[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CD0P2XCHF1G6EMSSWX33AA":3,"skill-same:01M6CD0P2XCHF1G6EMSSWX33AA":72},{"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":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":14,"repositoryHtmlUrl":49,"repositoryHomepageUrl":6,"ownerHtmlUrl":50,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":51,"install":52,"resources":65},"01M6CD0P2XCHF1G6EMSSWX33AA","doc-sync",null,"Synchronizes CLAUDE.md navigation indexes and README.md architecture docs across a repository. Use when asked to \"sync docs\", \"update CLAUDE.md files\", \"ensure documentation is in sync\", \"audit documentation\", or when documentation maintenance is needed after code changes.","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\u002Fdoc-sync\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36],"sync","doc sync","doc","indexes","docs","files","navigation","maintenance","use","sync docs","implementer","README","repository","audit","code","update","documentation","architecture","2026-11-10 10:12:30",false,"---\nname: doc-sync\ndescription: Synchronizes CLAUDE.md navigation indexes and README.md architecture docs across a repository. Use when asked to \"sync docs\", \"update CLAUDE.md files\", \"ensure documentation is in sync\", \"audit documentation\", or when documentation maintenance is needed after code changes.\nlicense: MIT\nagents:\n  - implementer\nmodel: claude-sonnet-4-5\nmetadata:\n  version: 1.1.0\n---\n\n# Doc Sync\n\nMaintains the CLAUDE.md navigation hierarchy and optional README.md architecture docs across a repository. This skill is self-contained and performs all documentation work directly.\n\n## Triggers\n\n| Trigger Phrase | Operation |\n|----------------|-----------|\n| `sync docs` | Repository-wide CLAUDE.md audit and update |\n| `update CLAUDE.md files` | Repository-wide index refresh |\n| `sync docs in src\u002Fparser\u002F` | Directory-scoped index update |\n| `audit documentation` | Full discovery, audit, and drift report |\n| `update CLAUDE.md for config.py` | Single-file parent directory update |\n\n---\n\n## When to Use\n\nUse this skill when:\n\n- CLAUDE.md files may be out of sync with actual directory contents\n- New files or directories were added without index updates\n- Architecture content is mixed into CLAUDE.md index files\n- A doc audit is needed after significant code changes\n\nUse direct editing instead when:\n\n- Adding inline code comments or docstrings\n- Writing function-level documentation\n- Updating a single README.md with no index impact\n\n---\n\n## Verification\n\nAfter execution:\n\n- [ ] Every directory in scope has a CLAUDE.md file\n- [ ] All CLAUDE.md files use table-based index format (What\u002FWhen columns)\n- [ ] No drift remains between file system and index entries\n- [ ] No architecture prose in subdirectory CLAUDE.md files (moved to README.md)\n- [ ] README.md files are indexed in their parent CLAUDE.md\n- [ ] Doc Sync Report generated with change summary\n\n---\n\n## Scope Resolution\n\nDetermine scope FIRST:\n\n| User Request                                            | Scope                                     |\n| ------------------------------------------------------- | ----------------------------------------- |\n| \"sync docs\" \u002F \"update documentation\" \u002F no specific path | REPOSITORY-WIDE                           |\n| \"sync docs in src\u002Fvalidator\u002F\"                           | DIRECTORY: src\u002Fvalidator\u002F and descendants |\n| \"update CLAUDE.md for parser.py\"                        | FILE: single file's parent directory      |\n\nFor REPOSITORY-WIDE scope, perform a full audit. For narrower scopes, operate only within the specified boundary.\n\n## CLAUDE.md Format Specification\n\n### Index Format\n\nUse tabular format with What and When columns:\n\n```markdown\n## Files\n\n| File        | What                           | When to read                              |\n| ----------- | ------------------------------ | ----------------------------------------- |\n| `cache.rs`  | LRU cache with O(1) operations | Implementing caching, debugging evictions |\n| `errors.rs` | Error types and Result aliases | Adding error variants, handling failures  |\n\n## Subdirectories\n\n| Directory   | What                          | When to read                              |\n| ----------- | ----------------------------- | ----------------------------------------- |\n| `config\u002F`   | Runtime configuration loading | Adding config options, modifying defaults |\n| `handlers\u002F` | HTTP request handlers         | Adding endpoints, modifying request flow  |\n```\n\n### Column Guidelines\n\n- **File\u002FDirectory**: Use backticks around names: `cache.rs`, `config\u002F`\n- **What**: Factual description of contents (nouns, not actions)\n- **When to read**: Task-oriented triggers using action verbs (implementing, debugging, modifying, adding, understanding)\n- At least one column must have content; empty cells use `-`\n\n### Trigger Quality Test\n\nGiven task \"add a new validation rule\", can an LLM scan the \"When to read\" column and identify the right file?\n\n### ROOT vs SUBDIRECTORY CLAUDE.md\n\n**ROOT CLAUDE.md:**\n\n```markdown\n# [Project Name]\n\n[One sentence: what this is]\n\n## Files\n\n| File | What | When to read |\n| ---- | ---- | ------------ |\n\n## Subdirectories\n\n| Directory | What | When to read |\n| --------- | ---- | ------------ |\n\n## Build\n\n[Copy-pasteable command]\n\n## Test\n\n[Copy-pasteable command]\n\n## Development\n\n[Setup instructions, environment requirements, workflow notes]\n```\n\n**SUBDIRECTORY CLAUDE.md:**\n\n```markdown\n# [directory-name]\u002F\n\n## Files\n\n| File | What | When to read |\n| ---- | ---- | ------------ |\n\n## Subdirectories\n\n| Directory | What | When to read |\n| --------- | ---- | ------------ |\n```\n\n**Critical constraint:** Subdirectory CLAUDE.md files are PURE INDEX. No prose, no overview sections, no architectural explanations. Those belong in README.md.\n\n## README.md Specification\n\n### Creation Criteria (Invisible Knowledge Test)\n\nCreate README.md ONLY when the directory contains knowledge NOT visible from reading the code:\n\n- Multiple components interact through non-obvious contracts or protocols\n- Design tradeoffs were made that affect how code should be modified\n- The directory's structure encodes domain knowledge (e.g., processing order matters)\n- Failure modes or edge cases aren't apparent from reading individual files\n- There are \"rules\" developers must follow that aren't enforced by the compiler\u002Flinter\n\n**DO NOT create README.md when:**\n\n- The directory is purely organizational (just groups related files)\n- Code is self-explanatory with good function\u002Fmodule docs\n- You'd be restating what CLAUDE.md index entries already convey\n\n### Content Test\n\nFor each sentence in README.md, ask: \"Could a developer learn this by reading the source files?\"\n\n- If YES: delete the sentence\n- If NO: keep it\n\nREADME.md earns its tokens by providing INVISIBLE knowledge: the reasoning behind the code, not descriptions of the code.\n\n### README.md Structure\n\n```markdown\n# [Component Name]\n\n## Overview\n\n[One paragraph: what problem this solves, high-level approach]\n\n## Architecture\n\n[How sub-components interact; data flow; key abstractions]\n\n## Design Decisions\n\n[Tradeoffs made and why; alternatives considered]\n\n## Invariants\n\n[Rules that must be maintained; constraints not enforced by code]\n```\n\n## Workflow\n\n### Phase 1: Discovery\n\nMap directories requiring CLAUDE.md verification:\n\n```bash\n# Find all directories (excluding .git, node_modules, __pycache__, etc.)\nfind . -type d \\( -name .git -o -name node_modules -o -name __pycache__ -o -name .venv -o -name target -o -name dist -o -name build \\) -prune -o -type d -print\n```\n\nFor each directory in scope, record:\n\n1. Does CLAUDE.md exist?\n2. If yes, does it have the required table-based index structure?\n3. What files\u002Fsubdirectories exist that need indexing?\n\n### Phase 2: Audit\n\nFor each directory, check for drift and misplaced content:\n\n```\n\u003Caudit_check dir=\"[path]\">\nCLAUDE.md exists: [YES\u002FNO]\nHas table-based index: [YES\u002FNO]\nFiles in directory: [list]\nFiles in index: [list]\nMissing from index: [list]\nStale in index (file deleted): [list]\nTriggers are task-oriented: [YES\u002FNO\u002FPARTIAL]\nContains misplaced content: [YES\u002FNO] (architecture\u002Fdesign docs that belong in README.md)\nREADME.md exists: [YES\u002FNO]\nREADME.md warranted: [YES\u002FNO] (invisible knowledge present?)\n\u003C\u002Faudit_check>\n```\n\n### Phase 3: Content Migration\n\n**Critical:** If CLAUDE.md contains content that does NOT belong there, migrate it:\n\nContent that MUST be moved from CLAUDE.md to README.md:\n\n- Architecture explanations or diagrams\n- Design decision documentation\n- Component interaction descriptions\n- Overview sections with prose (in subdirectory CLAUDE.md files)\n- Invariants or rules documentation\n- Any \"why\" explanations beyond simple triggers\n\nMigration process:\n\n1. Identify misplaced content in CLAUDE.md\n2. Create or update README.md with the architectural content\n3. Strip CLAUDE.md down to pure index format\n4. Add README.md to the CLAUDE.md index table\n\n### Phase 4: Index Updates\n\nFor each directory needing work:\n\n**Creating\u002FUpdating CLAUDE.md:**\n\n1. Use the appropriate template (ROOT or SUBDIRECTORY)\n2. Populate tables with all files and subdirectories\n3. Write \"What\" column: factual content description\n4. Write \"When to read\" column: action-oriented triggers\n5. If README.md exists, include it in the Files table\n\n**Creating README.md (only when warranted):**\n\n1. Verify invisible knowledge criteria are met\n2. Document architecture, design decisions, invariants\n3. Apply the content test: remove anything visible from code\n4. Keep under ~500 tokens\n\n### Phase 5: Verification\n\nAfter all updates complete, verify:\n\n1. Every directory in scope has CLAUDE.md\n2. All CLAUDE.md files use table-based index format\n3. No drift remains (files \u003C-> index entries match)\n4. No misplaced content in CLAUDE.md (architecture docs moved to README.md)\n5. README.md files are indexed in their parent CLAUDE.md\n6. Subdirectory CLAUDE.md files contain no prose\u002Foverview sections\n\n## Output Format\n\n```\n## Doc Sync Report\n\n### Scope: [REPOSITORY-WIDE | directory path]\n\n### Changes Made\n- CREATED: [list of new CLAUDE.md files]\n- UPDATED: [list of modified CLAUDE.md files]\n- MIGRATED: [list of content moved from CLAUDE.md to README.md]\n- CREATED: [list of new README.md files]\n- FLAGGED: [any issues requiring human decision]\n\n### Verification\n- Directories audited: [count]\n- CLAUDE.md coverage: [count]\u002F[total] (100%)\n- Drift detected: [count] entries fixed\n- Content migrations: [count] (architecture docs moved to README.md)\n- README.md files: [count] (only where warranted)\n```\n\n## Exclusions\n\nDO NOT index:\n\n- Generated files (dist\u002F, build\u002F, _.generated._, compiled outputs)\n- Vendored dependencies (node_modules\u002F, vendor\u002F, third_party\u002F)\n- Git internals (.git\u002F)\n- IDE\u002Feditor configs (.idea\u002F, .vscode\u002F unless project-specific settings)\n\nDO index:\n\n- Hidden config files that affect development (.eslintrc, .env.example, .gitignore)\n- Test files and test directories\n- Documentation files (including README.md)\n\n## Anti-Patterns\n\n| Avoid | Why | Instead |\n|-------|-----|---------|\n| Vague \"When to read\" triggers | Matches everything, helps nothing | Use specific action verbs: \"implementing\", \"debugging\" |\n| Putting architecture prose in subdirectory CLAUDE.md | CLAUDE.md is pure index | Move to README.md, index the README |\n| Recreating CLAUDE.md from memory | Misses files, wrong format | Run discovery phase, use template |\n| Syncing a single file without checking parent index | Creates partial drift | Always verify parent directory index too |\n| Creating README.md for simple directories | Token waste, redundant with code | Apply invisible knowledge test first |\n\n### Index Anti-Patterns (Detailed)\n\n**Too vague (matches everything):**\n\n```markdown\n| `config\u002F` | Configuration | Working with configuration |\n```\n\n**Content description instead of trigger:**\n\n```markdown\n| `cache.rs` | Contains the LRU cache implementation | - |\n```\n\n**Missing action verb:**\n\n```markdown\n| `parser.py` | Input parsing | Input parsing and format handling |\n```\n\n### Correct Examples\n\n```markdown\n| `cache.rs` | LRU cache with O(1) get\u002Fset | Implementing caching, debugging misses, tuning eviction |\n| `config\u002F` | YAML config parsing, env overrides | Adding config options, changing defaults, debugging config loading |\n```\n\n## When NOT to Use This Skill\n\n- Single file documentation (inline comments, docstrings) - handle directly\n- Code comments - handle directly\n- Function\u002Fmodule docstrings - handle directly\n- This skill is for CLAUDE.md\u002FREADME.md synchronization specifically\n\n## Reference\n\nFor additional trigger pattern examples, see `references\u002Ftrigger-patterns.md`.\n","# Doc Sync\n\nMaintains the CLAUDE.md navigation hierarchy and optional README.md architecture docs across a repository. This skill is self-contained and performs all documentation work directly.\n\n## Triggers\n\n| Trigger Phrase | Operation |\n|----------------|-----------|\n| `sync docs` | Repository-wide CLAUDE.md audit and update |\n| `update CLAUDE.md files` | Repository-wide index refresh |\n| `sync docs in src\u002Fparser\u002F` | Directory-scoped index update |\n| `audit documentation` | Full discovery, audit, and drift report |\n| `update CLAUDE.md for config.py` | Single-file parent directory update |\n\n---\n\n## When to Use\n\nUse this skill when:\n\n- CLAUDE.md files may be out of sync with actual directory contents\n- New files or directories were added without index updates\n- Architecture content is mixed into CLAUDE.md index files\n- A doc audit is needed after significant code changes\n\nUse direct editing instead when:\n\n- Adding inline code comments or docstrings\n- Writing function-level documentation\n- Updating a single README.md with no index impact\n\n---\n\n## Verification\n\nAfter execution:\n\n- [ ] Every directory in scope has a CLAUDE.md file\n- [ ] All CLAUDE.md files use table-based index format (What\u002FWhen columns)\n- [ ] No drift remains between file system and index entries\n- [ ] No architecture prose in subdirectory CLAUDE.md files (moved to README.md)\n- [ ] README.md files are indexed in their parent CLAUDE.md\n- [ ] Doc Sync Report generated with change summary\n\n---\n\n## Scope Resolution\n\nDetermine scope FIRST:\n\n| User Request                                            | Scope                                     |\n| ------------------------------------------------------- | ----------------------------------------- |\n| \"sync docs\" \u002F \"update documentation\" \u002F no specific path | REPOSITORY-WIDE                           |\n| \"sync docs in src\u002Fvalidator\u002F\"                           | DIRECTORY: src\u002Fvalidator\u002F and descendants |\n| \"update CLAUDE.md for parser.py\"                        | FILE: single file's parent directory      |\n\nFor REPOSITORY-WIDE scope, perform a full audit. For narrower scopes, operate only within the specified boundary.\n\n## CLAUDE.md Format Specification\n\n### Index Format\n\nUse tabular format with What and When columns:\n\n```markdown\n## Files\n\n| File        | What                           | When to read                              |\n| ----------- | ------------------------------ | ----------------------------------------- |\n| `cache.rs`  | LRU cache with O(1) operations | Implementing caching, debugging evictions |\n| `errors.rs` | Error types and Result aliases | Adding error variants, handling failures  |\n\n## Subdirectories\n\n| Directory   | What                          | When to read                              |\n| ----------- | ----------------------------- | ----------------------------------------- |\n| `config\u002F`   | Runtime configuration loading | Adding config options, modifying defaults |\n| `handlers\u002F` | HTTP request handlers         | Adding endpoints, modifying request flow  |\n```\n\n### Column Guidelines\n\n- **File\u002FDirectory**: Use backticks around names: `cache.rs`, `config\u002F`\n- **What**: Factual description of contents (nouns, not actions)\n- **When to read**: Task-oriented triggers using action verbs (implementing, debugging, modifying, adding, understanding)\n- At least one column must have content; empty cells use `-`\n\n### Trigger Quality Test\n\nGiven task \"add a new validation rule\", can an LLM scan the \"When to read\" column and identify the right file?\n\n### ROOT vs SUBDIRECTORY CLAUDE.md\n\n**ROOT CLAUDE.md:**\n\n```markdown\n# [Project Name]\n\n[One sentence: what this is]\n\n## Files\n\n| File | What | When to read |\n| ---- | ---- | ------------ |\n\n## Subdirectories\n\n| Directory | What | When to read |\n| --------- | ---- | ------------ |\n\n## Build\n\n[Copy-pasteable command]\n\n## Test\n\n[Copy-pasteable command]\n\n## Development\n\n[Setup instructions, environment requirements, workflow notes]\n```\n\n**SUBDIRECTORY CLAUDE.md:**\n\n```markdown\n# [directory-name]\u002F\n\n## Files\n\n| File | What | When to read |\n| ---- | ---- | ------------ |\n\n## Subdirectories\n\n| Directory | What | When to read |\n| --------- | ---- | ------------ |\n```\n\n**Critical constraint:** Subdirectory CLAUDE.md files are PURE INDEX. No prose, no overview sections, no architectural explanations. Those belong in README.md.\n\n## README.md Specification\n\n### Creation Criteria (Invisible Knowledge Test)\n\nCreate README.md ONLY when the directory contains knowledge NOT visible from reading the code:\n\n- Multiple components interact through non-obvious contracts or protocols\n- Design tradeoffs were made that affect how code should be modified\n- The directory's structure encodes domain knowledge (e.g., processing order matters)\n- Failure modes or edge cases aren't apparent from reading individual files\n- There are \"rules\" developers must follow that aren't enforced by the compiler\u002Flinter\n\n**DO NOT create README.md when:**\n\n- The directory is purely organizational (just groups related files)\n- Code is self-explanatory with good function\u002Fmodule docs\n- You'd be restating what CLAUDE.md index entries already convey\n\n### Content Test\n\nFor each sentence in README.md, ask: \"Could a developer learn this by reading the source files?\"\n\n- If YES: delete the sentence\n- If NO: keep it\n\nREADME.md earns its tokens by providing INVISIBLE knowledge: the reasoning behind the code, not descriptions of the code.\n\n### README.md Structure\n\n```markdown\n# [Component Name]\n\n## Overview\n\n[One paragraph: what problem this solves, high-level approach]\n\n## Architecture\n\n[How sub-components interact; data flow; key abstractions]\n\n## Design Decisions\n\n[Tradeoffs made and why; alternatives considered]\n\n## Invariants\n\n[Rules that must be maintained; constraints not enforced by code]\n```\n\n## Workflow\n\n### Phase 1: Discovery\n\nMap directories requiring CLAUDE.md verification:\n\n```bash\n# Find all directories (excluding .git, node_modules, __pycache__, etc.)\nfind . -type d \\( -name .git -o -name node_modules -o -name __pycache__ -o -name .venv -o -name target -o -name dist -o -name build \\) -prune -o -type d -print\n```\n\nFor each directory in scope, record:\n\n1. Does CLAUDE.md exist?\n2. If yes, does it have the required table-based index structure?\n3. What files\u002Fsubdirectories exist that need indexing?\n\n### Phase 2: Audit\n\nFor each directory, check for drift and misplaced content:\n\n```\n\u003Caudit_check dir=\"[path]\">\nCLAUDE.md exists: [YES\u002FNO]\nHas table-based index: [YES\u002FNO]\nFiles in directory: [list]\nFiles in index: [list]\nMissing from index: [list]\nStale in index (file deleted): [list]\nTriggers are task-oriented: [YES\u002FNO\u002FPARTIAL]\nContains misplaced content: [YES\u002FNO] (architecture\u002Fdesign docs that belong in README.md)\nREADME.md exists: [YES\u002FNO]\nREADME.md warranted: [YES\u002FNO] (invisible knowledge present?)\n\u003C\u002Faudit_check>\n```\n\n### Phase 3: Content Migration\n\n**Critical:** If CLAUDE.md contains content that does NOT belong there, migrate it:\n\nContent that MUST be moved from CLAUDE.md to README.md:\n\n- Architecture explanations or diagrams\n- Design decision documentation\n- Component interaction descriptions\n- Overview sections with prose (in subdirectory CLAUDE.md files)\n- Invariants or rules documentation\n- Any \"why\" explanations beyond simple triggers\n\nMigration process:\n\n1. Identify misplaced content in CLAUDE.md\n2. Create or update README.md with the architectural content\n3. Strip CLAUDE.md down to pure index format\n4. Add README.md to the CLAUDE.md index table\n\n### Phase 4: Index Updates\n\nFor each directory needing work:\n\n**Creating\u002FUpdating CLAUDE.md:**\n\n1. Use the appropriate template (ROOT or SUBDIRECTORY)\n2. Populate tables with all files and subdirectories\n3. Write \"What\" column: factual content description\n4. Write \"When to read\" column: action-oriented triggers\n5. If README.md exists, include it in the Files table\n\n**Creating README.md (only when warranted):**\n\n1. Verify invisible knowledge criteria are met\n2. Document architecture, design decisions, invariants\n3. Apply the content test: remove anything visible from code\n4. Keep under ~500 tokens\n\n### Phase 5: Verification\n\nAfter all updates complete, verify:\n\n1. Every directory in scope has CLAUDE.md\n2. All CLAUDE.md files use table-based index format\n3. No drift remains (files \u003C-> index entries match)\n4. No misplaced content in CLAUDE.md (architecture docs moved to README.md)\n5. README.md files are indexed in their parent CLAUDE.md\n6. Subdirectory CLAUDE.md files contain no prose\u002Foverview sections\n\n## Output Format\n\n```\n## Doc Sync Report\n\n### Scope: [REPOSITORY-WIDE | directory path]\n\n### Changes Made\n- CREATED: [list of new CLAUDE.md files]\n- UPDATED: [list of modified CLAUDE.md files]\n- MIGRATED: [list of content moved from CLAUDE.md to README.md]\n- CREATED: [list of new README.md files]\n- FLAGGED: [any issues requiring human decision]\n\n### Verification\n- Directories audited: [count]\n- CLAUDE.md coverage: [count]\u002F[total] (100%)\n- Drift detected: [count] entries fixed\n- Content migrations: [count] (architecture docs moved to README.md)\n- README.md files: [count] (only where warranted)\n```\n\n## Exclusions\n\nDO NOT index:\n\n- Generated files (dist\u002F, build\u002F, _.generated._, compiled outputs)\n- Vendored dependencies (node_modules\u002F, vendor\u002F, third_party\u002F)\n- Git internals (.git\u002F)\n- IDE\u002Feditor configs (.idea\u002F, .vscode\u002F unless project-specific settings)\n\nDO index:\n\n- Hidden config files that affect development (.eslintrc, .env.example, .gitignore)\n- Test files and test directories\n- Documentation files (including README.md)\n\n## Anti-Patterns\n\n| Avoid | Why | Instead |\n|-------|-----|---------|\n| Vague \"When to read\" triggers | Matches everything, helps nothing | Use specific action verbs: \"implementing\", \"debugging\" |\n| Putting architecture prose in subdirectory CLAUDE.md | CLAUDE.md is pure index | Move to README.md, index the README |\n| Recreating CLAUDE.md from memory | Misses files, wrong format | Run discovery phase, use template |\n| Syncing a single file without checking parent index | Creates partial drift | Always verify parent directory index too |\n| Creating README.md for simple directories | Token waste, redundant with code | Apply invisible knowledge test first |\n\n### Index Anti-Patterns (Detailed)\n\n**Too vague (matches everything):**\n\n```markdown\n| `config\u002F` | Configuration | Working with configuration |\n```\n\n**Content description instead of trigger:**\n\n```markdown\n| `cache.rs` | Contains the LRU cache implementation | - |\n```\n\n**Missing action verb:**\n\n```markdown\n| `parser.py` | Input parsing | Input parsing and format handling |\n```\n\n### Correct Examples\n\n```markdown\n| `cache.rs` | LRU cache with O(1) get\u002Fset | Implementing caching, debugging misses, tuning eviction |\n| `config\u002F` | YAML config parsing, env overrides | Adding config options, changing defaults, debugging config loading |\n```\n\n## When NOT to Use This Skill\n\n- Single file documentation (inline comments, docstrings) - handle directly\n- Code comments - handle directly\n- Function\u002Fmodule docstrings - handle directly\n- This skill is for CLAUDE.md\u002FREADME.md synchronization specifically\n\n## Reference\n\nFor additional trigger pattern examples, see `references\u002Ftrigger-patterns.md`.\n",{"name":5,"model":42,"agents":43,"license":15,"metadata":44,"description":7},"claude-sonnet-4-5",[29],{"version":45},"1.1.0","main","2bd10cb7ca989f88dbf338b57957763718eda59b","templates\u002Fskills\u002Fdoc-sync","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain","https:\u002F\u002Fgithub.com\u002Floriensleafs","2026-03-11 23:51:59",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add loriensleafs\u002Fbrain --skill doc-sync",{"tool":58,"command":59},"bunx","bunx skills add loriensleafs\u002Fbrain --skill doc-sync",{"tool":61,"command":62},"pnpm","pnpm dlx skills add loriensleafs\u002Fbrain --skill doc-sync","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fdoc-sync\u002FSKILL.md",true,[66],{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Ftrigger-patterns.md","REFERENCE","参考文档",7935,"https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fdoc-sync\u002Freferences\u002Ftrigger-patterns.md",[73,87,104,126,147,171],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":37},"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",[],[80,81,82,27,29,83,84,85,33,86],"validation authority","validation","config","behavior","tool","architect","change",{"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":93,"publishedAt":37},"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",[],[94,95,96,97,98,99,100,27,101,102,103],"using brain memory","memory","content","create","notes","graph","guidance","context","knowledge","knowledge graph",{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":37},"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",[],[111,112,113,27,114,85,115,116,117,118,119,120,121,122,36,123,124,125],"threat","threat modeling","prioritization","question","architecture review","stride","analysis","risk","owasp","methodology","framework","security analysis","security","go","review",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":137,"publishedAt":37},"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",[132],{"categoryNo":133,"categoryName":134,"taxonomyType":135,"taxonomyTypeDesc":136},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[138,29,139,140,27,141,142,143,144,145,33,146],"taste lints","surfaces","complexity","instructions","remediation","file","logging","qa","writing",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":153,"publishedAt":37},"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",[],[154,155,156,157,158,159,29,160,161,162,163,164,145,165,33,166,167,168,169,170],"style enforcement","enforcement","ci","pipelines","directory","hooks","Rules","json","pre-commit","editorconfig","reports","issues","validate","commit","javascript","python","typescript",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":177,"publishedAt":37},"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",[],[178,27,24,179,101,180,100,143],"steering matcher","haiku","orchestrator"]