[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6E0FEZ45AT1S0YR8RG422J7":3,"skill-same:01M6E0FEZ45AT1S0YR8RG422J7":69},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":14,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":46,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M6E0FEZ45AT1S0YR8RG422J7","rag-coverage",null,"Audit corpus distribution by source type and repo; identify coverage gaps and underindexed topics. Answers what's missing from RAG.","LucasSantana-Dev\u002Fforgekit","LucasSantana-Dev","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F98131142?v=4","01M6E038X8H7VE9GCEJP9PT5CA","Lucas Santana","01M6E0391WB0JYZTWXEBR9WSXA",1,"MIT","https:\u002F\u002Fgithub.com\u002FLucasSantana-Dev\u002Fforgekit\u002Fblob\u002Fmain\u002Fpackages\u002Fcatalog\u002Fcatalog\u002Fskills\u002Fadt-rag-coverage\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30],"rag","coverage","rag coverage","coverage gaps","audit","repo","distribution","type","missing","source","topics","gaps","2026-11-10 10:12:30",false,"---\nname: rag-coverage\ndescription: Audit corpus distribution by source type and repo; identify coverage gaps and underindexed topics. Answers what's missing from RAG.\ntriggers:\n  - rag coverage\n  - corpus audit\n  - rag gaps\n  - coverage audit\n  - what's missing from rag\n---\n\n# RAG Coverage\n\nAudit what's indexed and what's missing. Use coverage reports to plan curation and decide between incremental fixes and full rebuilds.\n\n## Coverage audit\n\nRun the weekly report to see coverage distribution:\n\n```bash\ncd ~\u002F.claude\u002Frag-index\nvenv\u002Fbin\u002Fpython report.py\n```\n\nRead the coverage summary:\n\n```bash\ncat ~\u002F.claude\u002Frag-index\u002Fweekly.md | grep -A 50 \"Coverage by source type\"\n```\n\nExample output:\n\n```\nCoverage by source type:\n  skills: 539 chunks (≥500 target: PASS)\n  handoffs: 259 chunks (≥200 target: PASS)\n  standards: 54 chunks (≥50 target: PASS)\n  code: 1847 chunks (scales with repo)\n  plans: 198 chunks\n  codex: 31 chunks (low)\n  repo-docs: 127 chunks\n  commit: 156 chunks\n  claude-mem: 203 chunks\n  spec: 89 chunks\n  changelog: 52 chunks\n  TOTAL: 14,355 chunks\n```\n\n## Coverage by source type\n\nQuery the index directly to see distribution:\n\n```bash\nsqlite3 ~\u002F.claude\u002Frag-index\u002Findex.sqlite \u003C\u003C 'EOF'\nSELECT source_type, COUNT(*) as chunk_count, \n       ROUND(AVG(LENGTH(text)), 0) as avg_size,\n       MIN(LENGTH(text)) as min_size,\n       MAX(LENGTH(text)) as max_size\nFROM chunks\nGROUP BY source_type\nORDER BY COUNT(*) DESC;\nEOF\n```\n\n**Healthy coverage targets:**\n\n| Source Type | Min Chunks | Reason |\n|-------------|-----------|--------|\n| skills | 500 | Comprehensive skill docs |\n| handoffs | 200 | Context summaries, transition notes |\n| code | 500+ | Scales with repo size and importance |\n| standards | 50 | Style guides, conventions |\n| plans | 100 | Roadmaps, architecture |\n| codex | 50 | Templates, patterns, how-tos |\n| claude-mem | 100 | Memory snapshots, context packs |\n| repo-docs | 100 | READMEs, architecture docs |\n| spec | 50 | Design specs, RFCs |\n| commit | 100 | Recent commit messages for context |\n| changelog | 30 | Release notes, version history |\n\n## Coverage by repository\n\nFind which repos are well-indexed:\n\n```bash\nsqlite3 ~\u002F.claude\u002Frag-index\u002Findex.sqlite \u003C\u003C 'EOF'\nSELECT repo, COUNT(*) as chunk_count, COUNT(DISTINCT path) as file_count\nFROM chunks\nWHERE repo IS NOT NULL\nGROUP BY repo\nORDER BY COUNT(*) DESC;\nEOF\n```\n\nRepos with \u003C50 chunks likely have gaps. Look for:\n- Missing source globs in build.py\n- Shallow documentation\n- Newly added repos not yet in the index\n\n## Coverage by source type + repo combo\n\nFind niche coverage gaps:\n\n```bash\nsqlite3 ~\u002F.claude\u002Frag-index\u002Findex.sqlite \u003C\u003C 'EOF'\nSELECT source_type, repo, COUNT(*) as chunk_count\nFROM chunks\nWHERE repo IS NOT NULL\nGROUP BY source_type, repo\nHAVING COUNT(*) \u003C 20\nORDER BY source_type, COUNT(*) DESC;\nEOF\n```\n\n## Find zero-hit patterns\n\nQueries that return no results indicate coverage gaps. Check weekly report:\n\n```bash\ncat ~\u002F.claude\u002Frag-index\u002Fweekly.md | grep -A 20 \"Zero-hit queries\"\n```\n\nExample:\n\n```\nZero-hit queries (no chunks retrieved):\n  \"authentication refresh token\" — no auth docs indexed\n  \"database migration strategy\" — missing infra\u002Fdb standards\n  \"component prop validation\" — missing React patterns in codex\n  \"error handling middleware\" — missing code examples in standards\n```\n\nFor each zero-hit query:\n1. Identify the missing topic\n2. Write or curate missing docs (see `adt-rag-curate`)\n3. Add source globs if code is involved (see `adt-rag-curate`)\n4. Incremental reindex\n5. Re-run the query to verify\n\n## Gaps by topic\n\nManual audit for missing categories:\n\n```bash\nsqlite3 ~\u002F.claude\u002Frag-index\u002Findex.sqlite \u003C\u003C 'EOF'\nSELECT path, source_type, COUNT(*) as chunk_count\nFROM chunks\nWHERE source_type IN ('standards', 'codex', 'plans')\nGROUP BY path\nORDER BY source_type, COUNT(*) DESC;\nEOF\n```\n\nIf you see topics with 1–2 chunks, they may be truncated or incomplete. Check with `adt-rag-inspect`.\n\n## Coverage decision tree\n\n| Situation | Detection | Action | Time |\n|-----------|-----------|--------|------|\n| Source type \u003C50% of target | Weekly report | Write missing docs + curate | 30 min – 2 hrs |\n| Repo has \u003C50 chunks | rag-coverage query | Add source globs to build.py + reindex | 20 min |\n| Zero-hit queries | Weekly report or user feedback | Identify missing topic, curate, reindex | 30 min |\n| Many tiny chunks (\u003C100 chars) | adt-rag-inspect | Rebuild with new chunk-size config | 1 hr |\n| Stale\u002Fmissing chunks | adt-rag-drift | Delete or reindex; see adt-rag-drift | 10 min |\n| Widespread gaps (>100 chunks missing) | Weekly report | Full rebuild | 2–5 min |\n\n## Post-coverage audit workflow\n\n1. **Run report:**\n\n```bash\ncd ~\u002F.claude\u002Frag-index\nvenv\u002Fbin\u002Fpython report.py\n```\n\n2. **Check targets:**\n\n```bash\ncat ~\u002F.claude\u002Frag-index\u002Fweekly.md | grep -A 20 \"Coverage by source type\"\n```\n\n3. **For each gap:**\n   - If missing doc → write and incremental reindex (see `adt-rag-curate`)\n   - If undercovered repo → add source globs and reindex\n   - If zero-hit query → curate related content\n\n4. **Re-run report** after curation:\n\n```bash\nvenv\u002Fbin\u002Fpython report.py\n```\n\n5. **Verify** with test queries:\n\n```bash\nvenv\u002Fbin\u002Fpython query.py \"previously zero-hit query\" --top 5\n```\n\n## Coverage maintenance cadence\n\n- **Weekly**: Run `report.py` to track trends\n- **After curation**: Re-run `report.py` to verify improvement\n- **Monthly**: Audit zero-hit queries and plan curation sprints\n- **Quarterly**: Review source type targets; adjust if project scope changes\n- **Post-major-changes**: Full rebuild if repo structure or doc locations change\n\n## See also\n\n- `adt-rag-curate` — fill coverage gaps\n- `adt-rag-quality` — audit retrieval quality (separate from coverage)\n- `adt-rag-inspect` — examine chunks in detail\n- `adt-rag-drift` — find stale or missing chunks\n- `adt-rag-index-rebuild` — full rebuild if coverage strategy changes\n","# RAG Coverage\n\nAudit what's indexed and what's missing. Use coverage reports to plan curation and decide between incremental fixes and full rebuilds.\n\n## Coverage audit\n\nRun the weekly report to see coverage distribution:\n\n```bash\ncd ~\u002F.claude\u002Frag-index\nvenv\u002Fbin\u002Fpython report.py\n```\n\nRead the coverage summary:\n\n```bash\ncat ~\u002F.claude\u002Frag-index\u002Fweekly.md | grep -A 50 \"Coverage by source type\"\n```\n\nExample output:\n\n```\nCoverage by source type:\n  skills: 539 chunks (≥500 target: PASS)\n  handoffs: 259 chunks (≥200 target: PASS)\n  standards: 54 chunks (≥50 target: PASS)\n  code: 1847 chunks (scales with repo)\n  plans: 198 chunks\n  codex: 31 chunks (low)\n  repo-docs: 127 chunks\n  commit: 156 chunks\n  claude-mem: 203 chunks\n  spec: 89 chunks\n  changelog: 52 chunks\n  TOTAL: 14,355 chunks\n```\n\n## Coverage by source type\n\nQuery the index directly to see distribution:\n\n```bash\nsqlite3 ~\u002F.claude\u002Frag-index\u002Findex.sqlite \u003C\u003C 'EOF'\nSELECT source_type, COUNT(*) as chunk_count, \n       ROUND(AVG(LENGTH(text)), 0) as avg_size,\n       MIN(LENGTH(text)) as min_size,\n       MAX(LENGTH(text)) as max_size\nFROM chunks\nGROUP BY source_type\nORDER BY COUNT(*) DESC;\nEOF\n```\n\n**Healthy coverage targets:**\n\n| Source Type | Min Chunks | Reason |\n|-------------|-----------|--------|\n| skills | 500 | Comprehensive skill docs |\n| handoffs | 200 | Context summaries, transition notes |\n| code | 500+ | Scales with repo size and importance |\n| standards | 50 | Style guides, conventions |\n| plans | 100 | Roadmaps, architecture |\n| codex | 50 | Templates, patterns, how-tos |\n| claude-mem | 100 | Memory snapshots, context packs |\n| repo-docs | 100 | READMEs, architecture docs |\n| spec | 50 | Design specs, RFCs |\n| commit | 100 | Recent commit messages for context |\n| changelog | 30 | Release notes, version history |\n\n## Coverage by repository\n\nFind which repos are well-indexed:\n\n```bash\nsqlite3 ~\u002F.claude\u002Frag-index\u002Findex.sqlite \u003C\u003C 'EOF'\nSELECT repo, COUNT(*) as chunk_count, COUNT(DISTINCT path) as file_count\nFROM chunks\nWHERE repo IS NOT NULL\nGROUP BY repo\nORDER BY COUNT(*) DESC;\nEOF\n```\n\nRepos with \u003C50 chunks likely have gaps. Look for:\n- Missing source globs in build.py\n- Shallow documentation\n- Newly added repos not yet in the index\n\n## Coverage by source type + repo combo\n\nFind niche coverage gaps:\n\n```bash\nsqlite3 ~\u002F.claude\u002Frag-index\u002Findex.sqlite \u003C\u003C 'EOF'\nSELECT source_type, repo, COUNT(*) as chunk_count\nFROM chunks\nWHERE repo IS NOT NULL\nGROUP BY source_type, repo\nHAVING COUNT(*) \u003C 20\nORDER BY source_type, COUNT(*) DESC;\nEOF\n```\n\n## Find zero-hit patterns\n\nQueries that return no results indicate coverage gaps. Check weekly report:\n\n```bash\ncat ~\u002F.claude\u002Frag-index\u002Fweekly.md | grep -A 20 \"Zero-hit queries\"\n```\n\nExample:\n\n```\nZero-hit queries (no chunks retrieved):\n  \"authentication refresh token\" — no auth docs indexed\n  \"database migration strategy\" — missing infra\u002Fdb standards\n  \"component prop validation\" — missing React patterns in codex\n  \"error handling middleware\" — missing code examples in standards\n```\n\nFor each zero-hit query:\n1. Identify the missing topic\n2. Write or curate missing docs (see `adt-rag-curate`)\n3. Add source globs if code is involved (see `adt-rag-curate`)\n4. Incremental reindex\n5. Re-run the query to verify\n\n## Gaps by topic\n\nManual audit for missing categories:\n\n```bash\nsqlite3 ~\u002F.claude\u002Frag-index\u002Findex.sqlite \u003C\u003C 'EOF'\nSELECT path, source_type, COUNT(*) as chunk_count\nFROM chunks\nWHERE source_type IN ('standards', 'codex', 'plans')\nGROUP BY path\nORDER BY source_type, COUNT(*) DESC;\nEOF\n```\n\nIf you see topics with 1–2 chunks, they may be truncated or incomplete. Check with `adt-rag-inspect`.\n\n## Coverage decision tree\n\n| Situation | Detection | Action | Time |\n|-----------|-----------|--------|------|\n| Source type \u003C50% of target | Weekly report | Write missing docs + curate | 30 min – 2 hrs |\n| Repo has \u003C50 chunks | rag-coverage query | Add source globs to build.py + reindex | 20 min |\n| Zero-hit queries | Weekly report or user feedback | Identify missing topic, curate, reindex | 30 min |\n| Many tiny chunks (\u003C100 chars) | adt-rag-inspect | Rebuild with new chunk-size config | 1 hr |\n| Stale\u002Fmissing chunks | adt-rag-drift | Delete or reindex; see adt-rag-drift | 10 min |\n| Widespread gaps (>100 chunks missing) | Weekly report | Full rebuild | 2–5 min |\n\n## Post-coverage audit workflow\n\n1. **Run report:**\n\n```bash\ncd ~\u002F.claude\u002Frag-index\nvenv\u002Fbin\u002Fpython report.py\n```\n\n2. **Check targets:**\n\n```bash\ncat ~\u002F.claude\u002Frag-index\u002Fweekly.md | grep -A 20 \"Coverage by source type\"\n```\n\n3. **For each gap:**\n   - If missing doc → write and incremental reindex (see `adt-rag-curate`)\n   - If undercovered repo → add source globs and reindex\n   - If zero-hit query → curate related content\n\n4. **Re-run report** after curation:\n\n```bash\nvenv\u002Fbin\u002Fpython report.py\n```\n\n5. **Verify** with test queries:\n\n```bash\nvenv\u002Fbin\u002Fpython query.py \"previously zero-hit query\" --top 5\n```\n\n## Coverage maintenance cadence\n\n- **Weekly**: Run `report.py` to track trends\n- **After curation**: Re-run `report.py` to verify improvement\n- **Monthly**: Audit zero-hit queries and plan curation sprints\n- **Quarterly**: Review source type targets; adjust if project scope changes\n- **Post-major-changes**: Full rebuild if repo structure or doc locations change\n\n## See also\n\n- `adt-rag-curate` — fill coverage gaps\n- `adt-rag-quality` — audit retrieval quality (separate from coverage)\n- `adt-rag-inspect` — examine chunks in detail\n- `adt-rag-drift` — find stale or missing chunks\n- `adt-rag-index-rebuild` — full rebuild if coverage strategy changes\n",{"name":5,"triggers":36,"description":7},[21,37,38,39,40],"corpus audit","rag gaps","coverage audit","what's missing from rag","main","f2e470f7ead3f9982aee7aadc1aa5bef5d4db833","packages\u002Fcatalog\u002Fcatalog\u002Fskills\u002Fadt-rag-coverage","https:\u002F\u002Fgithub.com\u002FLucasSantana-Dev\u002Fforgekit","https:\u002F\u002Fgithub.com\u002FLucasSantana-Dev","https:\u002F\u002Flucassantana.tech","Senior engineer. AI agent tooling and evals on Node\u002FTS backends. Brazil, UTC-3.","2026-11-11 07:05:28",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add LucasSantana-Dev\u002Fforgekit --skill rag-coverage",{"tool":55,"command":56},"bunx","bunx skills add LucasSantana-Dev\u002Fforgekit --skill rag-coverage",{"tool":58,"command":59},"pnpm","pnpm dlx skills add LucasSantana-Dev\u002Fforgekit --skill rag-coverage","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLucasSantana-Dev\u002Fforgekit\u002Fblob\u002Fmain\u002Fpackages\u002Fcatalog\u002Fcatalog\u002Fskills\u002Fadt-rag-coverage\u002FSKILL.md",true,[63],{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"manifest.json","REFERENCE","参考文档",919,"https:\u002F\u002Fgithub.com\u002FLucasSantana-Dev\u002Fforgekit\u002Fblob\u002Fmain\u002Fpackages\u002Fcatalog\u002Fcatalog\u002Fskills\u002Fadt-rag-coverage\u002Fmanifest.json",[70,101,133,156,165,183],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":81,"publishedAt":31},"01M6WR9SQGQ5WDEJY9HH3T93E8","token-audit","Audit historical Claude Code token usage from JSONL session files — shows total spend, cache hit rates, top costly sessions, weekly trends, and where tokens are going. Run after heavy sessions or weekly to measure optimization impact. Answers how many tokens a session used, how expensive was that session, session cost, and token usage report.","https:\u002F\u002Fgithub.com\u002FLucasSantana-Dev\u002Fforgekit\u002Fblob\u002Fmain\u002Fpackages\u002Fcatalog\u002Fcatalog\u002Fskills\u002Fadt-token-audit\u002FSKILL.md",[76],{"categoryNo":77,"categoryName":78,"taxonomyType":79,"taxonomyTypeDesc":80},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[23,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100],"token","token audit","session","rate","weekly","top","usage","jsonl","usage report","impact","tokens","files","cost","how","Optimization","cache","code","run","sessions",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":112,"publishedAt":31},"01M6WR919T3NGWMZ5R5XKWX9KN","smart-model-route","Auto-classify prompt complexity via Haiku (with heuristic fallback) and inject model routing hints for Agent tool calls. Wired as a UserPromptSubmit hook — fires on every prompt, routes low tasks to Haiku, standard to Sonnet, complex to Sonnet with thorough reasoning, and critical (security\u002Farch\u002Fmigrations) to Opus. Handles model selection, for example choose model by task complexity.","https:\u002F\u002Fgithub.com\u002FLucasSantana-Dev\u002Fforgekit\u002Fblob\u002Fmain\u002Fpackages\u002Fcatalog\u002Fcatalog\u002Fskills\u002Fadt-smart-model-route\u002FSKILL.md",[107],{"categoryNo":108,"categoryName":109,"taxonomyType":110,"taxonomyTypeDesc":111},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132],"smart model route","route","model route","model","security","model selection","tasks","critical","arch","classify","selection","fallback","complexity","auto","opus","haiku","choose","hook","agent tool","sonnet",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":140,"publishedAt":31},"01M6WR8TMGS9G79DFTX0K1ZA8T","smart-commands","Decision guide for when to proactively use Claude Code slash commands — \u002Fthink, \u002Fmodel, \u002Fcompact, \u002Fclear. Use when choosing whether to invoke a command before or during a task, or when a complexity-classifier hook has flagged a task as high or critical. Pairs with the complexity-classifier UserPromptSubmit hook. Answers when to compact, should I switch models, and whether to use extended thinking. Use to pick the right \u002Fmodel command and switch model.","https:\u002F\u002Fgithub.com\u002FLucasSantana-Dev\u002Fforgekit\u002Fblob\u002Fmain\u002Fpackages\u002Fcatalog\u002Fcatalog\u002Fskills\u002Fadt-smart-commands\u002FSKILL.md",[139],{"categoryNo":77,"categoryName":78,"taxonomyType":79,"taxonomyTypeDesc":80},[141,142,143,144,145,146,130,120,147,148,149,150,125,151,152,153,154,155,116,98],"smart commands","commands","when","as","use","for","compact","thinking","switch","classifier","invoke","guide","command","decision","pick",{"skillNo":157,"name":158,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":161,"publishedAt":31},"01M6E0ZGQ78S4SE6X6RCN1PR9A","spec-ship","https:\u002F\u002Fgithub.com\u002FLucasSantana-Dev\u002Fforgekit\u002Fblob\u002Fmain\u002Fpackages\u002Fcore\u002Fkit\u002Fspecs\u002Fskills\u002Fspec-ship\u002FSKILL.md",[],[162,163,164],"spec","ship","spec ship",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":171,"publishedAt":31},"01M6E0ZD27S87Z954JTHECWG34","spec-new","Create a committed per-feature spec under `docs\u002Fspecs\u002FYYYY-MM-DD-\u003Cslug>\u002F{spec,tasks}.md` with frontmatter (status, created, owner, pr, tags). Promotes an ephemeral `.claude\u002Fplans\u002F\u003Cname>.md` into a persistent, searchable artifact. Use when starting a feature that's larger than a one-shot PR.","https:\u002F\u002Fgithub.com\u002FLucasSantana-Dev\u002Fforgekit\u002Fblob\u002Fmain\u002Fpackages\u002Fcore\u002Fkit\u002Fspecs\u002Fskills\u002Fspec-new\u002FSKILL.md",[],[172,162,173,145,174,175,119,176,177,178,179,180,181,182],"spec new","artifact","dd","create","pr","status","docs","feature","tags","name","plans",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":192,"publishedAt":31},"01M6E0Z9B5YE1G4NM05JPNVWMK","roadmap-refresh","Regenerate `docs\u002Froadmap.md` for a repo from all specs under `docs\u002Fspecs\u002F` + their frontmatter (status, tags, pr). Produces Now\u002FNext\u002FRecently-shipped sections. Run after creating \u002F shipping a spec, or at the start of a new session for orientation.","https:\u002F\u002Fgithub.com\u002FLucasSantana-Dev\u002Fforgekit\u002Fblob\u002Fmain\u002Fpackages\u002Fcore\u002Fkit\u002Fspecs\u002Fskills\u002Froadmap-refresh\u002FSKILL.md",[189],{"categoryNo":190,"categoryName":191,"taxonomyType":79,"taxonomyTypeDesc":80},"01JBSEEDCAT000000000000031","产品经理",[193,194,195,196,180,197,84,24,198,199,200,99,176,177,178,162],"roadmap refresh","roadmap","refresh","next","now","new session","start","shipping"]