[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CD16KXQTP7Q63NM0R1JN1H":3,"skill-same:01M6CD16KXQTP7Q63NM0R1JN1H":73},{"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":6,"ownerDescription":6,"updatedAt":46,"install":47,"resources":60},"01M6CD16KXQTP7Q63NM0R1JN1H","incoherence",null,"Detect contradictions between documentation and code, ambiguous specs, and policy violations across a codebase. Use when documentation seems stale, specs conflict with implementation, or a pre-release consistency audit is needed. Produces an actionable incoherence report with resolution workflow.","loriensleafs\u002Fbrain","loriensleafs","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F315385?v=4","01M6CCYZETMCJPTHNS258YRCBC","Peter Kloss","01M6CCYZK25T8516A39S9PCJT7",0,"MIT","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fincoherence\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30],"policy","workflow","documentation","code","report","release","qa","audit","critic","use","stale","implementation","2026-11-10 10:12:30",false,"---\nname: incoherence\ndescription: Detect contradictions between documentation and code, ambiguous specs,\n  and policy violations across a codebase. Use when documentation seems stale,\n  specs conflict with implementation, or a pre-release consistency audit is needed.\n  Produces an actionable incoherence report with resolution workflow.\nlicense: MIT\nagents: [analyst, critic, qa]\nmodel: claude-sonnet-4-5\nmetadata:\n  version: 1.0.0\n---\n\n# Incoherence Detector Skill\n\n## Purpose\n\nDetect and resolve incoherence: contradictions between docs and code, ambiguous specifications, missing documentation, or policy violations.\n\n## Triggers\n\n| Trigger Phrase | Operation |\n|----------------|-----------|\n| `find contradictions in the docs` | Detection phase (steps 1-13) |\n| `audit docs vs code consistency` | Detection phase with Dimension A focus |\n| `check for stale documentation` | Detection phase with Dimension D focus |\n| `run incoherence detector` | Full detection phase |\n| `reconcile incoherence report` | Reconciliation phase (steps 14-22) |\n\n---\n\n## When to Use\n\nUse this skill when:\n\n- Documentation may contradict actual code behavior\n- Preparing for a release and need a consistency audit\n- Specs have changed but implementation status is unclear\n- Multiple authors edited docs and code independently\n\nUse direct code review instead when:\n\n- Investigating a single known bug\n- The inconsistency is already identified and just needs a fix\n\n---\n\n## Anti-Patterns\n\n| Avoid | Why | Instead |\n|-------|-----|---------|\n| Skipping the report filename specification | Script requires output path upfront | Specify filename before starting detection |\n| Running reconciliation without user edits | Nothing to apply, wasted steps | Wait for user to fill Resolution sections |\n| Editing the report format manually | Breaks reconciliation parsing | Let the script manage report structure |\n| Selecting all 11 dimensions | Excessive scope, diminishing returns | Let step 2 select the most relevant 3-5 |\n| Ignoring low-severity issues | They accumulate into real drift | Triage all issues, defer explicitly if needed |\n\n---\n\n## Verification\n\nAfter detection:\n\n- [ ] Report file created at user-specified path\n- [ ] Each issue has Type, Severity, Source A\u002FB, Suggestions, and Resolution section\n- [ ] Dimension coverage matches selection from step 2\n\nAfter reconciliation:\n\n- [ ] Resolved issues show status marker in report\n- [ ] Code changes match user-provided resolutions\n- [ ] No unresolved critical or high severity issues remain\n\n---\n\n## Prerequisites\n\n**Before starting**: User must specify the report filename (e.g., \"output to incoherence-report.md\").\n\n## Scripts\n\n| Script | Purpose |\n|--------|---------|\n| `scripts\u002Fincoherence.ts` | 22-step detection and reconciliation workflow for doc-code contradictions |\n\n## Invocation\n\n```bash\n# Detection phase (steps 1-13)\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fincoherence.ts --step-number 1 --total-steps 22 --thoughts \"\u003Ccontext>\"\n\n# Reconciliation phase (steps 14-22, after user edits report)\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fincoherence.ts --step-number 14 --total-steps 22 --thoughts \"Reconciling...\"\n```\n\n## Process\n\n```\nDETECTION PHASE (Steps 1-13):\n\nStep 1:  CODEBASE SURVEY          ─────┐\nStep 2:  DIMENSION SELECTION           │ Parent\nStep 3:  EXPLORATION DISPATCH     ─────┘\n         │\n         ▼\n    ┌────────────────────────┐\n    │ Step 4:  BROAD SWEEP   │\n    │ Step 5:  COVERAGE CHECK│ Exploration\n    │ Step 6:  GAP-FILL      │ Sub-agents\n    │ Step 7:  FORMAT        │\n    └────────────────────────┘\n         │\n         ▼\nStep 8:  SYNTHESIS                ─────┐\nStep 9:  DEEP-DIVE DISPATCH       ─────┘ Parent\n         │\n         ▼\n    ┌────────────────────────┐\n    │ Step 10: EXPLORATION   │ Deep-dive\n    │ Step 11: FORMAT        │ Sub-agents\n    └────────────────────────┘\n         │\n         ▼\nStep 12: VERDICT ANALYSIS         ─────┐\nStep 13: REPORT GENERATION             │ Parent\n         │                        ─────┘\n         ▼\n    ═══════════════════════════\n    USER EDITS REPORT\n    (fills in Resolution sections)\n    ═══════════════════════════\n         │\n         ▼\nRECONCILIATION PHASE (Steps 14-22):\n\nStep 14: RECONCILE PARSE          ─────┐\nStep 15: RECONCILE ANALYZE             │\nStep 16: RECONCILE PLAN                │ Parent\nStep 17: RECONCILE DISPATCH       ─────┘\n         │\n         ▼\n    ┌────────────────────────┐\n    │ Step 18: APPLY         │ Sub-agents\n    │ Step 19: FORMAT        │ (invoke script)\n    └────────────────────────┘\n         │\n         ▼\nStep 20: RECONCILE COLLECT        ───┐\n         │ (loop if more waves)      │\n         ▼                           │ Parent\nStep 21: RECONCILE UPDATE            │\n         │                           │\n         ▼                           │\nStep 22: RECONCILE COMPLETE      ────┘\n```\n\n## Reconciliation Behavior\n\n**Idempotent**: Can be run multiple times on the same report.\n\n**Skip conditions** (issue left unchanged):\n\n- No resolution provided by user\n- Already marked as resolved (from previous run)\n- Could not apply (sub-agent failed)\n\n**Only action**: Mark successfully applied resolutions as ✅ RESOLVED in report.\n\n## Report Format\n\nStep 9 generates issues with Resolution sections:\n\n```markdown\n### Issue I1: [Title]\n\n**Type**: Contradiction | Ambiguity | Gap | Policy Violation\n**Severity**: critical | high | medium | low\n\n#### Source A \u002F Source B\n\n[quotes and locations]\n\n#### Suggestions\n\n1. [Option A]\n2. [Option B]\n\n#### Resolution\n\n\u003C!-- USER: Write your decision below. Be specific. -->\n\n\u003C!-- \u002FResolution -->\n```\n\nAfter reconciliation, resolved issues get a Status section:\n\n```markdown\n#### Resolution\n\n\u003C!-- USER: Write your decision below. Be specific. -->\n\nUse the spec value (100MB).\n\n\u003C!-- \u002FResolution -->\n\n#### Status\n\n✅ RESOLVED — src\u002Fuploader.py:156: Changed MAX_FILE_SIZE to 100MB\n```\n\n## Dimension Catalog (A-K)\n\n| Cat | Name                              | Detects                                 |\n| --- | --------------------------------- | --------------------------------------- |\n| A   | Specification vs Behavior         | Docs vs code                            |\n| B   | Interface Contract Integrity      | Types\u002Fschemas vs runtime                |\n| C   | Cross-Reference Consistency       | Doc vs doc                              |\n| D   | Temporal Consistency              | Stale references                        |\n| E   | Error Handling Consistency        | Error docs vs implementation            |\n| F   | Configuration & Environment       | Config docs vs code                     |\n| G   | Ambiguity & Underspecification    | Vague specs                             |\n| H   | Policy & Convention Compliance    | ADRs\u002Fstyle guides violated              |\n| I   | Completeness & Documentation Gaps | Missing docs                            |\n| J   | Compositional Consistency         | Claims valid alone, impossible together |\n| K   | Implicit Contract Integrity       | Names\u002Fmessages that lie about behavior  |\n","# Incoherence Detector Skill\n\n## Purpose\n\nDetect and resolve incoherence: contradictions between docs and code, ambiguous specifications, missing documentation, or policy violations.\n\n## Triggers\n\n| Trigger Phrase | Operation |\n|----------------|-----------|\n| `find contradictions in the docs` | Detection phase (steps 1-13) |\n| `audit docs vs code consistency` | Detection phase with Dimension A focus |\n| `check for stale documentation` | Detection phase with Dimension D focus |\n| `run incoherence detector` | Full detection phase |\n| `reconcile incoherence report` | Reconciliation phase (steps 14-22) |\n\n---\n\n## When to Use\n\nUse this skill when:\n\n- Documentation may contradict actual code behavior\n- Preparing for a release and need a consistency audit\n- Specs have changed but implementation status is unclear\n- Multiple authors edited docs and code independently\n\nUse direct code review instead when:\n\n- Investigating a single known bug\n- The inconsistency is already identified and just needs a fix\n\n---\n\n## Anti-Patterns\n\n| Avoid | Why | Instead |\n|-------|-----|---------|\n| Skipping the report filename specification | Script requires output path upfront | Specify filename before starting detection |\n| Running reconciliation without user edits | Nothing to apply, wasted steps | Wait for user to fill Resolution sections |\n| Editing the report format manually | Breaks reconciliation parsing | Let the script manage report structure |\n| Selecting all 11 dimensions | Excessive scope, diminishing returns | Let step 2 select the most relevant 3-5 |\n| Ignoring low-severity issues | They accumulate into real drift | Triage all issues, defer explicitly if needed |\n\n---\n\n## Verification\n\nAfter detection:\n\n- [ ] Report file created at user-specified path\n- [ ] Each issue has Type, Severity, Source A\u002FB, Suggestions, and Resolution section\n- [ ] Dimension coverage matches selection from step 2\n\nAfter reconciliation:\n\n- [ ] Resolved issues show status marker in report\n- [ ] Code changes match user-provided resolutions\n- [ ] No unresolved critical or high severity issues remain\n\n---\n\n## Prerequisites\n\n**Before starting**: User must specify the report filename (e.g., \"output to incoherence-report.md\").\n\n## Scripts\n\n| Script | Purpose |\n|--------|---------|\n| `scripts\u002Fincoherence.ts` | 22-step detection and reconciliation workflow for doc-code contradictions |\n\n## Invocation\n\n```bash\n# Detection phase (steps 1-13)\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fincoherence.ts --step-number 1 --total-steps 22 --thoughts \"\u003Ccontext>\"\n\n# Reconciliation phase (steps 14-22, after user edits report)\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fincoherence.ts --step-number 14 --total-steps 22 --thoughts \"Reconciling...\"\n```\n\n## Process\n\n```\nDETECTION PHASE (Steps 1-13):\n\nStep 1:  CODEBASE SURVEY          ─────┐\nStep 2:  DIMENSION SELECTION           │ Parent\nStep 3:  EXPLORATION DISPATCH     ─────┘\n         │\n         ▼\n    ┌────────────────────────┐\n    │ Step 4:  BROAD SWEEP   │\n    │ Step 5:  COVERAGE CHECK│ Exploration\n    │ Step 6:  GAP-FILL      │ Sub-agents\n    │ Step 7:  FORMAT        │\n    └────────────────────────┘\n         │\n         ▼\nStep 8:  SYNTHESIS                ─────┐\nStep 9:  DEEP-DIVE DISPATCH       ─────┘ Parent\n         │\n         ▼\n    ┌────────────────────────┐\n    │ Step 10: EXPLORATION   │ Deep-dive\n    │ Step 11: FORMAT        │ Sub-agents\n    └────────────────────────┘\n         │\n         ▼\nStep 12: VERDICT ANALYSIS         ─────┐\nStep 13: REPORT GENERATION             │ Parent\n         │                        ─────┘\n         ▼\n    ═══════════════════════════\n    USER EDITS REPORT\n    (fills in Resolution sections)\n    ═══════════════════════════\n         │\n         ▼\nRECONCILIATION PHASE (Steps 14-22):\n\nStep 14: RECONCILE PARSE          ─────┐\nStep 15: RECONCILE ANALYZE             │\nStep 16: RECONCILE PLAN                │ Parent\nStep 17: RECONCILE DISPATCH       ─────┘\n         │\n         ▼\n    ┌────────────────────────┐\n    │ Step 18: APPLY         │ Sub-agents\n    │ Step 19: FORMAT        │ (invoke script)\n    └────────────────────────┘\n         │\n         ▼\nStep 20: RECONCILE COLLECT        ───┐\n         │ (loop if more waves)      │\n         ▼                           │ Parent\nStep 21: RECONCILE UPDATE            │\n         │                           │\n         ▼                           │\nStep 22: RECONCILE COMPLETE      ────┘\n```\n\n## Reconciliation Behavior\n\n**Idempotent**: Can be run multiple times on the same report.\n\n**Skip conditions** (issue left unchanged):\n\n- No resolution provided by user\n- Already marked as resolved (from previous run)\n- Could not apply (sub-agent failed)\n\n**Only action**: Mark successfully applied resolutions as ✅ RESOLVED in report.\n\n## Report Format\n\nStep 9 generates issues with Resolution sections:\n\n```markdown\n### Issue I1: [Title]\n\n**Type**: Contradiction | Ambiguity | Gap | Policy Violation\n**Severity**: critical | high | medium | low\n\n#### Source A \u002F Source B\n\n[quotes and locations]\n\n#### Suggestions\n\n1. [Option A]\n2. [Option B]\n\n#### Resolution\n\n\u003C!-- USER: Write your decision below. Be specific. -->\n\n\u003C!-- \u002FResolution -->\n```\n\nAfter reconciliation, resolved issues get a Status section:\n\n```markdown\n#### Resolution\n\n\u003C!-- USER: Write your decision below. Be specific. -->\n\nUse the spec value (100MB).\n\n\u003C!-- \u002FResolution -->\n\n#### Status\n\n✅ RESOLVED — src\u002Fuploader.py:156: Changed MAX_FILE_SIZE to 100MB\n```\n\n## Dimension Catalog (A-K)\n\n| Cat | Name                              | Detects                                 |\n| --- | --------------------------------- | --------------------------------------- |\n| A   | Specification vs Behavior         | Docs vs code                            |\n| B   | Interface Contract Integrity      | Types\u002Fschemas vs runtime                |\n| C   | Cross-Reference Consistency       | Doc vs doc                              |\n| D   | Temporal Consistency              | Stale references                        |\n| E   | Error Handling Consistency        | Error docs vs implementation            |\n| F   | Configuration & Environment       | Config docs vs code                     |\n| G   | Ambiguity & Underspecification    | Vague specs                             |\n| H   | Policy & Convention Compliance    | ADRs\u002Fstyle guides violated              |\n| I   | Completeness & Documentation Gaps | Missing docs                            |\n| J   | Compositional Consistency         | Claims valid alone, impossible together |\n| K   | Implicit Contract Integrity       | Names\u002Fmessages that lie about behavior  |\n",{"name":5,"model":36,"agents":37,"license":15,"metadata":39,"description":7},"claude-sonnet-4-5",[38,27,25],"analyst",{"version":40},"1.0.0","main","2bd10cb7ca989f88dbf338b57957763718eda59b","templates\u002Fskills\u002Fincoherence","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain","https:\u002F\u002Fgithub.com\u002Floriensleafs","2026-03-11 23:51:59",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add loriensleafs\u002Fbrain --skill incoherence",{"tool":53,"command":54},"bunx","bunx skills add loriensleafs\u002Fbrain --skill incoherence",{"tool":56,"command":57},"pnpm","pnpm dlx skills add loriensleafs\u002Fbrain --skill incoherence","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fincoherence\u002FSKILL.md",true,[61,67],{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002FDEVELOPMENT.md","REFERENCE","参考文档",1635,"https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fincoherence\u002Freferences\u002FDEVELOPMENT.md",{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"scripts\u002Fincoherence.ts","SCRIPT","脚本",13011,"https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fincoherence\u002Fscripts\u002Fincoherence.ts",[74,89,106,129,149,173],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":31},"01M6CD3KHDHPR633RVP95G4XWN","validation-authority","Treat upstream validators as authoritative. Align local config to them. Use when validation fails unexpectedly, before modifying validator behavior, or when tempted to change upstream tool code.","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fvalidation-authority\u002FSKILL.md",[],[81,82,83,28,84,85,86,87,22,88],"validation authority","validation","config","implementer","behavior","tool","architect","change",{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":31},"01M6CD3H29Q8FWN9YETT8YVQTS","using-brain-memory","Guidance for using Brain semantic memory effectively. Applies Zettelkasten atomic note principles with observations and relations. Use when deciding whether to query or create notes, structuring note content, or understanding the semantic knowledge graph.","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fusing-forgetful-memory\u002FSKILL.md",[],[96,97,98,99,100,101,102,28,103,104,105],"using brain memory","memory","content","create","notes","graph","guidance","context","knowledge","knowledge graph",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":31},"01M6CD3E2KTTMNSWXRJAAZA7D1","threat-modeling","Structured security analysis using OWASP Four-Question Framework and STRIDE methodology. Generates threat matrices with risk ratings, mitigations, and prioritization. Use for attack surface analysis, security architecture review, or when asking what can go wrong.","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fthreat-modeling\u002FSKILL.md",[],[113,114,115,28,116,87,117,118,119,120,121,122,123,124,125,126,127,128],"threat","threat modeling","prioritization","question","architecture review","stride","analysis","risk","owasp","methodology","framework","security analysis","architecture","security","go","review",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":140,"publishedAt":31},"01M6CD3BC6G0Q2MDNW6X51XHBQ","taste-lints","Custom lints with agent-readable remediation instructions. Enforces taste invariants (file size, naming conventions, structured logging, complexity) and surfaces errors that agents can act on directly. Use when writing or reviewing code to catch style violations early.","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Ftaste-lints\u002FSKILL.md",[135],{"categoryNo":136,"categoryName":137,"taxonomyType":138,"taxonomyTypeDesc":139},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[141,84,142,143,28,144,145,146,147,25,22,148],"taste lints","surfaces","complexity","instructions","remediation","file","logging","writing",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":31},"01M6CD37Z7VD22BH42TG0GM66V","style-enforcement","Validate code against style rules from .editorconfig, StyleCop.json, and Directory.Build.props. Detects line ending violations, naming convention issues, indentation problems, and charset mismatches across C#, Python, TypeScript, and JavaScript. Produces JSON reports for pre-commit hooks and CI pipelines.","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fstyle-enforcement\u002FSKILL.md",[],[156,157,158,159,160,161,84,162,163,164,165,166,25,167,22,168,169,170,171,172],"style enforcement","enforcement","ci","pipelines","directory","hooks","Rules","json","pre-commit","editorconfig","reports","issues","validate","commit","javascript","python","typescript",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":179,"publishedAt":31},"01M6CD35JW73TPMCZBF9DTDEE8","steering-matcher","Match file paths against steering file glob patterns to determine applicable steering guidance. Use when orchestrator needs to inject context-aware guidance based on files being modified.","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fsteering-matcher\u002FSKILL.md",[],[180,28,181,182,103,183,102,146],"steering matcher","files","haiku","orchestrator"]