Update to AI DevKit

{
  "description": "AI DevKit · Document a code entry point with structured analysis, dependency mapping, and saved knowledge docs. Use when users ask to document, understand, or map code for a module, file, folder, function, or API.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 321
    }
  ],
  "name": "document-code",
  "skill_md_contents": "---\nname: document-code\ndescription: AI DevKit · Document a code entry point with structured analysis, dependency mapping, and saved knowledge docs. Use when users ask to document, understand, or map code for a module, file, folder, function, or API.\n---\n\n# Code Documentation Assistant\n\nBuild structured understanding of code entry points with an analysis-first workflow.\n\n## Hard Rule\n- Do not create documentation until the entry point is validated and analysis is complete.\n\n## Workflow\n\n1. Gather & Validate\n- Confirm entry point (file, folder, function, API), purpose, and desired depth.\n- Verify it exists; resolve ambiguity or suggest alternatives if not found.\n- Search for existing knowledge before analyzing: `npx ai-devkit@latest memory search --query \"<entry point name or purpose>\"`\n\n2. Collect Source Context\n- Summarize purpose, exports, key patterns.\n- Folders: list structure, highlight key modules.\n- Functions/APIs: capture signature, parameters, return values, error handling.\n\n3. Analyze Dependencies\n- Build dependency view up to depth 3, track visited nodes to avoid loops.\n- Categorize: imports, function calls, services, external packages.\n- Exclude external systems or generated code.\n\n4. Synthesize\n- Overview (purpose, language, high-level behavior).\n- Core logic, execution flow, patterns.\n- Error handling, performance, security considerations.\n- Improvements or risks discovered during analysis.\n\n5. Create Documentation\n- Normalize name to kebab-case (`calculateTotalPrice` → `calculate-total-price`).\n- Create `docs/ai/implementation/knowledge-{name}.md` using the Output Template — this is the source of truth.\n- Include mermaid diagrams when they clarify flows or relationships.\n\n6. Offer HTML Artifact\n- After the markdown is written, ask the user once: \"Also generate an HTML artifact for easier scanning? (y/N)\".\n- If yes, generate sibling `docs/ai/implementation/knowledge-{name}.html` per the HTML Artifact spec. Regenerate from the markdown on subsequent runs; never hand-edit.\n- If no or no response, stop here — markdown alone is a complete result.\n\n## HTML Artifact\n\nGenerated only when the user opts in at step 6. A self-contained HTML file optimized for scanning, not reference reading. Complements the markdown — does not replace it.\n\nConstraints:\n- Single file. Inline CSS. No build step. Only external asset allowed is mermaid via CDN (`https://cdn.jsdelivr.net/npm/mermaid/dist/mermaid.min.js`).\n- Card-based grid layout, not a long scroll. The reader should capture structure at a glance.\n- Responsive down to laptop width. Print-friendly.\n- No interactivity beyond collapsible deep-dives and mermaid pan/zoom.\n\nSection mapping (from the Output Template):\n- Overview → hero card: title, one-line purpose, language/type badges.\n- Implementation Details → grid of sectioned cards with short bullets, not prose.\n- Dependencies → graph card (mermaid) plus a categorized list (imports, calls, services, external).\n- Visual Diagrams → full-width rendered mermaid blocks.\n- Additional Insights → callout boxes, color-coded by kind (info, warning, risk).\n- Next Steps → checklist card.\n- Metadata → compact footer (date, depth, files touched).\n\n## Red Flags and Rationalizations\n\n| Rationalization | Why It's Wrong | Do Instead |\n|---|---|---|\n| \"I already understand this code\" | Understanding ≠ documented understanding | Write it down, then verify |\n| \"The code is self-documenting\" | Future readers lack your current context | Capture the why, not just the what |\n| \"Dependencies are obvious\" | Implicit dependencies cause surprises | Map them explicitly to depth 3 |\n\n## Validation\n- Documentation covers all Output Template sections.\n- If an HTML artifact was generated, it opens standalone in a browser, renders mermaid, and reflects the markdown content (no drift).\n- Summarize key insights, open questions, and related areas for deeper dives.\n- Confirm file path(s) and remind to commit.\n\n## Output Template\n- Overview\n- Implementation Details\n- Dependencies\n- Visual Diagrams (mermaid)\n- Additional Insights\n- Metadata (date, depth, files touched)\n- Next Steps\n"
}