[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GXJH52VVCZBN7DT32B7TYT":3,"skill-same:01M6GXJH52VVCZBN7DT32B7TYT":86},{"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":23,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":59,"ownerHtmlUrl":60,"ownerBlogUrl":59,"ownerDescription":61,"updatedAt":62,"install":63,"resources":75},"01M6GXJH52VVCZBN7DT32B7TYT","architect",null,"Given a PRD, produces an implementation architecture: file tree, component breakdown, data model, and a phased build plan with end conditions that Archon can execute directly. Multi-candidate evaluation for key decisions.","SethGammon\u002FCitadel","SethGammon","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F5523585?v=4","01M6GXJ90FD2CE9QF5GQERWN06","Seth Gammon","01M6GXJ94VXYGK5KAW14EYE901",931,"MIT","https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel\u002Fblob\u002Fmain\u002Fskills\u002Farchitect\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000031","产品经理","PROFESSION","适用职业",[5,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"decisions","can","true","tree","with","multi","false","end","structure","file tree","design","model","system","plan","data","Evaluation","file","architecture","component","2026-11-10 10:12:30",false,"---\nname: architect\nlicense: MIT\ndescription: >-\n  Given a PRD, produces an implementation architecture: file tree, component\n  breakdown, data model, and a phased build plan with end conditions that\n  Archon can execute directly. Multi-candidate evaluation for key decisions.\nuser-invocable: true\nauto-trigger: false\ntrigger_keywords:\n  - architect\n  - architecture\n  - design the system\n  - file structure\n  - plan the build\neffort: high\n---\n\n# \u002Farchitect — Implementation Architecture from PRD\n\n## When to Use\n\n**Don't use when:** you already have an architecture and want to implement it (use \u002Fmarshal or \u002Farchon); you need a PRD first (use \u002Fprd before \u002Farchitect).\n\n- After \u002Fprd produces an approved PRD (greenfield or feature mode)\n- When the user has a clear direction + existing codebase (no PRD needed)\n- When \u002Fdo routes a build request\n- When the user has a spec and wants a build plan\n\n## Inputs\n\nOne of:\n1. A PRD file path (from \u002Fprd) — preferred, contains structured requirements\n2. A user-provided spec or description + an existing codebase — sufficient\n3. Neither — suggest \u002Fprd first, but don't hard-gate. If the user has a clear\n   direction (\"add auth to my app\"), that + the existing code IS the input.\n\n## Mode Detection\n\n**Greenfield mode**: PRD exists with `Mode: greenfield`, or no existing source files.\nProduces a complete architecture from scratch.\n\n**Feature mode**: PRD exists with `Mode: feature`, OR the user describes a feature\nand the project has existing source files. The architecture describes changes to\nexisting code, not a standalone system.\n\nIn feature mode:\n- Read the existing file tree FIRST — understand the current architecture before planning changes\n- Read key files (package.json, tsconfig, main entry points, existing patterns)\n- The File Tree section shows ONLY new and modified files, not the entire project\n- Phases include a Phase 0: \"Baseline\" that records current typecheck\u002Ftest state\n- Every phase's end conditions include \"no new typecheck errors\" and \"existing tests pass\"\n- The Risk Register includes \"regression in existing functionality\" as a default risk\n\n## Protocol\n\n### Step 1: READ\n\n**If PRD exists**, read it. Extract:\n- Core features (the numbered list)\n- Technical decisions (stack choices)\n- End conditions (what \"done\" looks like)\n- Out of scope (what NOT to build)\n- Integration points (feature mode)\n\n**If no PRD**, read the codebase instead:\n- Scan the file tree for structure and conventions\n- Read package.json \u002F equivalent for dependencies and scripts\n- Read the main entry point(s) to understand the architecture\n- Use the user's description as the feature spec\n- Infer end conditions from the description (\"add auth\" → \"protected routes return 401 without token\")\n\n### Step 2: EVALUATE OPTIONS (for non-trivial decisions)\n\nFor decisions with multiple valid approaches — state management, API structure, auth pattern, DB schema, routing — generate 2-3 candidates. Assess each on complexity, risk, maintainability, and LLM-friendliness. Pick the winner and document why. Reject alternatives with reasoning.\n\nSimple decisions (file naming, folder structure, CSS) don't need this — use the PRD's stack choices and move on.\n\n### Step 3: PRODUCE\n\nWrite to `.planning\u002Farchitecture-{slug}.md`:\n\n```markdown\n# Architecture: {App Name}\n> PRD: .planning\u002Fprd-{slug}.md  |  Date: {ISO date}\n\n## File Tree\n{Greenfield: complete file tree for v1, every file listed.\nFeature mode: ONLY new (+) and modified (~) files.}\n\n## Component Breakdown\n### Feature: {name}\n- Files: | Dependencies: | Complexity: {low\u002Fmedium\u002Fhigh}\n\n## Data Model\n### {Entity name}\n- Fields: {name: type}  |  Relationships: {connections}\n{Omit section if no database.}\n\n## Key Decisions\n### {Decision}: {chosen approach}\n- **Chosen**: {approach} — {reasoning}\n- **Rejected**: {alternative} — {why not}\n\n## Build Phases\n### Phase N: {name}\n- **Goal**: {one sentence}\n- **Files**: | **Dependencies**: {or \"none\"}\n- **End Conditions**: [ ] {machine-verifiable}\n\n## Phase Dependency Graph\n{Text format: Phase 1 → Phase 2 → Phase 3 \u002F Phase 3 + 4 → Phase 5}\n\n## Risk Register\n1. {risk}: {mitigation}\n2. {risk}: {mitigation}\n3. {risk}: {mitigation}\n\n## Deployment Strategy\n{Skip if \"deploy later\" or static-only.}\n- **Platform**: | **Method**: | **Environment variables**: | **Pre-deploy checks**:\n{Final phase is \"Deploy\" when a platform is specified. A failed deploy does NOT fail the campaign.}\n```\n\n### Step 4: CONNECT TO CAMPAIGN\n\nEach build phase becomes a campaign phase; end conditions carry over; the dependency graph determines ordering; parallel-safe phases flagged for Fleet.\n\nPresent summary to user (file count, phase count, key decisions, estimated complexity) and ask: \"Ready to build? This will create an Archon campaign.\" If approved, write the campaign file.\n\n### Step 5: HANDOFF\n\n```\n---HANDOFF---\n- Architecture: {app name}\n- Document: .planning\u002Farchitecture-{slug}.md\n- Phases: {count}\n- Estimated complexity: {low\u002Fmedium\u002Fhigh}\n- Next: Archon campaign ready to execute\n- Reversibility: green — delete .planning\u002Farchitecture-{slug}.md to undo\n---\n```\n\n## Contextual Gates\n\n**Disclosure:** \"Generating architecture plan for [description]. No files modified until you approve.\"\n**Reversibility:** green — creates `.planning\u002Farchitecture-{slug}.md` only; undo with `rm .planning\u002Farchitecture-{slug}.md`.\n**Trust gates:**\n- Any: generate architecture document, evaluate options, connect to campaign.\n\n## Quality Gates\n\n- Every phase has at least one machine-verifiable end condition\n- Every key decision documents what was rejected and why\n- File tree is complete (no \"etc.\" or \"...\" placeholders)\n- Phase dependencies are explicit (no implicit ordering)\n- Risk register has at least 2 entries\n\n## Fringe Cases\n\n**No PRD:** Treat user description + existing codebase as the spec; read file tree and package.json; proceed without requiring a PRD.\n\n**Project already has code:** Use feature mode; read existing architecture first; file tree shows only new\u002Fmodified files; Phase 0 records baseline typecheck\u002Ftest state.\n\n**Vague description:** Ask at most 2 clarifying questions; don't block on perfect clarity.\n\n**`.planning\u002F` missing:** Create it; if not possible, output the architecture inline and instruct the user to save it.\n\n## Exit Protocol\n\n```\n---HANDOFF---\n- Architecture: {app name}\n- Document: .planning\u002Farchitecture-{slug}.md\n- Phases: {count}\n- Estimated complexity: {low\u002Fmedium\u002Fhigh}\n- Next: Archon campaign ready to execute\n- Reversibility: green — delete .planning\u002Farchitecture-{slug}.md to undo\n---\n```\n","# \u002Farchitect — Implementation Architecture from PRD\n\n## When to Use\n\n**Don't use when:** you already have an architecture and want to implement it (use \u002Fmarshal or \u002Farchon); you need a PRD first (use \u002Fprd before \u002Farchitect).\n\n- After \u002Fprd produces an approved PRD (greenfield or feature mode)\n- When the user has a clear direction + existing codebase (no PRD needed)\n- When \u002Fdo routes a build request\n- When the user has a spec and wants a build plan\n\n## Inputs\n\nOne of:\n1. A PRD file path (from \u002Fprd) — preferred, contains structured requirements\n2. A user-provided spec or description + an existing codebase — sufficient\n3. Neither — suggest \u002Fprd first, but don't hard-gate. If the user has a clear\n   direction (\"add auth to my app\"), that + the existing code IS the input.\n\n## Mode Detection\n\n**Greenfield mode**: PRD exists with `Mode: greenfield`, or no existing source files.\nProduces a complete architecture from scratch.\n\n**Feature mode**: PRD exists with `Mode: feature`, OR the user describes a feature\nand the project has existing source files. The architecture describes changes to\nexisting code, not a standalone system.\n\nIn feature mode:\n- Read the existing file tree FIRST — understand the current architecture before planning changes\n- Read key files (package.json, tsconfig, main entry points, existing patterns)\n- The File Tree section shows ONLY new and modified files, not the entire project\n- Phases include a Phase 0: \"Baseline\" that records current typecheck\u002Ftest state\n- Every phase's end conditions include \"no new typecheck errors\" and \"existing tests pass\"\n- The Risk Register includes \"regression in existing functionality\" as a default risk\n\n## Protocol\n\n### Step 1: READ\n\n**If PRD exists**, read it. Extract:\n- Core features (the numbered list)\n- Technical decisions (stack choices)\n- End conditions (what \"done\" looks like)\n- Out of scope (what NOT to build)\n- Integration points (feature mode)\n\n**If no PRD**, read the codebase instead:\n- Scan the file tree for structure and conventions\n- Read package.json \u002F equivalent for dependencies and scripts\n- Read the main entry point(s) to understand the architecture\n- Use the user's description as the feature spec\n- Infer end conditions from the description (\"add auth\" → \"protected routes return 401 without token\")\n\n### Step 2: EVALUATE OPTIONS (for non-trivial decisions)\n\nFor decisions with multiple valid approaches — state management, API structure, auth pattern, DB schema, routing — generate 2-3 candidates. Assess each on complexity, risk, maintainability, and LLM-friendliness. Pick the winner and document why. Reject alternatives with reasoning.\n\nSimple decisions (file naming, folder structure, CSS) don't need this — use the PRD's stack choices and move on.\n\n### Step 3: PRODUCE\n\nWrite to `.planning\u002Farchitecture-{slug}.md`:\n\n```markdown\n# Architecture: {App Name}\n> PRD: .planning\u002Fprd-{slug}.md  |  Date: {ISO date}\n\n## File Tree\n{Greenfield: complete file tree for v1, every file listed.\nFeature mode: ONLY new (+) and modified (~) files.}\n\n## Component Breakdown\n### Feature: {name}\n- Files: | Dependencies: | Complexity: {low\u002Fmedium\u002Fhigh}\n\n## Data Model\n### {Entity name}\n- Fields: {name: type}  |  Relationships: {connections}\n{Omit section if no database.}\n\n## Key Decisions\n### {Decision}: {chosen approach}\n- **Chosen**: {approach} — {reasoning}\n- **Rejected**: {alternative} — {why not}\n\n## Build Phases\n### Phase N: {name}\n- **Goal**: {one sentence}\n- **Files**: | **Dependencies**: {or \"none\"}\n- **End Conditions**: [ ] {machine-verifiable}\n\n## Phase Dependency Graph\n{Text format: Phase 1 → Phase 2 → Phase 3 \u002F Phase 3 + 4 → Phase 5}\n\n## Risk Register\n1. {risk}: {mitigation}\n2. {risk}: {mitigation}\n3. {risk}: {mitigation}\n\n## Deployment Strategy\n{Skip if \"deploy later\" or static-only.}\n- **Platform**: | **Method**: | **Environment variables**: | **Pre-deploy checks**:\n{Final phase is \"Deploy\" when a platform is specified. A failed deploy does NOT fail the campaign.}\n```\n\n### Step 4: CONNECT TO CAMPAIGN\n\nEach build phase becomes a campaign phase; end conditions carry over; the dependency graph determines ordering; parallel-safe phases flagged for Fleet.\n\nPresent summary to user (file count, phase count, key decisions, estimated complexity) and ask: \"Ready to build? This will create an Archon campaign.\" If approved, write the campaign file.\n\n### Step 5: HANDOFF\n\n```\n---HANDOFF---\n- Architecture: {app name}\n- Document: .planning\u002Farchitecture-{slug}.md\n- Phases: {count}\n- Estimated complexity: {low\u002Fmedium\u002Fhigh}\n- Next: Archon campaign ready to execute\n- Reversibility: green — delete .planning\u002Farchitecture-{slug}.md to undo\n---\n```\n\n## Contextual Gates\n\n**Disclosure:** \"Generating architecture plan for [description]. No files modified until you approve.\"\n**Reversibility:** green — creates `.planning\u002Farchitecture-{slug}.md` only; undo with `rm .planning\u002Farchitecture-{slug}.md`.\n**Trust gates:**\n- Any: generate architecture document, evaluate options, connect to campaign.\n\n## Quality Gates\n\n- Every phase has at least one machine-verifiable end condition\n- Every key decision documents what was rejected and why\n- File tree is complete (no \"etc.\" or \"...\" placeholders)\n- Phase dependencies are explicit (no implicit ordering)\n- Risk register has at least 2 entries\n\n## Fringe Cases\n\n**No PRD:** Treat user description + existing codebase as the spec; read file tree and package.json; proceed without requiring a PRD.\n\n**Project already has code:** Use feature mode; read existing architecture first; file tree shows only new\u002Fmodified files; Phase 0 records baseline typecheck\u002Ftest state.\n\n**Vague description:** Ask at most 2 clarifying questions; don't block on perfect clarity.\n\n**`.planning\u002F` missing:** Create it; if not possible, output the architecture inline and instruct the user to save it.\n\n## Exit Protocol\n\n```\n---HANDOFF---\n- Architecture: {app name}\n- Document: .planning\u002Farchitecture-{slug}.md\n- Phases: {count}\n- Estimated complexity: {low\u002Fmedium\u002Fhigh}\n- Next: Archon campaign ready to execute\n- Reversibility: green — delete .planning\u002Farchitecture-{slug}.md to undo\n---\n```\n",{"name":5,"effort":48,"license":15,"description":7,"auto-trigger":44,"user-invocable":49,"trigger_keywords":50},"high",true,[5,41,51,52,53],"design the system","file structure","plan the build","main","e1a3d45697a0f323aaedcbea0ab6a0387b5fe722","skills\u002Farchitect",84,"https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel","https:\u002F\u002Fsethgammon.github.io\u002FCitadel\u002F","https:\u002F\u002Fgithub.com\u002FSethGammon","Building Citadel, the repo-local operating layer for Claude Code and Codex. Persistent work, routing, verification, and coordinated agent fleets.","2026-11-13 02:05:13",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":49},[65,68,71],{"tool":66,"command":67},"npx","npx skills add SethGammon\u002FCitadel --skill architect",{"tool":69,"command":70},"bunx","bunx skills add SethGammon\u002FCitadel --skill architect",{"tool":72,"command":73},"pnpm","pnpm dlx skills add SethGammon\u002FCitadel --skill architect","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel\u002Fblob\u002Fmain\u002Fskills\u002Farchitect\u002FSKILL.md",[76,82],{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"__benchmarks__\u002Fno-prd.md","REFERENCE","参考文档",791,"https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel\u002Fblob\u002Fmain\u002Fskills\u002Farchitect\u002F__benchmarks__\u002Fno-prd.md",{"path":83,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":84,"sourceHtmlUrl":85},"__benchmarks__\u002Fwith-direction.md",897,"https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel\u002Fblob\u002Fmain\u002Fskills\u002Farchitect\u002F__benchmarks__\u002Fwith-direction.md",[87,112,141,165,191,209],{"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":43},"01M6GXSBKE9A2HQWF8QRAZ4WJ5","workspace","Multi-repo campaign coordinator. Same lifecycle as fleet -- scope claims, discovery relay, wave-based execution -- but the unit of work is a repo, not a file. Coordinates campaigns across repositories with shared context.","https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel\u002Fblob\u002Fmain\u002Fskills\u002Fworkspace\u002FSKILL.md",[],[89,94,95,96,97,98,99,100,101,102,103,104,105,30,106,107,108,109,110,111],"repos","snowflake","multi-repo","work","context","campaign","coordinate","but","across","campaigns","shared","as","scope","add","unit","coordinator","fleet","claims",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":123,"publishedAt":43},"01M6GXS873AD1Y6RTM6GV47F3E","wiki","Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to ~400K words.","https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel\u002Fblob\u002Fmain\u002Fskills\u002Fwiki\u002FSKILL.md",[118],{"categoryNo":119,"categoryName":120,"taxonomyType":121,"taxonomyTypeDesc":122},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[114,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,105,30,139,140],"vector","embeddings","librarian","markdown","knowledge","karpathy","knowledge management","karpathy wiki","up","files","maintain","self","knowledge base","project","db","sources","native",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":43},"01M6GXS2840SJ61285SZ43EJC3","watch","File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through \u002Fdo. Use for automatic reactions to file changes; do NOT use for one-off inspection or tasks needing human judgment per file.","https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel\u002Fblob\u002Fmain\u002Fskills\u002Fwatch\u002FSKILL.md",[],[143,148,149,150,151,152,153,154,155,156,157,158,133,159,160,161,162,163,30,164],"directory","commit","tasks","git","batch","actions","start","sentinel","diff","auto","stop","do","scan","human","judgment","reactions","processing",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":174,"publishedAt":43},"01M6GXRXHYJ5RD9RZP81S2VFSW","verify","Self-test the Citadel hook pipeline from within a live session. Exercises real tool calls (Write, Edit, Bash, Read) and checks that hooks fired, telemetry accumulated, and no errors occurred. Reports HOOK HEALTH: PASS or HOOK HEALTH: FAIL with a per-hook breakdown.","https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel\u002Fblob\u002Fmain\u002Fskills\u002Fverify\u002FSKILL.md",[171],{"categoryNo":172,"categoryName":173,"taxonomyType":121,"taxonomyTypeDesc":122},"01JBSEEDCAT000000000000008","测试与质量",[167,175,176,177,178,179,180,181,182,183,184,185,186,135,187,30,188,189,190,26],"citadel","telemetry","harness","pipeline","Bash","tool","read","write","edit","session","hooks","reports","live","hook","errors","calls",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":197,"publishedAt":43},"01M6GXRS9MCJFMQZ917H2XH3AC","unharness","Safely leave Citadel using the active adoption receipt. Produces a no-write, reviewable plan, preserves a portable archive, removes only exact owned material, and reports modified or externally registered surfaces as retained or unknown. Legacy installs must be imported before exact leave is claimed.","https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel\u002Fblob\u002Fmain\u002Fskills\u002Funharness\u002FSKILL.md",[],[193,198,175,177,199,37,200,201,202,132,186,203,204,205,206,207,105,30,208,26],"uninstall","adoption","archive","remove","only","Legacy","surfaces","clean","imported","active","material",{"skillNo":210,"name":211,"nameZh":6,"description":212,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":213,"categories":214,"keywords":221,"publishedAt":43},"01M6GXRMEJ2VHD43R9FNPD4910","triage","GitHub issue and PR investigator. Pulls open issues\u002FPRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code review unrelated to GitHub issues.","https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel\u002Fblob\u002Fmain\u002Fskills\u002Ftriage\u002FSKILL.md",[215,218],{"categoryNo":216,"categoryName":217,"taxonomyType":121,"taxonomyTypeDesc":122},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":219,"categoryName":220,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000030","开发工程师",[211,222,223,224,225,226,227,228,229,230,231,232,233,234,159,30,235,236,237,26],"code review","review","review pr","pr","code","github issues","issues","open","use","unrelated","issue","general","references","line","investigator","reviews"]