[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GXQHTWHZRZZ2Y8Q1PM46QR":3,"skill-same:01M6GXQHTWHZRZZ2Y8Q1PM46QR":82},{"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":28,"publishedAt":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":55,"ownerHtmlUrl":56,"ownerBlogUrl":55,"ownerDescription":57,"updatedAt":58,"install":59,"resources":71},"01M6GXQHTWHZRZZ2Y8Q1PM46QR","review",null,"5-pass structured code review — correctness, security, performance, readability, consistency","SethGammon\u002FCitadel","SethGammon","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F5523585?v=4","01M6GXJ90FD2CE9QF5GQERWN06","Seth Gammon","01M6GXJ94VXYGK5KAW14EYE901",929,"MIT","https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel\u002Fblob\u002Fmain\u002Fskills\u002Freview\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[5,29,30,31,32,33,34,35,36,37,38,39],"code review","security","review pr","performance","pr","code","structured","readability","correctness","consistency","true","2026-11-10 10:12:30",false,"---\nname: review\nlicense: MIT\ndescription: 5-pass structured code review — correctness, security, performance, readability, consistency\nuser-invocable: true\ntrigger_keywords:\n  - \u002Freview\n  - code review\n  - review this\n  - review PR\n  - review\n---\n\n## Orientation\n\n**Use when:** reviewing code for correctness, security, performance, and readability.\n**Don't use when:** generating tests (use \u002Ftest-gen); security audit (use \u002Fsecurity-review); skill file review (use \u002Fimprove skill-md).\n\n# Identity\n\nYou are a senior code reviewer executing a structured 5-pass review. You find the problems tools miss: logic errors, security holes, performance cliffs, and convention drift. Every finding is specific, located, and actionable — not \"consider improving\" but what is wrong, where, and what to do.\n\n# Orientation\n\n**Input**: A review target — one of:\n- A file path (`\u002Freview src\u002Fauth\u002Fsession.ts`)\n- A directory (`\u002Freview src\u002Fauth\u002F`)\n- A git diff range (`\u002Freview --diff HEAD~3` or `\u002Freview --diff main..feature`)\n- No argument defaults to staged + unstaged changes (`git diff HEAD`)\n\n**Output**: A structured review report with findings grouped by pass and severity, ending with a summary verdict.\n\n**Scope rules**:\n- For a file: review that file\n- For a directory: review all source files in that directory (recursive), skip generated files, node_modules, lock files, and build artifacts\n- For a diff: review only changed lines and their surrounding context (20 lines above\u002Fbelow each hunk) — but flag issues in unchanged code only if the change introduces a dependency on that code\n- Binary files, images, and lock files are always skipped\n\n## Protocol\n\n## Step 1 — Resolve scope\n\nDetermine the review target. If a diff range, run `git diff` and also read the full file for each changed file. If a directory, glob for source files. Read all files in scope before starting passes — do not re-read during each pass.\n\n## Step 2 — Load project conventions\n\nRead `CLAUDE.md`, `.eslintrc*`, `tsconfig.json`, `.prettierrc*`, or equivalent config at repo root. These become the baseline for Pass 5. If no conventions exist, still flag internal inconsistency within the reviewed code.\n\n## Step 3 — Execute 5 passes\n\nRun each pass across ALL files. Do not skip a pass — confirm explicitly if nothing found.\n\n### Pass 1: Correctness\n\n- Logic errors (inverted conditions, wrong operator, incorrect boolean logic)\n- Off-by-one errors in loops, slices, index access\n- Null\u002Fundefined dereference without guards; unhandled promise rejections or missing awaits\n- Race conditions (shared mutable state in async code without synchronization)\n- Type coercion bugs (loose equality, implicit conversions)\n- Resource leaks (connections\u002Fhandles\u002Fsubscriptions never closed); missing cleanup in effects\u002Flifecycle\n- Edge cases: empty arrays, zero values, negative numbers, very large inputs\n- State mutations bypassing the expected mutation path\n\n### Pass 2: Security\n\n- **Injection**: SQL\u002FNoSQL\u002Fcommand\u002Ftemplate injection — user input reaching a query or command without parameterization\n- **XSS**: `dangerouslySetInnerHTML`, `innerHTML`, unescaped template interpolation\n- **Auth issues**: missing auth checks, broken access control, privilege escalation, JWT validation gaps\n- **Secrets**: API keys, tokens, passwords, connection strings hardcoded (not env vars)\n- **Unsafe deserialization**: `eval()`, `Function()`, `JSON.parse` on untrusted input without schema validation, `pickle.loads`, `yaml.load` without SafeLoader\n- **SSRF**: user-controlled URLs passed to fetch\u002Frequest without allowlist\n- **Path traversal**: user input in file paths without sanitization\n- **Insecure crypto**: MD5\u002FSHA1 for passwords, ECB mode, hardcoded IVs, `Math.random()` for security-sensitive values\n- **Dependency issues**: prototype pollution-prone patterns, known vulnerable usage\n\n### Pass 3: Performance\n\n- **Algorithmic**: O(n²) or worse in data-scaling paths (nested loops, repeated array scans)\n- **Allocation waste**: objects\u002Farrays created inside hot loops or render functions that could be hoisted\n- **Missing memoization**: expensive derivations recomputed on every call\u002Frender\n- **N+1 queries**: DB\u002FAPI calls inside loops instead of batched\n- **Bundle size**: importing entire libraries when one function is needed\n- **Render performance**: new object\u002Farray references in render, missing React.memo on expensive children, inline function props recreated in hot paths\n- **I\u002FO in hot paths**: sync file reads, blocking ops, layout-thrashing DOM reads (getBoundingClientRect) in animation loops\n- **Missing pagination\u002Flimits**: unbounded queries or list renders\n- **Regex catastrophe**: nested quantifiers vulnerable to ReDoS\n\n### Pass 4: Readability\n\n- **Naming**: vague names (data, info, result), misleading names, inconsistent casing within a file\n- **Function length**: functions over 50 lines doing multiple things\n- **Cognitive complexity**: deeply nested conditionals (3+ levels), complex boolean expressions not extracted to named variables\n- **Dead code**: unreachable branches, commented-out blocks, unused variables\u002Fimports\u002Fparameters\n- **Misleading comments**: comments that no longer match the code; TODO\u002FFIXME\u002FHACK markers\n- **Magic values**: hardcoded numbers or strings without named constants\n- **Inconsistent abstraction levels**: high-level orchestration mixed with low-level details in the same function\n\n### Pass 5: Consistency\n\nScan against conventions from Step 2: import style\u002Fordering\u002Faliases, error handling pattern, file organization, API signatures, naming conventions. Also flag internal inconsistency within the reviewed code (e.g., some functions throw, others return null for errors in the same module).\n\n## Step 4 — Format findings\n\nEvery finding must include: **File** (absolute path), **Line**, **Severity** (`CRITICAL` \u002F `WARNING` \u002F `INFO`), **Finding** (one sentence), **Code** (problematic lines only), **Fix** (specific action).\n\nSeverity: CRITICAL = production bugs\u002Fsecurity\u002Fcrashes; WARNING = conditional problems or maintenance burden; INFO = minor clarity\u002Fstyle. Group by pass, sort by severity within each pass. If a pass finds nothing: `**Pass N ({name})**: No findings.`\n\n## Step 5 — Produce verdict\n\nCount findings across all passes:\n\n| Verdict | Criteria |\n|---|---|\n| **PASS** | 0 critical, 3 or fewer warnings |\n| **CONDITIONAL** | 0 critical, more than 3 warnings |\n| **FAIL** | Any critical finding |\n\nOutput the verdict with a one-line rationale and the finding counts.\n\n## Contextual Gates\n\n**Disclosure:** \"Running structured code review. Read-only — no files modified.\"\n**Reversibility:** green — read-only 5-pass review; no files modified\n**Trust gates:**\n- Any: run review on any target; findings are advisory\n\n## Quality Gates\n\n1. Every finding is actionable — no \"consider\" without a concrete fix.\n2. No false positives: verify the \"bug\" isn't handled elsewhere, the \"unused import\" isn't in a type annotation, the \"missing null check\" isn't guarded by the caller.\n3. Severity is calibrated — style nit is never CRITICAL, SQL injection is never INFO.\n4. No linter-catchable findings (missing semicolons, indentation). Focus on semantic issues.\n5. Line numbers are accurate — verify against file content.\n\n## Fringe Cases\n\n- **No diff vs. main**: output \"No diff found. Confirm branch or specify base ref.\"\n- **Binary files**: skip; note as \"(skipped: binary)\".\n- **Diff >500 lines**: warn; note limitation in verdict.\n\n## Exit Protocol\n\nDeliver the review in this structure:\n\n```\n## Code Review: {target}\n\n**Scope**: {N files, M total lines} | **Mode**: {file | directory | diff}\n\n---\n\n### Pass 1: Correctness\n{findings or \"No findings.\"}\n\n### Pass 2: Security\n{findings or \"No findings.\"}\n\n### Pass 3: Performance\n{findings or \"No findings.\"}\n\n### Pass 4: Readability\n{findings or \"No findings.\"}\n\n### Pass 5: Consistency\n{findings or \"No findings.\"}\n\n---\n\n## Verdict: {PASS | CONDITIONAL | FAIL}\n{one-line rationale}\n\n| Severity | Count |\n|---|---|\n| Critical | N |\n| Warning | N |\n| Info | N |\n```\n\nIf the user provided a diff range, also note which findings are in new\u002Fchanged code vs. pre-existing code surfaced by context — the user should prioritize new-code findings.\n\nDo not offer to fix anything unless asked. The review is the deliverable.\n","## Orientation\n\n**Use when:** reviewing code for correctness, security, performance, and readability.\n**Don't use when:** generating tests (use \u002Ftest-gen); security audit (use \u002Fsecurity-review); skill file review (use \u002Fimprove skill-md).\n\n# Identity\n\nYou are a senior code reviewer executing a structured 5-pass review. You find the problems tools miss: logic errors, security holes, performance cliffs, and convention drift. Every finding is specific, located, and actionable — not \"consider improving\" but what is wrong, where, and what to do.\n\n# Orientation\n\n**Input**: A review target — one of:\n- A file path (`\u002Freview src\u002Fauth\u002Fsession.ts`)\n- A directory (`\u002Freview src\u002Fauth\u002F`)\n- A git diff range (`\u002Freview --diff HEAD~3` or `\u002Freview --diff main..feature`)\n- No argument defaults to staged + unstaged changes (`git diff HEAD`)\n\n**Output**: A structured review report with findings grouped by pass and severity, ending with a summary verdict.\n\n**Scope rules**:\n- For a file: review that file\n- For a directory: review all source files in that directory (recursive), skip generated files, node_modules, lock files, and build artifacts\n- For a diff: review only changed lines and their surrounding context (20 lines above\u002Fbelow each hunk) — but flag issues in unchanged code only if the change introduces a dependency on that code\n- Binary files, images, and lock files are always skipped\n\n## Protocol\n\n## Step 1 — Resolve scope\n\nDetermine the review target. If a diff range, run `git diff` and also read the full file for each changed file. If a directory, glob for source files. Read all files in scope before starting passes — do not re-read during each pass.\n\n## Step 2 — Load project conventions\n\nRead `CLAUDE.md`, `.eslintrc*`, `tsconfig.json`, `.prettierrc*`, or equivalent config at repo root. These become the baseline for Pass 5. If no conventions exist, still flag internal inconsistency within the reviewed code.\n\n## Step 3 — Execute 5 passes\n\nRun each pass across ALL files. Do not skip a pass — confirm explicitly if nothing found.\n\n### Pass 1: Correctness\n\n- Logic errors (inverted conditions, wrong operator, incorrect boolean logic)\n- Off-by-one errors in loops, slices, index access\n- Null\u002Fundefined dereference without guards; unhandled promise rejections or missing awaits\n- Race conditions (shared mutable state in async code without synchronization)\n- Type coercion bugs (loose equality, implicit conversions)\n- Resource leaks (connections\u002Fhandles\u002Fsubscriptions never closed); missing cleanup in effects\u002Flifecycle\n- Edge cases: empty arrays, zero values, negative numbers, very large inputs\n- State mutations bypassing the expected mutation path\n\n### Pass 2: Security\n\n- **Injection**: SQL\u002FNoSQL\u002Fcommand\u002Ftemplate injection — user input reaching a query or command without parameterization\n- **XSS**: `dangerouslySetInnerHTML`, `innerHTML`, unescaped template interpolation\n- **Auth issues**: missing auth checks, broken access control, privilege escalation, JWT validation gaps\n- **Secrets**: API keys, tokens, passwords, connection strings hardcoded (not env vars)\n- **Unsafe deserialization**: `eval()`, `Function()`, `JSON.parse` on untrusted input without schema validation, `pickle.loads`, `yaml.load` without SafeLoader\n- **SSRF**: user-controlled URLs passed to fetch\u002Frequest without allowlist\n- **Path traversal**: user input in file paths without sanitization\n- **Insecure crypto**: MD5\u002FSHA1 for passwords, ECB mode, hardcoded IVs, `Math.random()` for security-sensitive values\n- **Dependency issues**: prototype pollution-prone patterns, known vulnerable usage\n\n### Pass 3: Performance\n\n- **Algorithmic**: O(n²) or worse in data-scaling paths (nested loops, repeated array scans)\n- **Allocation waste**: objects\u002Farrays created inside hot loops or render functions that could be hoisted\n- **Missing memoization**: expensive derivations recomputed on every call\u002Frender\n- **N+1 queries**: DB\u002FAPI calls inside loops instead of batched\n- **Bundle size**: importing entire libraries when one function is needed\n- **Render performance**: new object\u002Farray references in render, missing React.memo on expensive children, inline function props recreated in hot paths\n- **I\u002FO in hot paths**: sync file reads, blocking ops, layout-thrashing DOM reads (getBoundingClientRect) in animation loops\n- **Missing pagination\u002Flimits**: unbounded queries or list renders\n- **Regex catastrophe**: nested quantifiers vulnerable to ReDoS\n\n### Pass 4: Readability\n\n- **Naming**: vague names (data, info, result), misleading names, inconsistent casing within a file\n- **Function length**: functions over 50 lines doing multiple things\n- **Cognitive complexity**: deeply nested conditionals (3+ levels), complex boolean expressions not extracted to named variables\n- **Dead code**: unreachable branches, commented-out blocks, unused variables\u002Fimports\u002Fparameters\n- **Misleading comments**: comments that no longer match the code; TODO\u002FFIXME\u002FHACK markers\n- **Magic values**: hardcoded numbers or strings without named constants\n- **Inconsistent abstraction levels**: high-level orchestration mixed with low-level details in the same function\n\n### Pass 5: Consistency\n\nScan against conventions from Step 2: import style\u002Fordering\u002Faliases, error handling pattern, file organization, API signatures, naming conventions. Also flag internal inconsistency within the reviewed code (e.g., some functions throw, others return null for errors in the same module).\n\n## Step 4 — Format findings\n\nEvery finding must include: **File** (absolute path), **Line**, **Severity** (`CRITICAL` \u002F `WARNING` \u002F `INFO`), **Finding** (one sentence), **Code** (problematic lines only), **Fix** (specific action).\n\nSeverity: CRITICAL = production bugs\u002Fsecurity\u002Fcrashes; WARNING = conditional problems or maintenance burden; INFO = minor clarity\u002Fstyle. Group by pass, sort by severity within each pass. If a pass finds nothing: `**Pass N ({name})**: No findings.`\n\n## Step 5 — Produce verdict\n\nCount findings across all passes:\n\n| Verdict | Criteria |\n|---|---|\n| **PASS** | 0 critical, 3 or fewer warnings |\n| **CONDITIONAL** | 0 critical, more than 3 warnings |\n| **FAIL** | Any critical finding |\n\nOutput the verdict with a one-line rationale and the finding counts.\n\n## Contextual Gates\n\n**Disclosure:** \"Running structured code review. Read-only — no files modified.\"\n**Reversibility:** green — read-only 5-pass review; no files modified\n**Trust gates:**\n- Any: run review on any target; findings are advisory\n\n## Quality Gates\n\n1. Every finding is actionable — no \"consider\" without a concrete fix.\n2. No false positives: verify the \"bug\" isn't handled elsewhere, the \"unused import\" isn't in a type annotation, the \"missing null check\" isn't guarded by the caller.\n3. Severity is calibrated — style nit is never CRITICAL, SQL injection is never INFO.\n4. No linter-catchable findings (missing semicolons, indentation). Focus on semantic issues.\n5. Line numbers are accurate — verify against file content.\n\n## Fringe Cases\n\n- **No diff vs. main**: output \"No diff found. Confirm branch or specify base ref.\"\n- **Binary files**: skip; note as \"(skipped: binary)\".\n- **Diff >500 lines**: warn; note limitation in verdict.\n\n## Exit Protocol\n\nDeliver the review in this structure:\n\n```\n## Code Review: {target}\n\n**Scope**: {N files, M total lines} | **Mode**: {file | directory | diff}\n\n---\n\n### Pass 1: Correctness\n{findings or \"No findings.\"}\n\n### Pass 2: Security\n{findings or \"No findings.\"}\n\n### Pass 3: Performance\n{findings or \"No findings.\"}\n\n### Pass 4: Readability\n{findings or \"No findings.\"}\n\n### Pass 5: Consistency\n{findings or \"No findings.\"}\n\n---\n\n## Verdict: {PASS | CONDITIONAL | FAIL}\n{one-line rationale}\n\n| Severity | Count |\n|---|---|\n| Critical | N |\n| Warning | N |\n| Info | N |\n```\n\nIf the user provided a diff range, also note which findings are in new\u002Fchanged code vs. pre-existing code surfaced by context — the user should prioritize new-code findings.\n\nDo not offer to fix anything unless asked. The review is the deliverable.\n",{"name":5,"license":15,"description":7,"user-invocable":45,"trigger_keywords":46},true,[47,29,48,49,5],"\u002Freview","review this","review PR","main","e1a3d45697a0f323aaedcbea0ab6a0387b5fe722","skills\u002Freview",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.","2026-11-06 02:04:44",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":45},[61,64,67],{"tool":62,"command":63},"npx","npx skills add SethGammon\u002FCitadel --skill review",{"tool":65,"command":66},"bunx","bunx skills add SethGammon\u002FCitadel --skill review",{"tool":68,"command":69},"pnpm","pnpm dlx skills add SethGammon\u002FCitadel --skill review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel\u002Fblob\u002Fmain\u002Fskills\u002Freview\u002FSKILL.md",[72,78],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"__benchmarks__\u002Fno-files-changed.md","REFERENCE","参考文档",759,"https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel\u002Fblob\u002Fmain\u002Fskills\u002Freview\u002F__benchmarks__\u002Fno-files-changed.md",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"__benchmarks__\u002Fspecific-file.md",815,"https:\u002F\u002Fgithub.com\u002FSethGammon\u002FCitadel\u002Fblob\u002Fmain\u002Fskills\u002Freview\u002F__benchmarks__\u002Fspecific-file.md",[83,109,136,160,186,205],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":40},"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",[],[85,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"repos","snowflake","multi-repo","work","context","campaign","coordinate","but","across","campaigns","shared","as","false","scope","add","unit","coordinator","fleet","claims",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":118,"publishedAt":40},"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",[115],{"categoryNo":116,"categoryName":117,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",[111,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,101,102,134,135],"vector","embeddings","librarian","markdown","knowledge","karpathy","knowledge management","karpathy wiki","up","files","maintain","self","knowledge base","project","db","sources","native",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":40},"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",[],[138,143,144,145,146,147,148,149,150,151,152,153,128,154,155,156,157,158,102,159],"directory","commit","tasks","git","batch","actions","start","sentinel","diff","auto","stop","do","scan","human","judgment","reactions","processing",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":169,"publishedAt":40},"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",[166],{"categoryNo":167,"categoryName":168,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[162,170,171,172,173,174,175,176,177,178,179,180,181,130,182,102,183,184,185,39],"citadel","telemetry","harness","pipeline","Bash","tool","read","write","edit","session","hooks","reports","live","hook","errors","calls",{"skillNo":187,"name":188,"nameZh":6,"description":189,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":190,"categories":191,"keywords":192,"publishedAt":40},"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",[],[188,193,170,172,194,195,196,197,198,127,181,199,200,201,202,203,101,102,204,39],"uninstall","adoption","plan","archive","remove","only","Legacy","surfaces","clean","imported","active","material",{"skillNo":206,"name":207,"nameZh":6,"description":208,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":209,"categories":210,"keywords":213,"publishedAt":40},"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",[211,212],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[207,29,5,31,33,34,214,215,216,217,218,219,220,221,154,102,222,223,224,39],"github issues","issues","open","use","unrelated","issue","general","references","line","investigator","reviews"]