[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CD1VMJAK5WBMTFCSW2K8BZ":3,"skill-same:01M6CD1VMJAK5WBMTFCSW2K8BZ":101},{"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":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":14,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":50,"install":51,"resources":64},"01M6CD1VMJAK5WBMTFCSW2K8BZ","pr-comment-responder",null,"PR review coordinator who gathers comment context, acknowledges every piece of feedback, and ensures all reviewer comments are addressed systematically. Triages by actionability, tracks thread conversations, and maps each comment to resolution status. Use when handling PR feedback, review threads, or bot comments.","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\u002Fpr-comment-responder\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"pr","Responder","pr comment responder","bot","review","status","pr review","specify","pr feedback","feedback","reviewer","context","implementer","use","maps","2026-11-10 10:12:30",false,"---\nname: pr-comment-responder\ndescription: PR review coordinator who gathers comment context, acknowledges every piece of feedback, and ensures all reviewer comments are addressed systematically. Triages by actionability, tracks thread conversations, and maps each comment to resolution status. Use when handling PR feedback, review threads, or bot comments.\nlicense: MIT\nagents:\n  - implementer\n  - analyst\nmodel: claude-sonnet-4-5\nmetadata:\n  version: 2.0.0\n  argument-hint: Specify the PR number or review comments to address\n---\n\n# PR Comment Responder\n\nCoordinates PR review responses through context gathering, comment tracking, and orchestrator delegation.\n\n## Triggers\n\n| Phrase | Action |\n|--------|--------|\n| `respond to PR comments` | Full workflow |\n| `address review feedback on PR #123` | Full workflow |\n| `handle PR review comments` | Full workflow |\n| `fix PR review issues` | Full workflow |\n| `reply to reviewer on PR #123` | Target specific PR |\n\n## Quick Reference\n\n### Context Inference (Phase -1)\n\n**ALWAYS extract PR context from prompt first. Never prompt for information already provided.**\n\nExtract PR context from user prompt or use `gh pr view` to get PR metadata.\n\nSupported patterns:\n\n- Text: `PR 806`, `PR #806`, `pull request 123`, `#806`\n- URLs: `github.com\u002Fowner\u002Frepo\u002Fpull\u002F123`\n\nSee [references\u002Fworkflow.md](references\u002Fworkflow.md) Phase -1 for full details.\n\n### Tools\n\n| Operation | Command |\n|-----------|---------|\n| **Context extraction** | Extract PR number from prompt or use `gh pr view` |\n| PR metadata | `gh pr view [number] --json title,body,state,author,baseRefName,headRefName` |\n| Comments | `gh pr view [number] --json comments,reviewDecision,reviews` |\n| Reviewers | `gh pr view [number] --json reviewRequests,reviews` |\n| Reply | `gh pr comment [number] --body \"[response]\"` |\n| Reaction | `gh api repos\u002F{owner}\u002F{repo}\u002Fissues\u002Fcomments\u002F{id}\u002Freactions -f content=eyes` |\n| Resolve thread | `gh api graphql` with resolveReviewThread mutation |\n\n### Reviewer Priority\n\n| Priority | Reviewer | Signal |\n|----------|----------|--------|\n| P0 | cursor[bot] | 100% actionable |\n| P1 | Human reviewers | High |\n| P2 | coderabbitai[bot] | ~50% |\n| P2 | Copilot | ~44% |\n\n### Domain-Based Priority\n\nComments are classified into domains for priority-based triage:\n\n| Priority | Domain | Keywords | Use Case |\n|----------|--------|----------|----------|\n| P0 | Security | CWE-*, vulnerability, injection, XSS, SQL, CSRF, auth, secrets, credentials, TOCTOU, symlink, traversal | Process FIRST - security-critical issues |\n| P1 | Bug | error, crash, exception, fail, null, undefined, race condition, deadlock, memory leak | Address functional issues |\n| P2 | Style | formatting, naming, indentation, whitespace, convention, prefer, consider, suggest | Apply improvements when time permits |\n| P3 | Summary | Bot-generated summaries (## Summary, ### Overview) | Informational only |\n\n**Domain-First Processing Workflow:**\n\n```bash\n# Get all review comments and PR comments\ncomments=$(gh api repos\u002F{owner}\u002F{repo}\u002Fpulls\u002F{number}\u002Fcomments)\nissue_comments=$(gh api repos\u002F{owner}\u002F{repo}\u002Fissues\u002F{number}\u002Fcomments)\n\n# Process by domain priority:\n# 1. Security (CWE, vulnerabilities, injection) - process FIRST\n# 2. Bug (errors, crashes, null references)\n# 3. Style (formatting, naming, conventions)\n# 4. General comments\n# 5. Skip summary comments (bot-generated noise)\n```\n\n**Benefits:**\n\n- Security issues processed before style suggestions\n- Reduces noise from bot-generated summaries\n- Enables metrics tracking (security vs style comment distribution)\n\n## When to Use\n\nUse this skill when:\n\n- A PR has unaddressed review comments from humans or bots\n- You need to systematically triage and respond to all review feedback\n- CI review bots (CodeRabbit, Copilot, cursor) left comments requiring action\n\nUse direct `gh pr comment` instead when:\n\n- Replying to a single known comment (no triage needed)\n- You already know the exact response to post\n\n## Process\n\n### Phase 1: Context and Gather\n\n1. Extract PR number from prompt (BLOCKING) or use `gh pr view`\n2. Search Brain memory for `pr-comment-responder` related notes\n3. Gather PR metadata, reviewers, all comments (use `--group-by-domain` for priority triage)\n4. Batch eyes reactions on all comments\n\n### Phase 2: Triage and Delegate\n\n1. Generate comment map (track in session or Brain memory note)\n2. Delegate each comment to orchestrator (process security domain first)\n3. Implement changes via orchestrator delegation\n\n### Phase 3: Verify\n\n1. All comments resolved (COMPLETE or WONTFIX)\n2. No new comments after 45s wait\n3. CI checks passing, all threads resolved, commits pushed\n\nSee [references\u002Fworkflow.md](references\u002Fworkflow.md) for full phase details.\n\n## Verification\n\n- [ ] All comments resolved (COMPLETE or WONTFIX)\n- [ ] No new comments after 45s wait\n- [ ] CI checks passing\n- [ ] All threads resolved\n- [ ] Commits pushed\n\nSee [references\u002Fgates.md](references\u002Fgates.md) for gate implementation.\n\n### Response Templates\n\nSee [references\u002Ftemplates.md](references\u002Ftemplates.md) for:\n\n- Won't Fix responses\n- Clarification requests\n- Resolution replies\n\n### Bot Handling\n\nSee [references\u002Fbots.md](references\u002Fbots.md) for:\n\n- Copilot follow-up PR handling\n- CodeRabbit commands\n- cursor[bot] patterns\n\n## Anti-Patterns\n\n| Avoid | Why | Instead |\n|-------|-----|---------|\n| Replying to bot summaries as actionable comments | Wastes time on informational noise | Skip Summary domain comments |\n| Processing style before security | Misses critical issues | Process domains in P0-P3 priority order |\n| Prompting user for PR number already in prompt | Redundant and frustrating | Parse PR number from input text or use `gh pr view` |\n\n## Extension Points\n\n- Add new domain classifiers for comment triage\n- Add reviewer priority entries for new bot integrations\n- Add response templates in `references\u002Ftemplates.md`\n","# PR Comment Responder\n\nCoordinates PR review responses through context gathering, comment tracking, and orchestrator delegation.\n\n## Triggers\n\n| Phrase | Action |\n|--------|--------|\n| `respond to PR comments` | Full workflow |\n| `address review feedback on PR #123` | Full workflow |\n| `handle PR review comments` | Full workflow |\n| `fix PR review issues` | Full workflow |\n| `reply to reviewer on PR #123` | Target specific PR |\n\n## Quick Reference\n\n### Context Inference (Phase -1)\n\n**ALWAYS extract PR context from prompt first. Never prompt for information already provided.**\n\nExtract PR context from user prompt or use `gh pr view` to get PR metadata.\n\nSupported patterns:\n\n- Text: `PR 806`, `PR #806`, `pull request 123`, `#806`\n- URLs: `github.com\u002Fowner\u002Frepo\u002Fpull\u002F123`\n\nSee [references\u002Fworkflow.md](references\u002Fworkflow.md) Phase -1 for full details.\n\n### Tools\n\n| Operation | Command |\n|-----------|---------|\n| **Context extraction** | Extract PR number from prompt or use `gh pr view` |\n| PR metadata | `gh pr view [number] --json title,body,state,author,baseRefName,headRefName` |\n| Comments | `gh pr view [number] --json comments,reviewDecision,reviews` |\n| Reviewers | `gh pr view [number] --json reviewRequests,reviews` |\n| Reply | `gh pr comment [number] --body \"[response]\"` |\n| Reaction | `gh api repos\u002F{owner}\u002F{repo}\u002Fissues\u002Fcomments\u002F{id}\u002Freactions -f content=eyes` |\n| Resolve thread | `gh api graphql` with resolveReviewThread mutation |\n\n### Reviewer Priority\n\n| Priority | Reviewer | Signal |\n|----------|----------|--------|\n| P0 | cursor[bot] | 100% actionable |\n| P1 | Human reviewers | High |\n| P2 | coderabbitai[bot] | ~50% |\n| P2 | Copilot | ~44% |\n\n### Domain-Based Priority\n\nComments are classified into domains for priority-based triage:\n\n| Priority | Domain | Keywords | Use Case |\n|----------|--------|----------|----------|\n| P0 | Security | CWE-*, vulnerability, injection, XSS, SQL, CSRF, auth, secrets, credentials, TOCTOU, symlink, traversal | Process FIRST - security-critical issues |\n| P1 | Bug | error, crash, exception, fail, null, undefined, race condition, deadlock, memory leak | Address functional issues |\n| P2 | Style | formatting, naming, indentation, whitespace, convention, prefer, consider, suggest | Apply improvements when time permits |\n| P3 | Summary | Bot-generated summaries (## Summary, ### Overview) | Informational only |\n\n**Domain-First Processing Workflow:**\n\n```bash\n# Get all review comments and PR comments\ncomments=$(gh api repos\u002F{owner}\u002F{repo}\u002Fpulls\u002F{number}\u002Fcomments)\nissue_comments=$(gh api repos\u002F{owner}\u002F{repo}\u002Fissues\u002F{number}\u002Fcomments)\n\n# Process by domain priority:\n# 1. Security (CWE, vulnerabilities, injection) - process FIRST\n# 2. Bug (errors, crashes, null references)\n# 3. Style (formatting, naming, conventions)\n# 4. General comments\n# 5. Skip summary comments (bot-generated noise)\n```\n\n**Benefits:**\n\n- Security issues processed before style suggestions\n- Reduces noise from bot-generated summaries\n- Enables metrics tracking (security vs style comment distribution)\n\n## When to Use\n\nUse this skill when:\n\n- A PR has unaddressed review comments from humans or bots\n- You need to systematically triage and respond to all review feedback\n- CI review bots (CodeRabbit, Copilot, cursor) left comments requiring action\n\nUse direct `gh pr comment` instead when:\n\n- Replying to a single known comment (no triage needed)\n- You already know the exact response to post\n\n## Process\n\n### Phase 1: Context and Gather\n\n1. Extract PR number from prompt (BLOCKING) or use `gh pr view`\n2. Search Brain memory for `pr-comment-responder` related notes\n3. Gather PR metadata, reviewers, all comments (use `--group-by-domain` for priority triage)\n4. Batch eyes reactions on all comments\n\n### Phase 2: Triage and Delegate\n\n1. Generate comment map (track in session or Brain memory note)\n2. Delegate each comment to orchestrator (process security domain first)\n3. Implement changes via orchestrator delegation\n\n### Phase 3: Verify\n\n1. All comments resolved (COMPLETE or WONTFIX)\n2. No new comments after 45s wait\n3. CI checks passing, all threads resolved, commits pushed\n\nSee [references\u002Fworkflow.md](references\u002Fworkflow.md) for full phase details.\n\n## Verification\n\n- [ ] All comments resolved (COMPLETE or WONTFIX)\n- [ ] No new comments after 45s wait\n- [ ] CI checks passing\n- [ ] All threads resolved\n- [ ] Commits pushed\n\nSee [references\u002Fgates.md](references\u002Fgates.md) for gate implementation.\n\n### Response Templates\n\nSee [references\u002Ftemplates.md](references\u002Ftemplates.md) for:\n\n- Won't Fix responses\n- Clarification requests\n- Resolution replies\n\n### Bot Handling\n\nSee [references\u002Fbots.md](references\u002Fbots.md) for:\n\n- Copilot follow-up PR handling\n- CodeRabbit commands\n- cursor[bot] patterns\n\n## Anti-Patterns\n\n| Avoid | Why | Instead |\n|-------|-----|---------|\n| Replying to bot summaries as actionable comments | Wastes time on informational noise | Skip Summary domain comments |\n| Processing style before security | Misses critical issues | Process domains in P0-P3 priority order |\n| Prompting user for PR number already in prompt | Redundant and frustrating | Parse PR number from input text or use `gh pr view` |\n\n## Extension Points\n\n- Add new domain classifiers for comment triage\n- Add reviewer priority entries for new bot integrations\n- Add response templates in `references\u002Ftemplates.md`\n",{"name":5,"model":39,"agents":40,"license":15,"metadata":42,"description":7},"claude-sonnet-4-5",[31,41],"analyst",{"version":43,"argument-hint":44},"2.0.0","Specify the PR number or review comments to address","main","2bd10cb7ca989f88dbf338b57957763718eda59b","templates\u002Fskills\u002Fpr-comment-responder","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain","https:\u002F\u002Fgithub.com\u002Floriensleafs","2026-03-11 23:51:59",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add loriensleafs\u002Fbrain --skill pr-comment-responder",{"tool":57,"command":58},"bunx","bunx skills add loriensleafs\u002Fbrain --skill pr-comment-responder",{"tool":60,"command":61},"pnpm","pnpm dlx skills add loriensleafs\u002Fbrain --skill pr-comment-responder","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fpr-comment-responder\u002FSKILL.md",true,[65,71,74,79,85,89,93,97],{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},".build-trigger","OTHER","其他",24,"https:\u002F\u002Fgithub.com\u002Fatomicfuse\u002Fatomic-labs-network\u002Fblob\u002Fmain\u002Fsites\u002Fqxnews\u002F.build-trigger",{"path":72,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":14,"sourceHtmlUrl":73},"articles\u002F.gitkeep","https:\u002F\u002Fgithub.com\u002Fatomicfuse\u002Fatomic-labs-network\u002Fblob\u002Fmain\u002Fsites\u002Fqxnews\u002Farticles\u002F.gitkeep",{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":14,"sourceHtmlUrl":78},"assets\u002F.gitkeep","ASSET","资产文件","https:\u002F\u002Fgithub.com\u002Fatomicfuse\u002Fatomic-labs-network\u002Fblob\u002Fmain\u002Fsites\u002Fqxnews\u002Fassets\u002F.gitkeep",{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fbots.md","REFERENCE","参考文档",3314,"https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fpr-comment-responder\u002Freferences\u002Fbots.md",{"path":86,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Fgates.md",4746,"https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fpr-comment-responder\u002Freferences\u002Fgates.md",{"path":90,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Ftemplates.md",2643,"https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fpr-comment-responder\u002Freferences\u002Ftemplates.md",{"path":94,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Fworkflow.md",6832,"https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fpr-comment-responder\u002Freferences\u002Fworkflow.md",{"path":98,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":99,"sourceHtmlUrl":100},"site.yaml",3018,"https:\u002F\u002Fgithub.com\u002Fatomicfuse\u002Fatomic-labs-network\u002Fblob\u002Fmain\u002Fsites\u002Fqxnews\u002Fsite.yaml",[102,117,133,155,176,200],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":34},"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",[],[109,110,111,32,31,112,113,114,115,116],"validation authority","validation","config","behavior","tool","architect","code","change",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":34},"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",[],[124,125,126,127,128,129,130,32,30,131,132],"using brain memory","memory","content","create","notes","graph","guidance","knowledge","knowledge graph",{"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":139,"publishedAt":34},"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",[],[140,141,142,32,143,114,144,145,146,147,148,149,150,151,152,153,154,23],"threat","threat modeling","prioritization","question","architecture review","stride","analysis","risk","owasp","methodology","framework","security analysis","architecture","security","go",{"skillNo":156,"name":157,"nameZh":6,"description":158,"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":166,"publishedAt":34},"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",[161],{"categoryNo":162,"categoryName":163,"taxonomyType":164,"taxonomyTypeDesc":165},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[167,31,168,169,32,170,171,172,173,174,115,175],"taste lints","surfaces","complexity","instructions","remediation","file","logging","qa","writing",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":182,"publishedAt":34},"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",[],[183,184,185,186,187,188,31,189,190,191,192,193,174,194,115,195,196,197,198,199],"style enforcement","enforcement","ci","pipelines","directory","hooks","Rules","json","pre-commit","editorconfig","reports","issues","validate","commit","javascript","python","typescript",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":206,"publishedAt":34},"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",[],[207,32,208,209,30,210,130,172],"steering matcher","files","haiku","orchestrator"]