).resolve() + unpacked_dir = self.unpacked_dir.resolve() + + is_valid, current_errors = self._validate_single_file_xsd( + xml_file, unpacked_dir + ) + + if is_valid is None: + return None, set() + elif is_valid: + return True, set() + + original_errors = self._get_original_file_errors(xml_file) + + assert current_errors is not None + new_errors = current_errors - original_errors + + new_errors = { + e for e in new_errors + if not any(pattern in e for pattern in self.IGNORED_VALIDATION_ERRORS) + } + + if new_errors: + if verbose: + relative_path = xml_file.relative_to(unpacked_dir) + print(f"FAILED - {relative_path}: {len(new_errors)} new error(s)") + for error in list(new_errors)[:3]: + truncated = error[:250] + "..." if len(error) > 250 else error + print(f" - {truncated}") + return False, new_errors + else: + if verbose: + print( + f"PASSED - No new errors (original had {len(current_errors)} errors)" + ) + return True, set() + + def validate_against_xsd(self): + new_errors = [] + original_error_count = 0 + valid_count = 0 + skipped_count = 0 + + for xml_file in self.xml_files: + relative_path = str(xml_file.relative_to(self.unpacked_dir)) + is_valid, new_file_errors = self.validate_file_against_xsd( + xml_file, verbose=False + ) + + if is_valid is None: + skipped_count += 1 + continue + elif is_valid and not new_file_errors: + valid_count += 1 + continue + elif is_valid: + original_error_count += 1 + valid_count += 1 + continue + + new_errors.append(f" {relative_path}: {len(new_file_errors)} new error(s)") + for error in list(new_file_errors)[:3]: + new_errors.append( + f" - {error[:250]}..." if len(error) > 250 else f" - {error}" + ) + + if self.verbose: + print(f"Validated {len(self.xml_files)} files:") + print(f" - Valid: {valid_count}") + print(f" - Skipped (no schema): {skipped_count}") + if original_error_count: + print(f" - With original errors (ignored): {original_error_count}") + print( + f" - With NEW errors: {len(new_errors) > 0 and len([e for e in new_errors if not e.startswith(' ')]) or 0}" + ) + + if new_errors: + print("\nFAILED - Found NEW validation errors:") + for error in new_errors: + print(error) + return False + else: + if self.verbose: + print("\nPASSED - No new XSD validation errors introduced") + return True + + def _get_schema_path(self, xml_file): + if xml_file.name in self.SCHEMA_MAPPINGS: + return self.schemas_dir / self.SCHEMA_MAPPINGS[xml_file.name] + + if xml_file.suffix == ".rels": + return self.schemas_dir / self.SCHEMA_MAPPINGS[".rels"] + + if "charts/" in str(xml_file) and xml_file.name.startswith("chart"): + return self.schemas_dir / self.SCHEMA_MAPPINGS["chart"] + + if "theme/" in str(xml_file) and xml_file.name.startswith("theme"): + return self.schemas_dir / self.SCHEMA_MAPPINGS["theme"] + + if xml_file.parent.name in self.MAIN_CONTENT_FOLDERS: + return self.schemas_dir / self.SCHEMA_MAPPINGS[xml_file.parent.name] + + return None + + def _clean_ignorable_namespaces(self, xml_doc): + xml_string = lxml.etree.tostring(xml_doc, encoding="unicode") + xml_copy = lxml.etree.fromstring(xml_string) + + for elem in xml_copy.iter(): + attrs_to_remove = [] + + for attr in elem.attrib: + if "{" in attr: + ns = attr.split("}")[0][1:] + if ns not in self.OOXML_NAMESPACES: + attrs_to_remove.append(attr) + + for attr in attrs_to_remove: + del elem.attrib[attr] + + self._remove_ignorable_elements(xml_copy) + + return lxml.etree.ElementTree(xml_copy) + + def _remove_ignorable_elements(self, root): + elements_to_remove = [] + + for elem in list(root): + if not hasattr(elem, "tag") or callable(elem.tag): + continue + + tag_str = str(elem.tag) + if tag_str.startswith("{"): + ns = tag_str.split("}")[0][1:] + if ns not in self.OOXML_NAMESPACES: + elements_to_remove.append(elem) + continue + + self._remove_ignorable_elements(elem) + + for elem in elements_to_remove: + root.remove(elem) + + def _preprocess_for_mc_ignorable(self, xml_doc): + root = xml_doc.getroot() + + if f"{{{self.MC_NAMESPACE}}}Ignorable" in root.attrib: + del root.attrib[f"{{{self.MC_NAMESPACE}}}Ignorable"] + + return xml_doc + + def _validate_single_file_xsd(self, xml_file, base_path): + schema_path = self._get_schema_path(xml_file) + if not schema_path: + return None, None + + try: + with open(schema_path, "rb") as xsd_file: + parser = lxml.etree.XMLParser() + xsd_doc = lxml.etree.parse( + xsd_file, parser=parser, base_url=str(schema_path) + ) + schema = lxml.etree.XMLSchema(xsd_doc) + + with open(xml_file, "r") as f: + xml_doc = lxml.etree.parse(f) + + xml_doc, _ = self._remove_template_tags_from_text_nodes(xml_doc) + xml_doc = self._preprocess_for_mc_ignorable(xml_doc) + + relative_path = xml_file.relative_to(base_path) + if ( + relative_path.parts + and relative_path.parts[0] in self.MAIN_CONTENT_FOLDERS + ): + xml_doc = self._clean_ignorable_namespaces(xml_doc) + + if schema.validate(xml_doc): + return True, set() + else: + errors = set() + for error in schema.error_log: + errors.add(error.message) + return False, errors + + except Exception as e: + return False, {str(e)} + + def _get_original_file_errors(self, xml_file): + if self.original_file is None: + return set() + + import tempfile + import zipfile + + xml_file = Path(xml_file).resolve() + unpacked_dir = self.unpacked_dir.resolve() + relative_path = xml_file.relative_to(unpacked_dir) + + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + with zipfile.ZipFile(self.original_file, "r") as zip_ref: + zip_ref.extractall(temp_path) + + original_xml_file = temp_path / relative_path + + if not original_xml_file.exists(): + return set() + + is_valid, errors = self._validate_single_file_xsd( + original_xml_file, temp_path + ) + return errors if errors else set() + + def _remove_template_tags_from_text_nodes(self, xml_doc): + warnings = [] + template_pattern = re.compile(r"\{\{[^}]*\}\}") + + xml_string = lxml.etree.tostring(xml_doc, encoding="unicode") + xml_copy = lxml.etree.fromstring(xml_string) + + def process_text_content(text, content_type): + if not text: + return text + matches = list(template_pattern.finditer(text)) + if matches: + for match in matches: + warnings.append( + f"Found template tag in {content_type}: {match.group()}" + ) + return template_pattern.sub("", text) + return text + + for elem in xml_copy.iter(): + if not hasattr(elem, "tag") or callable(elem.tag): + continue + tag_str = str(elem.tag) + if tag_str.endswith("}t") or tag_str == "t": + continue + + elem.text = process_text_content(elem.text, "text content") + elem.tail = process_text_content(elem.tail, "tail content") + + return lxml.etree.ElementTree(xml_copy), warnings + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/.claude/skills/xlsx/scripts/office/validators/docx.py b/.claude/skills/xlsx/scripts/office/validators/docx.py new file mode 100644 index 0000000..fec405e --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/validators/docx.py @@ -0,0 +1,446 @@ +""" +Validator for Word document XML files against XSD schemas. +""" + +import random +import re +import tempfile +import zipfile + +import defusedxml.minidom +import lxml.etree + +from .base import BaseSchemaValidator + + +class DOCXSchemaValidator(BaseSchemaValidator): + + WORD_2006_NAMESPACE = "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + W14_NAMESPACE = "http://schemas.microsoft.com/office/word/2010/wordml" + W16CID_NAMESPACE = "http://schemas.microsoft.com/office/word/2016/wordml/cid" + + ELEMENT_RELATIONSHIP_TYPES = {} + + def validate(self): + if not self.validate_xml(): + return False + + all_valid = True + if not self.validate_namespaces(): + all_valid = False + + if not self.validate_unique_ids(): + all_valid = False + + if not self.validate_file_references(): + all_valid = False + + if not self.validate_content_types(): + all_valid = False + + if not self.validate_against_xsd(): + all_valid = False + + if not self.validate_whitespace_preservation(): + all_valid = False + + if not self.validate_deletions(): + all_valid = False + + if not self.validate_insertions(): + all_valid = False + + if not self.validate_all_relationship_ids(): + all_valid = False + + if not self.validate_id_constraints(): + all_valid = False + + if not self.validate_comment_markers(): + all_valid = False + + self.compare_paragraph_counts() + + return all_valid + + def validate_whitespace_preservation(self): + errors = [] + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + + for elem in root.iter(f"{{{self.WORD_2006_NAMESPACE}}}t"): + if elem.text: + text = elem.text + if re.search(r"^[ \t\n\r]", text) or re.search( + r"[ \t\n\r]$", text + ): + xml_space_attr = f"{{{self.XML_NAMESPACE}}}space" + if ( + xml_space_attr not in elem.attrib + or elem.attrib[xml_space_attr] != "preserve" + ): + text_preview = ( + repr(text)[:50] + "..." + if len(repr(text)) > 50 + else repr(text) + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: w:t element with whitespace missing xml:space='preserve': {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} whitespace preservation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All whitespace is properly preserved") + return True + + def validate_deletions(self): + errors = [] + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + namespaces = {"w": self.WORD_2006_NAMESPACE} + + for t_elem in root.xpath(".//w:del//w:t", namespaces=namespaces): + if t_elem.text: + text_preview = ( + repr(t_elem.text)[:50] + "..." + if len(repr(t_elem.text)) > 50 + else repr(t_elem.text) + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {t_elem.sourceline}: found within : {text_preview}" + ) + + for instr_elem in root.xpath( + ".//w:del//w:instrText", namespaces=namespaces + ): + text_preview = ( + repr(instr_elem.text or "")[:50] + "..." + if len(repr(instr_elem.text or "")) > 50 + else repr(instr_elem.text or "") + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {instr_elem.sourceline}: found within (use ): {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} deletion validation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - No w:t elements found within w:del elements") + return True + + def count_paragraphs_in_unpacked(self): + count = 0 + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + paragraphs = root.findall(f".//{{{self.WORD_2006_NAMESPACE}}}p") + count = len(paragraphs) + except Exception as e: + print(f"Error counting paragraphs in unpacked document: {e}") + + return count + + def count_paragraphs_in_original(self): + original = self.original_file + if original is None: + return 0 + + count = 0 + + try: + with tempfile.TemporaryDirectory() as temp_dir: + with zipfile.ZipFile(original, "r") as zip_ref: + zip_ref.extractall(temp_dir) + + doc_xml_path = temp_dir + "/word/document.xml" + root = lxml.etree.parse(doc_xml_path).getroot() + + paragraphs = root.findall(f".//{{{self.WORD_2006_NAMESPACE}}}p") + count = len(paragraphs) + + except Exception as e: + print(f"Error counting paragraphs in original document: {e}") + + return count + + def validate_insertions(self): + errors = [] + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + namespaces = {"w": self.WORD_2006_NAMESPACE} + + invalid_elements = root.xpath( + ".//w:ins//w:delText[not(ancestor::w:del)]", namespaces=namespaces + ) + + for elem in invalid_elements: + text_preview = ( + repr(elem.text or "")[:50] + "..." + if len(repr(elem.text or "")) > 50 + else repr(elem.text or "") + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: within : {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} insertion validation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - No w:delText elements within w:ins elements") + return True + + def compare_paragraph_counts(self): + original_count = self.count_paragraphs_in_original() + new_count = self.count_paragraphs_in_unpacked() + + diff = new_count - original_count + diff_str = f"+{diff}" if diff > 0 else str(diff) + print(f"\nParagraphs: {original_count} → {new_count} ({diff_str})") + + def _parse_id_value(self, val: str, base: int = 16) -> int: + return int(val, base) + + def validate_id_constraints(self): + errors = [] + para_id_attr = f"{{{self.W14_NAMESPACE}}}paraId" + durable_id_attr = f"{{{self.W16CID_NAMESPACE}}}durableId" + + for xml_file in self.xml_files: + try: + for elem in lxml.etree.parse(str(xml_file)).iter(): + if val := elem.get(para_id_attr): + if self._parse_id_value(val, base=16) >= 0x80000000: + errors.append( + f" {xml_file.name}:{elem.sourceline}: paraId={val} >= 0x80000000" + ) + + if val := elem.get(durable_id_attr): + if xml_file.name == "numbering.xml": + try: + if self._parse_id_value(val, base=10) >= 0x7FFFFFFF: + errors.append( + f" {xml_file.name}:{elem.sourceline}: " + f"durableId={val} >= 0x7FFFFFFF" + ) + except ValueError: + errors.append( + f" {xml_file.name}:{elem.sourceline}: " + f"durableId={val} must be decimal in numbering.xml" + ) + else: + if self._parse_id_value(val, base=16) >= 0x7FFFFFFF: + errors.append( + f" {xml_file.name}:{elem.sourceline}: " + f"durableId={val} >= 0x7FFFFFFF" + ) + except Exception: + pass + + if errors: + print(f"FAILED - {len(errors)} ID constraint violations:") + for e in errors: + print(e) + elif self.verbose: + print("PASSED - All paraId/durableId values within constraints") + return not errors + + def validate_comment_markers(self): + errors = [] + + document_xml = None + comments_xml = None + for xml_file in self.xml_files: + if xml_file.name == "document.xml" and "word" in str(xml_file): + document_xml = xml_file + elif xml_file.name == "comments.xml": + comments_xml = xml_file + + if not document_xml: + if self.verbose: + print("PASSED - No document.xml found (skipping comment validation)") + return True + + try: + doc_root = lxml.etree.parse(str(document_xml)).getroot() + namespaces = {"w": self.WORD_2006_NAMESPACE} + + range_starts = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in doc_root.xpath( + ".//w:commentRangeStart", namespaces=namespaces + ) + } + range_ends = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in doc_root.xpath( + ".//w:commentRangeEnd", namespaces=namespaces + ) + } + references = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in doc_root.xpath( + ".//w:commentReference", namespaces=namespaces + ) + } + + orphaned_ends = range_ends - range_starts + for comment_id in sorted( + orphaned_ends, key=lambda x: int(x) if x and x.isdigit() else 0 + ): + errors.append( + f' document.xml: commentRangeEnd id="{comment_id}" has no matching commentRangeStart' + ) + + orphaned_starts = range_starts - range_ends + for comment_id in sorted( + orphaned_starts, key=lambda x: int(x) if x and x.isdigit() else 0 + ): + errors.append( + f' document.xml: commentRangeStart id="{comment_id}" has no matching commentRangeEnd' + ) + + comment_ids = set() + if comments_xml and comments_xml.exists(): + comments_root = lxml.etree.parse(str(comments_xml)).getroot() + comment_ids = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in comments_root.xpath( + ".//w:comment", namespaces=namespaces + ) + } + + marker_ids = range_starts | range_ends | references + invalid_refs = marker_ids - comment_ids + for comment_id in sorted( + invalid_refs, key=lambda x: int(x) if x and x.isdigit() else 0 + ): + if comment_id: + errors.append( + f' document.xml: marker id="{comment_id}" references non-existent comment' + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append(f" Error parsing XML: {e}") + + if errors: + print(f"FAILED - {len(errors)} comment marker violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All comment markers properly paired") + return True + + def repair(self) -> int: + repairs = super().repair() + repairs += self.repair_durableId() + return repairs + + def repair_durableId(self) -> int: + repairs = 0 + + for xml_file in self.xml_files: + try: + content = xml_file.read_text(encoding="utf-8") + dom = defusedxml.minidom.parseString(content) + modified = False + + for elem in dom.getElementsByTagName("*"): + if not elem.hasAttribute("w16cid:durableId"): + continue + + durable_id = elem.getAttribute("w16cid:durableId") + needs_repair = False + + if xml_file.name == "numbering.xml": + try: + needs_repair = ( + self._parse_id_value(durable_id, base=10) >= 0x7FFFFFFF + ) + except ValueError: + needs_repair = True + else: + try: + needs_repair = ( + self._parse_id_value(durable_id, base=16) >= 0x7FFFFFFF + ) + except ValueError: + needs_repair = True + + if needs_repair: + value = random.randint(1, 0x7FFFFFFE) + if xml_file.name == "numbering.xml": + new_id = str(value) + else: + new_id = f"{value:08X}" + + elem.setAttribute("w16cid:durableId", new_id) + print( + f" Repaired: {xml_file.name}: durableId {durable_id} → {new_id}" + ) + repairs += 1 + modified = True + + if modified: + xml_file.write_bytes(dom.toxml(encoding="UTF-8")) + + except Exception: + pass + + return repairs + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/.claude/skills/xlsx/scripts/office/validators/pptx.py b/.claude/skills/xlsx/scripts/office/validators/pptx.py new file mode 100644 index 0000000..09842aa --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/validators/pptx.py @@ -0,0 +1,275 @@ +""" +Validator for PowerPoint presentation XML files against XSD schemas. +""" + +import re + +from .base import BaseSchemaValidator + + +class PPTXSchemaValidator(BaseSchemaValidator): + + PRESENTATIONML_NAMESPACE = ( + "http://schemas.openxmlformats.org/presentationml/2006/main" + ) + + ELEMENT_RELATIONSHIP_TYPES = { + "sldid": "slide", + "sldmasterid": "slidemaster", + "notesmasterid": "notesmaster", + "sldlayoutid": "slidelayout", + "themeid": "theme", + "tablestyleid": "tablestyles", + } + + def validate(self): + if not self.validate_xml(): + return False + + all_valid = True + if not self.validate_namespaces(): + all_valid = False + + if not self.validate_unique_ids(): + all_valid = False + + if not self.validate_uuid_ids(): + all_valid = False + + if not self.validate_file_references(): + all_valid = False + + if not self.validate_slide_layout_ids(): + all_valid = False + + if not self.validate_content_types(): + all_valid = False + + if not self.validate_against_xsd(): + all_valid = False + + if not self.validate_notes_slide_references(): + all_valid = False + + if not self.validate_all_relationship_ids(): + all_valid = False + + if not self.validate_no_duplicate_slide_layouts(): + all_valid = False + + return all_valid + + def validate_uuid_ids(self): + import lxml.etree + + errors = [] + uuid_pattern = re.compile( + r"^[\{\(]?[0-9A-Fa-f]{8}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{12}[\}\)]?$" + ) + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + + for elem in root.iter(): + for attr, value in elem.attrib.items(): + attr_name = attr.split("}")[-1].lower() + if attr_name == "id" or attr_name.endswith("id"): + if self._looks_like_uuid(value): + if not uuid_pattern.match(value): + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: ID '{value}' appears to be a UUID but contains invalid hex characters" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} UUID ID validation errors:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All UUID-like IDs contain valid hex values") + return True + + def _looks_like_uuid(self, value): + clean_value = value.strip("{}()").replace("-", "") + return len(clean_value) == 32 and all(c.isalnum() for c in clean_value) + + def validate_slide_layout_ids(self): + import lxml.etree + + errors = [] + + slide_masters = list(self.unpacked_dir.glob("ppt/slideMasters/*.xml")) + + if not slide_masters: + if self.verbose: + print("PASSED - No slide masters found") + return True + + for slide_master in slide_masters: + try: + root = lxml.etree.parse(str(slide_master)).getroot() + + rels_file = slide_master.parent / "_rels" / f"{slide_master.name}.rels" + + if not rels_file.exists(): + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: " + f"Missing relationships file: {rels_file.relative_to(self.unpacked_dir)}" + ) + continue + + rels_root = lxml.etree.parse(str(rels_file)).getroot() + + valid_layout_rids = set() + for rel in rels_root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rel_type = rel.get("Type", "") + if "slideLayout" in rel_type: + valid_layout_rids.add(rel.get("Id")) + + for sld_layout_id in root.findall( + f".//{{{self.PRESENTATIONML_NAMESPACE}}}sldLayoutId" + ): + r_id = sld_layout_id.get( + f"{{{self.OFFICE_RELATIONSHIPS_NAMESPACE}}}id" + ) + layout_id = sld_layout_id.get("id") + + if r_id and r_id not in valid_layout_rids: + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: " + f"Line {sld_layout_id.sourceline}: sldLayoutId with id='{layout_id}' " + f"references r:id='{r_id}' which is not found in slide layout relationships" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} slide layout ID validation errors:") + for error in errors: + print(error) + print( + "Remove invalid references or add missing slide layouts to the relationships file." + ) + return False + else: + if self.verbose: + print("PASSED - All slide layout IDs reference valid slide layouts") + return True + + def validate_no_duplicate_slide_layouts(self): + import lxml.etree + + errors = [] + slide_rels_files = list(self.unpacked_dir.glob("ppt/slides/_rels/*.xml.rels")) + + for rels_file in slide_rels_files: + try: + root = lxml.etree.parse(str(rels_file)).getroot() + + layout_rels = [ + rel + for rel in root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ) + if "slideLayout" in rel.get("Type", "") + ] + + if len(layout_rels) > 1: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: has {len(layout_rels)} slideLayout references" + ) + + except Exception as e: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print("FAILED - Found slides with duplicate slideLayout references:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All slides have exactly one slideLayout reference") + return True + + def validate_notes_slide_references(self): + import lxml.etree + + errors = [] + notes_slide_references = {} + + slide_rels_files = list(self.unpacked_dir.glob("ppt/slides/_rels/*.xml.rels")) + + if not slide_rels_files: + if self.verbose: + print("PASSED - No slide relationship files found") + return True + + for rels_file in slide_rels_files: + try: + root = lxml.etree.parse(str(rels_file)).getroot() + + for rel in root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rel_type = rel.get("Type", "") + if "notesSlide" in rel_type: + target = rel.get("Target", "") + if target: + normalized_target = target.replace("../", "") + + slide_name = rels_file.stem.replace( + ".xml", "" + ) + + if normalized_target not in notes_slide_references: + notes_slide_references[normalized_target] = [] + notes_slide_references[normalized_target].append( + (slide_name, rels_file) + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + for target, references in notes_slide_references.items(): + if len(references) > 1: + slide_names = [ref[0] for ref in references] + errors.append( + f" Notes slide '{target}' is referenced by multiple slides: {', '.join(slide_names)}" + ) + for slide_name, rels_file in references: + errors.append(f" - {rels_file.relative_to(self.unpacked_dir)}") + + if errors: + print( + f"FAILED - Found {len([e for e in errors if not e.startswith(' ')])} notes slide reference validation errors:" + ) + for error in errors: + print(error) + print("Each slide may optionally have its own slide file.") + return False + else: + if self.verbose: + print("PASSED - All notes slide references are unique") + return True + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/.claude/skills/xlsx/scripts/office/validators/redlining.py b/.claude/skills/xlsx/scripts/office/validators/redlining.py new file mode 100644 index 0000000..71c81b6 --- /dev/null +++ b/.claude/skills/xlsx/scripts/office/validators/redlining.py @@ -0,0 +1,247 @@ +""" +Validator for tracked changes in Word documents. +""" + +import subprocess +import tempfile +import zipfile +from pathlib import Path + + +class RedliningValidator: + + def __init__(self, unpacked_dir, original_docx, verbose=False, author="Claude"): + self.unpacked_dir = Path(unpacked_dir) + self.original_docx = Path(original_docx) + self.verbose = verbose + self.author = author + self.namespaces = { + "w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + } + + def repair(self) -> int: + return 0 + + def validate(self): + modified_file = self.unpacked_dir / "word" / "document.xml" + if not modified_file.exists(): + print(f"FAILED - Modified document.xml not found at {modified_file}") + return False + + try: + import xml.etree.ElementTree as ET + + tree = ET.parse(modified_file) + root = tree.getroot() + + del_elements = root.findall(".//w:del", self.namespaces) + ins_elements = root.findall(".//w:ins", self.namespaces) + + author_del_elements = [ + elem + for elem in del_elements + if elem.get(f"{{{self.namespaces['w']}}}author") == self.author + ] + author_ins_elements = [ + elem + for elem in ins_elements + if elem.get(f"{{{self.namespaces['w']}}}author") == self.author + ] + + if not author_del_elements and not author_ins_elements: + if self.verbose: + print(f"PASSED - No tracked changes by {self.author} found.") + return True + + except Exception: + pass + + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + try: + with zipfile.ZipFile(self.original_docx, "r") as zip_ref: + zip_ref.extractall(temp_path) + except Exception as e: + print(f"FAILED - Error unpacking original docx: {e}") + return False + + original_file = temp_path / "word" / "document.xml" + if not original_file.exists(): + print( + f"FAILED - Original document.xml not found in {self.original_docx}" + ) + return False + + try: + import xml.etree.ElementTree as ET + + modified_tree = ET.parse(modified_file) + modified_root = modified_tree.getroot() + original_tree = ET.parse(original_file) + original_root = original_tree.getroot() + except ET.ParseError as e: + print(f"FAILED - Error parsing XML files: {e}") + return False + + self._remove_author_tracked_changes(original_root) + self._remove_author_tracked_changes(modified_root) + + modified_text = self._extract_text_content(modified_root) + original_text = self._extract_text_content(original_root) + + if modified_text != original_text: + error_message = self._generate_detailed_diff( + original_text, modified_text + ) + print(error_message) + return False + + if self.verbose: + print(f"PASSED - All changes by {self.author} are properly tracked") + return True + + def _generate_detailed_diff(self, original_text, modified_text): + error_parts = [ + f"FAILED - Document text doesn't match after removing {self.author}'s tracked changes", + "", + "Likely causes:", + " 1. Modified text inside another author's or tags", + " 2. Made edits without proper tracked changes", + " 3. Didn't nest inside when deleting another's insertion", + "", + "For pre-redlined documents, use correct patterns:", + " - To reject another's INSERTION: Nest inside their ", + " - To restore another's DELETION: Add new AFTER their ", + "", + ] + + git_diff = self._get_git_word_diff(original_text, modified_text) + if git_diff: + error_parts.extend(["Differences:", "============", git_diff]) + else: + error_parts.append("Unable to generate word diff (git not available)") + + return "\n".join(error_parts) + + def _get_git_word_diff(self, original_text, modified_text): + try: + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + original_file = temp_path / "original.txt" + modified_file = temp_path / "modified.txt" + + original_file.write_text(original_text, encoding="utf-8") + modified_file.write_text(modified_text, encoding="utf-8") + + result = subprocess.run( + [ + "git", + "diff", + "--word-diff=plain", + "--word-diff-regex=.", + "-U0", + "--no-index", + str(original_file), + str(modified_file), + ], + capture_output=True, + text=True, + ) + + if result.stdout.strip(): + lines = result.stdout.split("\n") + content_lines = [] + in_content = False + for line in lines: + if line.startswith("@@"): + in_content = True + continue + if in_content and line.strip(): + content_lines.append(line) + + if content_lines: + return "\n".join(content_lines) + + result = subprocess.run( + [ + "git", + "diff", + "--word-diff=plain", + "-U0", + "--no-index", + str(original_file), + str(modified_file), + ], + capture_output=True, + text=True, + ) + + if result.stdout.strip(): + lines = result.stdout.split("\n") + content_lines = [] + in_content = False + for line in lines: + if line.startswith("@@"): + in_content = True + continue + if in_content and line.strip(): + content_lines.append(line) + return "\n".join(content_lines) + + except (subprocess.CalledProcessError, FileNotFoundError, Exception): + pass + + return None + + def _remove_author_tracked_changes(self, root): + ins_tag = f"{{{self.namespaces['w']}}}ins" + del_tag = f"{{{self.namespaces['w']}}}del" + author_attr = f"{{{self.namespaces['w']}}}author" + + for parent in root.iter(): + to_remove = [] + for child in parent: + if child.tag == ins_tag and child.get(author_attr) == self.author: + to_remove.append(child) + for elem in to_remove: + parent.remove(elem) + + deltext_tag = f"{{{self.namespaces['w']}}}delText" + t_tag = f"{{{self.namespaces['w']}}}t" + + for parent in root.iter(): + to_process = [] + for child in parent: + if child.tag == del_tag and child.get(author_attr) == self.author: + to_process.append((child, list(parent).index(child))) + + for del_elem, del_index in reversed(to_process): + for elem in del_elem.iter(): + if elem.tag == deltext_tag: + elem.tag = t_tag + + for child in reversed(list(del_elem)): + parent.insert(del_index, child) + parent.remove(del_elem) + + def _extract_text_content(self, root): + p_tag = f"{{{self.namespaces['w']}}}p" + t_tag = f"{{{self.namespaces['w']}}}t" + + paragraphs = [] + for p_elem in root.findall(f".//{p_tag}"): + text_parts = [] + for t_elem in p_elem.findall(f".//{t_tag}"): + if t_elem.text: + text_parts.append(t_elem.text) + paragraph_text = "".join(text_parts) + if paragraph_text: + paragraphs.append(paragraph_text) + + return "\n".join(paragraphs) + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/.claude/skills/xlsx/scripts/recalc.py b/.claude/skills/xlsx/scripts/recalc.py new file mode 100644 index 0000000..f472e9a --- /dev/null +++ b/.claude/skills/xlsx/scripts/recalc.py @@ -0,0 +1,184 @@ +""" +Excel Formula Recalculation Script +Recalculates all formulas in an Excel file using LibreOffice +""" + +import json +import os +import platform +import subprocess +import sys +from pathlib import Path + +from office.soffice import get_soffice_env + +from openpyxl import load_workbook + +MACRO_DIR_MACOS = "~/Library/Application Support/LibreOffice/4/user/basic/Standard" +MACRO_DIR_LINUX = "~/.config/libreoffice/4/user/basic/Standard" +MACRO_FILENAME = "Module1.xba" + +RECALCULATE_MACRO = """ + + + Sub RecalculateAndSave() + ThisComponent.calculateAll() + ThisComponent.store() + ThisComponent.close(True) + End Sub +""" + + +def has_gtimeout(): + try: + subprocess.run( + ["gtimeout", "--version"], capture_output=True, timeout=1, check=False + ) + return True + except (FileNotFoundError, subprocess.TimeoutExpired): + return False + + +def setup_libreoffice_macro(): + macro_dir = os.path.expanduser( + MACRO_DIR_MACOS if platform.system() == "Darwin" else MACRO_DIR_LINUX + ) + macro_file = os.path.join(macro_dir, MACRO_FILENAME) + + if ( + os.path.exists(macro_file) + and "RecalculateAndSave" in Path(macro_file).read_text() + ): + return True + + if not os.path.exists(macro_dir): + subprocess.run( + ["soffice", "--headless", "--terminate_after_init"], + capture_output=True, + timeout=10, + env=get_soffice_env(), + ) + os.makedirs(macro_dir, exist_ok=True) + + try: + Path(macro_file).write_text(RECALCULATE_MACRO) + return True + except Exception: + return False + + +def recalc(filename, timeout=30): + if not Path(filename).exists(): + return {"error": f"File {filename} does not exist"} + + abs_path = str(Path(filename).absolute()) + + if not setup_libreoffice_macro(): + return {"error": "Failed to setup LibreOffice macro"} + + cmd = [ + "soffice", + "--headless", + "--norestore", + "vnd.sun.star.script:Standard.Module1.RecalculateAndSave?language=Basic&location=application", + abs_path, + ] + + if platform.system() == "Linux": + cmd = ["timeout", str(timeout)] + cmd + elif platform.system() == "Darwin" and has_gtimeout(): + cmd = ["gtimeout", str(timeout)] + cmd + + result = subprocess.run(cmd, capture_output=True, text=True, env=get_soffice_env()) + + if result.returncode != 0 and result.returncode != 124: + error_msg = result.stderr or "Unknown error during recalculation" + if "Module1" in error_msg or "RecalculateAndSave" not in error_msg: + return {"error": "LibreOffice macro not configured properly"} + return {"error": error_msg} + + try: + wb = load_workbook(filename, data_only=True) + + excel_errors = [ + "#VALUE!", + "#DIV/0!", + "#REF!", + "#NAME?", + "#NULL!", + "#NUM!", + "#N/A", + ] + error_details = {err: [] for err in excel_errors} + total_errors = 0 + + for sheet_name in wb.sheetnames: + ws = wb[sheet_name] + for row in ws.iter_rows(): + for cell in row: + if cell.value is not None and isinstance(cell.value, str): + for err in excel_errors: + if err in cell.value: + location = f"{sheet_name}!{cell.coordinate}" + error_details[err].append(location) + total_errors += 1 + break + + wb.close() + + result = { + "status": "success" if total_errors == 0 else "errors_found", + "total_errors": total_errors, + "error_summary": {}, + } + + for err_type, locations in error_details.items(): + if locations: + result["error_summary"][err_type] = { + "count": len(locations), + "locations": locations[:20], + } + + wb_formulas = load_workbook(filename, data_only=False) + formula_count = 0 + for sheet_name in wb_formulas.sheetnames: + ws = wb_formulas[sheet_name] + for row in ws.iter_rows(): + for cell in row: + if ( + cell.value + and isinstance(cell.value, str) + and cell.value.startswith("=") + ): + formula_count += 1 + wb_formulas.close() + + result["total_formulas"] = formula_count + + return result + + except Exception as e: + return {"error": str(e)} + + +def main(): + if len(sys.argv) < 2: + print("Usage: python recalc.py [timeout_seconds]") + print("\nRecalculates all formulas in an Excel file using LibreOffice") + print("\nReturns JSON with error details:") + print(" - status: 'success' or 'errors_found'") + print(" - total_errors: Total number of Excel errors found") + print(" - total_formulas: Number of formulas in the file") + print(" - error_summary: Breakdown by error type with locations") + print(" - #VALUE!, #DIV/0!, #REF!, #NAME?, #NULL!, #NUM!, #N/A") + sys.exit(1) + + filename = sys.argv[1] + timeout = int(sys.argv[2]) if len(sys.argv) > 2 else 30 + + result = recalc(filename, timeout) + print(json.dumps(result, indent=2)) + + +if __name__ == "__main__": + main()