[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6EGFSEFV2TMTN82ZZCEZ998":3,"skill-same:01M6EGFSEFV2TMTN82ZZCEZ998":65},{"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":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":45,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":48,"ownerDescription":49,"updatedAt":50,"install":51,"resources":64},"01M6EGFSEFV2TMTN82ZZCEZ998","ln-610-docs-auditor",null,"Coordinates 4 documentation audit workers (structure, semantic, fact-check, code comments). Delegates parallel audits, aggregates into docs\u002Fproject\u002Fdocs_audit.md.","levalencia\u002Fagent-god-mode","levalencia","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6962857?v=4","01M6EB0FZZ4BPQPC4HET4QY6NM","Luis Valencia ","01M6EB0G4HWHPWW0H9X7QKSAHP",3,"MIT","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fln-610-docs-auditor\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35],"ln 610 docs auditor","docs","check","semantic","project","aggregates","structure","coordinates","workers","read","grep","parallel","code comments","Bash","audit","code","documentation","2026-11-10 10:12:30",false,"---\nname: ln-610-docs-auditor\ndescription: \"Coordinates 4 documentation audit workers (structure, semantic, fact-check, code comments). Delegates parallel audits, aggregates into docs\u002Fproject\u002Fdocs_audit.md.\"\nallowed-tools: Read, Grep, Glob, Bash, Skill\nlicense: MIT\n---\n\n> **Paths:** File paths (`shared\u002F`, `references\u002F`, `..\u002Fln-*`) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root.\n\n# Documentation Auditor (L2 Coordinator)\n\nCoordinates 4 specialized audit workers to perform comprehensive documentation quality analysis.\n\n## Purpose & Scope\n\n- **Coordinates 4 audit workers** running in parallel:\n  - ln-611 (documentation structure) — 1 invocation\n  - ln-612 (semantic content) — N invocations (per target document)\n  - ln-613 (code comments) — 1 invocation\n  - ln-614 (fact verification) — 1 invocation\n- Detect project type + tech stack ONCE\n- Pass shared context to all workers (token-efficient)\n- Aggregate worker results into single consolidated report\n- Write report to `docs\u002Fproject\u002Fdocs_audit.md` (file-based, no task creation)\n- Manual invocation by user or called by ln-100-documents-pipeline\n\n## Workflow\n\n1) **Discovery:** Detect project type, tech stack, scan .md files\n2) **Context Build:** Build contextStore with output_dir, project_root, tech_stack\n3) **Prepare Output:** Create output directory\n4) **Delegate:** Invoke 4 workers in parallel\n5) **Aggregate:** Collect worker results, calculate overall score\n6) **Context Validation:** Post-filter findings\n7) **Write Report:** Save to `docs\u002Fproject\u002Fdocs_audit.md`\n8) **Results Log:** Append trend row\n9) **Cleanup:** Delete worker files\n\n## Phase 1: Discovery\n\n**Load project metadata:**\n- `CLAUDE.md` — root of documentation hierarchy\n- `docs\u002FREADME.md` — documentation index\n- Package manifests: `package.json`, `requirements.txt`, `go.mod`, `Cargo.toml`\n- Existing docs in `docs\u002Fproject\u002F`\n\n**Extract:**\n- Programming language(s)\n- Major frameworks\u002Flibraries\n- List of `.md` files in project (for ln-611 hierarchy check)\n- Target documents for semantic audit (for ln-612)\n\n**Target documents for ln-612:**\n```\nFOR doc IN [CLAUDE.md, docs\u002FREADME.md, docs\u002Fdocumentation_standards.md,\n            docs\u002Fprinciples.md, docs\u002Fproject\u002F*.md]:\n  IF doc exists AND doc NOT IN [docs\u002Ftasks\u002F*, docs\u002Freference\u002F*, docs\u002Fpresentation\u002F*]:\n    semantic_targets.append(doc)\n```\n\n## Phase 2: Build contextStore\n\n```json\n{\n  \"tech_stack\": {\"language\": \"...\", \"frameworks\": [...]},\n  \"project_root\": \"...\",\n  \"output_dir\": \"docs\u002Fproject\u002F.audit\u002Fln-610\u002F{YYYY-MM-DD}\"\n}\n```\n\nWhere `{YYYY-MM-DD}` is current date (e.g., `2026-03-01`).\n\n## Phase 3: Prepare Output\n\n```bash\nmkdir -p {output_dir}\n```\n\nWorker files are cleaned up after consolidation (see Phase 9).\n\n## Phase 4: Delegate to Workers\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Ftask_delegation_pattern.md`.\n\nAll workers in PARALLEL via Agent tool:\n\n| Worker | Invocations | Output |\n|--------|-------------|--------|\n| ln-611-docs-structure-auditor | 1 | `{output_dir}\u002F611-structure.md` |\n| ln-612-semantic-content-auditor | N (per target document) | `{output_dir}\u002F612-semantic-{doc-slug}.md` |\n| ln-613-code-comments-auditor | 1 | `{output_dir}\u002F613-code-comments.md` |\n| ln-614-docs-fact-checker | 1 | `{output_dir}\u002F614-fact-checker.md` |\n\nln-614 receives only `contextStore` and discovers `.md` files internally. Workers follow the shared file-based audit contract and return compact summaries with report path, score, and severity counts.\n\n**Invocation:**\n```javascript\n\u002F\u002F Global workers (ln-611, ln-613, ln-614) — 1 invocation each:\nFOR EACH worker IN [ln-611, ln-613, ln-614]:\n  Agent(description: \"Docs audit via \" + worker,\n       prompt: \"Execute audit worker.\n\nStep 1: Invoke worker:\n  Skill(skill: \\\"\" + worker + \"\\\")\n\nCONTEXT:\n\" + JSON.stringify(contextStore),\n       subagent_type: \"general-purpose\")\n\n\u002F\u002F Per-document worker (ln-612) — N invocations:\nFOR EACH doc IN semantic_targets:\n  doc_context = { ...contextStore, doc_path: doc }\n  Agent(description: \"Semantic audit \" + doc + \" via ln-612\",\n       prompt: \"Execute audit worker.\n\nStep 1: Invoke worker:\n  Skill(skill: \\\"ln-612-semantic-content-auditor\\\")\n\nCONTEXT:\n\" + JSON.stringify(doc_context),\n       subagent_type: \"general-purpose\")\n```\n\n## Phase 5: Aggregate Results\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Faudit_coordinator_aggregation.md`.\n\nUse the shared aggregation pattern for summary parsing, worker report reads, severity rollups, and final report assembly.\n\nCategory weights:\n\n| Category | Source | Weight |\n|----------|--------|--------|\n| Documentation Structure | ln-611 | 25% |\n| Semantic Content | ln-612 (avg across docs) | 30% |\n| Code Comments | ln-613 | 20% |\n| Fact Accuracy | ln-614 | 25% |\n\nCalculate overall score as the weighted average of the 4 categories above.\n\n## Phase 6: Context Validation (Post-Filter)\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fcontext_validation.md`\n\nApply Rule 1 + documentation-specific inline filters:\n```\nFOR EACH finding WHERE severity IN (HIGH, MEDIUM):\n  # Rule 1: ADR\u002FPlanned Override\n  IF finding matches ADR → advisory \"[Planned: ADR-XXX]\"\n\n  # Doc-specific: Compression context (from ln-611)\n  IF Structure finding Cat 3 (Compression):\n    - Skip if path in references\u002F or templates\u002F (reference docs = naturally large)\n    - Skip if filename contains architecture\u002Fdesign\u002Fapi_spec\n    - Skip if tables+lists > 50% of content (already structured)\n\n  # Fact-checker: Example\u002Ftemplate path exclusion (from ln-614)\n  IF Fact finding (PATH_NOT_FOUND):\n    - Path in examples\u002F or templates\u002F directory reference → advisory\n    - Path has placeholder pattern (YOUR_*, \u003Cproject>, {name}) → remove\n\n  # Fact-checker: Planned feature claims (from ln-614)\n  IF Fact finding (ENTITY_NOT_FOUND, ENDPOINT_NOT_FOUND):\n    - Entity mentioned in ADR\u002Froadmap as planned → advisory \"[Planned: ADR-XXX]\"\n\n  # Fact-checker: Cross-doc contradiction authority (from ln-614)\n  IF Fact finding (CROSS_DOC_*_CONFLICT):\n    - docs\u002Fproject\u002F is authority over docs\u002Freference\u002F → report reference doc\n\n  # Comment-specific: Per-category density targets (from ln-613)\n  IF Comment finding Cat 2 (Density):\n    - test\u002F or tests\u002F → target density 2-10%\n    - infra\u002F or config\u002F or ci\u002F → target density 5-15%\n    - business\u002Fdomain\u002Fservices → target density 15-25%\n    Recalculate with per-category target.\n\n  # Comment-specific: Complexity context for WHY-not-WHAT (from ln-613)\n  IF Comment finding Cat 1 (WHY not WHAT):\n    - If file McCabe complexity > 15 → WHAT comments acceptable\n    - If file in domain\u002F or business\u002F → explanatory comments OK\n\nDowngraded findings → \"Advisory Findings\" section in report.\n```\n\n## Phase 7: Write Report\n\nWrite consolidated report to `docs\u002Fproject\u002Fdocs_audit.md`:\n\n```markdown\n## Documentation Audit Report - {DATE}\n\n### Overall Score: X.X\u002F10\n\n| Category | Score | Worker | Issues |\n|----------|-------|--------|--------|\n| Documentation Structure | X\u002F10 | ln-611 | N issues |\n| Semantic Content | X\u002F10 | ln-612 | N issues (across M docs) |\n| Code Comments | X\u002F10 | ln-613 | N issues |\n| Fact Accuracy | X\u002F10 | ln-614 | N issues |\n\n### Critical Findings\n\n- [ ] **[Category]** `path\u002Ffile:line` - Issue. **Action:** Fix suggestion.\n\n### Advisory Findings\n\n(Context-validated findings downgraded from MEDIUM\u002FHIGH)\n\n### Recommended Actions\n\n| Priority | Action | Location | Category |\n|----------|--------|----------|----------|\n| High | ... | ... | ... |\n```\n\n## Scoring Algorithm\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Faudit_scoring.md`.\n\n## Critical Notes\n\n- **Pure coordinator:** Does NOT perform any audit checks directly. ALL auditing delegated to workers.\n- **Fix content, not rules:** NEVER modify standards\u002Frules files to make violations pass\n- **Fact verification via ln-614:** Dedicated worker extracts and verifies all claims across ALL docs\n- **Compress always:** Size limits are upper bounds, not targets\n- **No code in docs:** Documents describe algorithms in tables or ASCII diagrams\n- **Code is truth:** When docs contradict code, always update docs\n- **Delete, don't archive:** Legacy content removed, not archived\n\n## Phase 8: Append Results Log\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fresults_log_pattern.md`\n\nAppend one row to `docs\u002Fproject\u002F.audit\u002Fresults_log.md` with: Skill=`ln-610`, Metric=`overall_score`, Scale=`0-10`, Score from Phase 7 report. Calculate Delta vs previous `ln-610` row. Create file with header if missing. Rolling window: max 50 entries.\n\n## Phase 9: Cleanup Worker Files\n\n```bash\nrm -rf {output_dir}\n```\n\nDelete the dated output directory (`docs\u002Fproject\u002F.audit\u002Fln-610\u002F{YYYY-MM-DD}\u002F`). The consolidated report and results log already preserve all audit data.\n\n## Definition of Done\n\n- Project metadata discovered (tech stack, doc list)\n- contextStore built with output_dir = `docs\u002Fproject\u002F.audit\u002Fln-610\u002F{YYYY-MM-DD}`\n- Output directory created for worker reports\n- All 4 workers invoked and completed\n- Worker reports aggregated: 4 category scores + overall\n- Context Validation applied to all findings\n- Consolidated report written to `docs\u002Fproject\u002Fdocs_audit.md`\n- Results log row appended to `docs\u002Fproject\u002F.audit\u002Fresults_log.md`\n- Worker output directory cleaned up after consolidation\n\n## Phase 10: Meta-Analysis\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fmeta_analysis_protocol.md`\n\nSkill type: `review-coordinator` (workers only). Run after all phases complete. Output to chat using the `review-coordinator — workers only` format.\n\n## Reference Files\n\n- **Context validation rules:** `shared\u002Freferences\u002Fcontext_validation.md`\n- **Task delegation pattern:** `shared\u002Freferences\u002Ftask_delegation_pattern.md`\n- **Aggregation pattern:** `shared\u002Freferences\u002Faudit_coordinator_aggregation.md`\n\n---\n**Version:** 5.0.0\n**Last Updated:** 2026-03-01\n","> **Paths:** File paths (`shared\u002F`, `references\u002F`, `..\u002Fln-*`) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root.\n\n# Documentation Auditor (L2 Coordinator)\n\nCoordinates 4 specialized audit workers to perform comprehensive documentation quality analysis.\n\n## Purpose & Scope\n\n- **Coordinates 4 audit workers** running in parallel:\n  - ln-611 (documentation structure) — 1 invocation\n  - ln-612 (semantic content) — N invocations (per target document)\n  - ln-613 (code comments) — 1 invocation\n  - ln-614 (fact verification) — 1 invocation\n- Detect project type + tech stack ONCE\n- Pass shared context to all workers (token-efficient)\n- Aggregate worker results into single consolidated report\n- Write report to `docs\u002Fproject\u002Fdocs_audit.md` (file-based, no task creation)\n- Manual invocation by user or called by ln-100-documents-pipeline\n\n## Workflow\n\n1) **Discovery:** Detect project type, tech stack, scan .md files\n2) **Context Build:** Build contextStore with output_dir, project_root, tech_stack\n3) **Prepare Output:** Create output directory\n4) **Delegate:** Invoke 4 workers in parallel\n5) **Aggregate:** Collect worker results, calculate overall score\n6) **Context Validation:** Post-filter findings\n7) **Write Report:** Save to `docs\u002Fproject\u002Fdocs_audit.md`\n8) **Results Log:** Append trend row\n9) **Cleanup:** Delete worker files\n\n## Phase 1: Discovery\n\n**Load project metadata:**\n- `CLAUDE.md` — root of documentation hierarchy\n- `docs\u002FREADME.md` — documentation index\n- Package manifests: `package.json`, `requirements.txt`, `go.mod`, `Cargo.toml`\n- Existing docs in `docs\u002Fproject\u002F`\n\n**Extract:**\n- Programming language(s)\n- Major frameworks\u002Flibraries\n- List of `.md` files in project (for ln-611 hierarchy check)\n- Target documents for semantic audit (for ln-612)\n\n**Target documents for ln-612:**\n```\nFOR doc IN [CLAUDE.md, docs\u002FREADME.md, docs\u002Fdocumentation_standards.md,\n            docs\u002Fprinciples.md, docs\u002Fproject\u002F*.md]:\n  IF doc exists AND doc NOT IN [docs\u002Ftasks\u002F*, docs\u002Freference\u002F*, docs\u002Fpresentation\u002F*]:\n    semantic_targets.append(doc)\n```\n\n## Phase 2: Build contextStore\n\n```json\n{\n  \"tech_stack\": {\"language\": \"...\", \"frameworks\": [...]},\n  \"project_root\": \"...\",\n  \"output_dir\": \"docs\u002Fproject\u002F.audit\u002Fln-610\u002F{YYYY-MM-DD}\"\n}\n```\n\nWhere `{YYYY-MM-DD}` is current date (e.g., `2026-03-01`).\n\n## Phase 3: Prepare Output\n\n```bash\nmkdir -p {output_dir}\n```\n\nWorker files are cleaned up after consolidation (see Phase 9).\n\n## Phase 4: Delegate to Workers\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Ftask_delegation_pattern.md`.\n\nAll workers in PARALLEL via Agent tool:\n\n| Worker | Invocations | Output |\n|--------|-------------|--------|\n| ln-611-docs-structure-auditor | 1 | `{output_dir}\u002F611-structure.md` |\n| ln-612-semantic-content-auditor | N (per target document) | `{output_dir}\u002F612-semantic-{doc-slug}.md` |\n| ln-613-code-comments-auditor | 1 | `{output_dir}\u002F613-code-comments.md` |\n| ln-614-docs-fact-checker | 1 | `{output_dir}\u002F614-fact-checker.md` |\n\nln-614 receives only `contextStore` and discovers `.md` files internally. Workers follow the shared file-based audit contract and return compact summaries with report path, score, and severity counts.\n\n**Invocation:**\n```javascript\n\u002F\u002F Global workers (ln-611, ln-613, ln-614) — 1 invocation each:\nFOR EACH worker IN [ln-611, ln-613, ln-614]:\n  Agent(description: \"Docs audit via \" + worker,\n       prompt: \"Execute audit worker.\n\nStep 1: Invoke worker:\n  Skill(skill: \\\"\" + worker + \"\\\")\n\nCONTEXT:\n\" + JSON.stringify(contextStore),\n       subagent_type: \"general-purpose\")\n\n\u002F\u002F Per-document worker (ln-612) — N invocations:\nFOR EACH doc IN semantic_targets:\n  doc_context = { ...contextStore, doc_path: doc }\n  Agent(description: \"Semantic audit \" + doc + \" via ln-612\",\n       prompt: \"Execute audit worker.\n\nStep 1: Invoke worker:\n  Skill(skill: \\\"ln-612-semantic-content-auditor\\\")\n\nCONTEXT:\n\" + JSON.stringify(doc_context),\n       subagent_type: \"general-purpose\")\n```\n\n## Phase 5: Aggregate Results\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Faudit_coordinator_aggregation.md`.\n\nUse the shared aggregation pattern for summary parsing, worker report reads, severity rollups, and final report assembly.\n\nCategory weights:\n\n| Category | Source | Weight |\n|----------|--------|--------|\n| Documentation Structure | ln-611 | 25% |\n| Semantic Content | ln-612 (avg across docs) | 30% |\n| Code Comments | ln-613 | 20% |\n| Fact Accuracy | ln-614 | 25% |\n\nCalculate overall score as the weighted average of the 4 categories above.\n\n## Phase 6: Context Validation (Post-Filter)\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fcontext_validation.md`\n\nApply Rule 1 + documentation-specific inline filters:\n```\nFOR EACH finding WHERE severity IN (HIGH, MEDIUM):\n  # Rule 1: ADR\u002FPlanned Override\n  IF finding matches ADR → advisory \"[Planned: ADR-XXX]\"\n\n  # Doc-specific: Compression context (from ln-611)\n  IF Structure finding Cat 3 (Compression):\n    - Skip if path in references\u002F or templates\u002F (reference docs = naturally large)\n    - Skip if filename contains architecture\u002Fdesign\u002Fapi_spec\n    - Skip if tables+lists > 50% of content (already structured)\n\n  # Fact-checker: Example\u002Ftemplate path exclusion (from ln-614)\n  IF Fact finding (PATH_NOT_FOUND):\n    - Path in examples\u002F or templates\u002F directory reference → advisory\n    - Path has placeholder pattern (YOUR_*, \u003Cproject>, {name}) → remove\n\n  # Fact-checker: Planned feature claims (from ln-614)\n  IF Fact finding (ENTITY_NOT_FOUND, ENDPOINT_NOT_FOUND):\n    - Entity mentioned in ADR\u002Froadmap as planned → advisory \"[Planned: ADR-XXX]\"\n\n  # Fact-checker: Cross-doc contradiction authority (from ln-614)\n  IF Fact finding (CROSS_DOC_*_CONFLICT):\n    - docs\u002Fproject\u002F is authority over docs\u002Freference\u002F → report reference doc\n\n  # Comment-specific: Per-category density targets (from ln-613)\n  IF Comment finding Cat 2 (Density):\n    - test\u002F or tests\u002F → target density 2-10%\n    - infra\u002F or config\u002F or ci\u002F → target density 5-15%\n    - business\u002Fdomain\u002Fservices → target density 15-25%\n    Recalculate with per-category target.\n\n  # Comment-specific: Complexity context for WHY-not-WHAT (from ln-613)\n  IF Comment finding Cat 1 (WHY not WHAT):\n    - If file McCabe complexity > 15 → WHAT comments acceptable\n    - If file in domain\u002F or business\u002F → explanatory comments OK\n\nDowngraded findings → \"Advisory Findings\" section in report.\n```\n\n## Phase 7: Write Report\n\nWrite consolidated report to `docs\u002Fproject\u002Fdocs_audit.md`:\n\n```markdown\n## Documentation Audit Report - {DATE}\n\n### Overall Score: X.X\u002F10\n\n| Category | Score | Worker | Issues |\n|----------|-------|--------|--------|\n| Documentation Structure | X\u002F10 | ln-611 | N issues |\n| Semantic Content | X\u002F10 | ln-612 | N issues (across M docs) |\n| Code Comments | X\u002F10 | ln-613 | N issues |\n| Fact Accuracy | X\u002F10 | ln-614 | N issues |\n\n### Critical Findings\n\n- [ ] **[Category]** `path\u002Ffile:line` - Issue. **Action:** Fix suggestion.\n\n### Advisory Findings\n\n(Context-validated findings downgraded from MEDIUM\u002FHIGH)\n\n### Recommended Actions\n\n| Priority | Action | Location | Category |\n|----------|--------|----------|----------|\n| High | ... | ... | ... |\n```\n\n## Scoring Algorithm\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Faudit_scoring.md`.\n\n## Critical Notes\n\n- **Pure coordinator:** Does NOT perform any audit checks directly. ALL auditing delegated to workers.\n- **Fix content, not rules:** NEVER modify standards\u002Frules files to make violations pass\n- **Fact verification via ln-614:** Dedicated worker extracts and verifies all claims across ALL docs\n- **Compress always:** Size limits are upper bounds, not targets\n- **No code in docs:** Documents describe algorithms in tables or ASCII diagrams\n- **Code is truth:** When docs contradict code, always update docs\n- **Delete, don't archive:** Legacy content removed, not archived\n\n## Phase 8: Append Results Log\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fresults_log_pattern.md`\n\nAppend one row to `docs\u002Fproject\u002F.audit\u002Fresults_log.md` with: Skill=`ln-610`, Metric=`overall_score`, Scale=`0-10`, Score from Phase 7 report. Calculate Delta vs previous `ln-610` row. Create file with header if missing. Rolling window: max 50 entries.\n\n## Phase 9: Cleanup Worker Files\n\n```bash\nrm -rf {output_dir}\n```\n\nDelete the dated output directory (`docs\u002Fproject\u002F.audit\u002Fln-610\u002F{YYYY-MM-DD}\u002F`). The consolidated report and results log already preserve all audit data.\n\n## Definition of Done\n\n- Project metadata discovered (tech stack, doc list)\n- contextStore built with output_dir = `docs\u002Fproject\u002F.audit\u002Fln-610\u002F{YYYY-MM-DD}`\n- Output directory created for worker reports\n- All 4 workers invoked and completed\n- Worker reports aggregated: 4 category scores + overall\n- Context Validation applied to all findings\n- Consolidated report written to `docs\u002Fproject\u002Fdocs_audit.md`\n- Results log row appended to `docs\u002Fproject\u002F.audit\u002Fresults_log.md`\n- Worker output directory cleaned up after consolidation\n\n## Phase 10: Meta-Analysis\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fmeta_analysis_protocol.md`\n\nSkill type: `review-coordinator` (workers only). Run after all phases complete. Output to chat using the `review-coordinator — workers only` format.\n\n## Reference Files\n\n- **Context validation rules:** `shared\u002Freferences\u002Fcontext_validation.md`\n- **Task delegation pattern:** `shared\u002Freferences\u002Ftask_delegation_pattern.md`\n- **Aggregation pattern:** `shared\u002Freferences\u002Faudit_coordinator_aggregation.md`\n\n---\n**Version:** 5.0.0\n**Last Updated:** 2026-03-01\n",{"name":5,"license":15,"description":7,"allowed-tools":41},"Read, Grep, Glob, Bash, Skill","main","fa638b97a18ff6d9f26cf0eaf3dfa123531bcc87","organized-skills\u002Fln-610-docs-auditor",1,"https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode","https:\u002F\u002Fgithub.com\u002Flevalencia","https:\u002F\u002Fmedium.com\u002F@luisevalencia","Microsoft MVP - Artificial Intelligence\r\nMachine Learning Enthusiast\r\n","2026-05-02 06:55:36",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add levalencia\u002Fagent-god-mode --skill ln-610-docs-auditor",{"tool":57,"command":58},"bunx","bunx skills add levalencia\u002Fagent-god-mode --skill ln-610-docs-auditor",{"tool":60,"command":61},"pnpm","pnpm dlx skills add levalencia\u002Fagent-god-mode --skill ln-610-docs-auditor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fln-610-docs-auditor\u002FSKILL.md",true,[],[66,87,125,152,178,205],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":36},"01M6EM8ES5M9J4S8N78NJST0YC","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fzarr-python\u002FSKILL.md",[],[73,74,75,76,77,78,79,80,30,81,82,83,84,85,86],"python","zarr python","storage","integration","s3","gcs","cloud","dask","pipelines","arrays","numpy","scientific computing","scale","scientific",{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":106,"publishedAt":36},"01M6EM8AR6ZFKZ9YVW8TTG850Z","zabbix","Zabbix monitoring system automation via API and Python. Use when: (1) Managing hosts, templates, items, triggers, or host groups, (2) Automating monitoring configuration, (3) Sending data via Zabbix trapper\u002Fsender, (4) Querying historical data or events, (5) Bulk operations on Zabbix objects, (6) Maintenance window management, (7) User\u002Fpermission management","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fzabbix-api-skill\u002FSKILL.md",[93,98,101],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":99,"categoryName":100,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":102,"categoryName":103,"taxonomyType":104,"taxonomyTypeDesc":105},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[89,73,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124],"automation","window management","monitoring","data","templates","api","system","operations","use","maintenance","objects","permission","bulk operations","triggers","host","events","via","bulk",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":36},"01M6EM6Q9JG846ECQY9A210A26","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fx-twitter-growth\u002FSKILL.md",[],[132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151],"twitter","x twitter growth","growth","competitive intelligence","search","analyzing","plan","marketing","web search","competitors","analyze","write","optimize","social","intelligence","viral","growth engine","mechanics","grow","competitive",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":36},"01M6EM3FQNPYNKPC4CV9TCVNGD","what-if-oracle","Run structured What-If scenario analysis with multi-branch possibility exploration. Use this skill when the user asks speculative questions like \"what if...\", \"what would happen if...\", \"what are the possibilities\", \"explore scenarios\", \"scenario analysis\", \"possibility space\", \"what could go wrong\", \"best case \u002F worst case\", \"risk analysis\", \"contingency planning\", \"strategic options\", or any question about uncertain futures. Also trigger when the user faces a fork-in-the-road decision, wants to stress-test an idea, or needs to think through consequences before committing.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fwhat-if-oracle\u002FSKILL.md",[],[159,160,161,162,163,164,165,166,167,168,169,170,115,171,172,173,174,175,176,177],"oracle","what if oracle","test","planning","ux","futures","risk","analysis","explore","decision","branch","question","exploration","options","stress-test","strategies","trigger","case","multi",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":187,"publishedAt":36},"01M6EM08C06RGDYCJ86HAPK0FF","vercel-react-best-practices","React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React\u002FNext.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fvercel-react-best-practices\u002FSKILL.md",[184],{"categoryNo":185,"categoryName":186,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000009","前端开发",[188,189,190,191,192,193,194,195,196,197,198,34,199,110,200,201,202,203,204,120],"react","vercel react best practices","best practices","react best practices","vercel","writing","performance","components","react components","guidelines","tasks","Optimization","Next.js","refactoring","performance optimization","next","pages",{"skillNo":206,"name":207,"nameZh":6,"description":208,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":209,"categories":210,"keywords":221,"publishedAt":36},"01M6EM00S13326QM08DTM94J6Z","venue-templates","Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fvenue-templates\u002FSKILL.md",[211,214,217,218],{"categoryNo":212,"categoryName":213,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":215,"categoryName":216,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":99,"categoryName":100,"taxonomyType":96,"taxonomyTypeDesc":97},{"categoryNo":219,"categoryName":220,"taxonomyType":104,"taxonomyTypeDesc":105},"01JBSEEDCAT000000000000036","内容创作者",[111,222,223,197,224,225,226,227,32,228,28,143,229,230,231,232,233,234,86,235],"venue templates","research","NeurIPS","ICML","LaTeX","science","access","edit","proposals","Academic","requirements","formatting","journal","chi"]