[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M754FCKRX7AVMFDYZ8G2W73H":3,"skill-same:01M754FCKRX7AVMFDYZ8G2W73H":56},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M754FCKRX7AVMFDYZ8G2W73H","x-lib-audit-rules",null,"Audits compliance of all project rules AND knowledge packs against source code. Launches parallel subagents (one per rule\u002Fknowledge-pack) for scanning, then aggregates into a unified report with severity classification and story suggestions.","review-bench\u002Federcnj_ia-dev-environment","review-bench","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F286778065?v=4","01M7517F9NTEPDZDAXJBR30FWT","ReviewBench","01M7517FAC9F4P7TGWCNJ8VYVW",0,"MIT","https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring-fintech-pci\u002F.claude\u002Fskills\u002Flib\u002Fx-lib-audit-rules\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: x-lib-audit-rules\ndescription: \"Audits compliance of all project rules AND knowledge packs against source code. Launches parallel subagents (one per rule\u002Fknowledge-pack) for scanning, then aggregates into a unified report with severity classification and story suggestions.\"\nuser-invocable: false\nallowed-tools: Read, Bash, Grep, Glob, Write\nrequires-capabilities: []\ncontext-budget: medium\n---\n\n## Global Output Policy\n\n- **Language**: English ONLY.\n- **Tone**: Technical, Direct, and Concise.\n- **Efficiency**: Remove all conversational fillers and greetings to save tokens.\n\n# Skill: Audit Rules (Library)\n\n## Purpose\n\nAudit compliance of all project rules AND knowledge packs against source code. Launch parallel subagents (one per rule\u002Fknowledge-pack) for scanning, then aggregate into a unified report with severity classification and story suggestions.\n\n## When Called\n\n| Caller Skill | Context |\n|-------------|---------|\n| x-audit-code | Full codebase compliance review |\n| (standalone) | Independent audit of rules and patterns |\n\n## Inputs\n\n| Input | Type | Default | Description |\n|-------|------|---------|-------------|\n| `--scope` | `all\\|rules\\|patterns` | `all` | Review rules + knowledge packs, rules only, or patterns only |\n| `--rules` | `all\\|comma-separated` | `all` | Review all rules or specific rules only (e.g., `01,02,03`) |\n| `--fix` | boolean | `false` | After report, prompt user to create stories |\n\n## Procedure\n\n```\n1. DISCOVER   -> List rules + knowledge packs (inline, lightweight)\n2. SCAN       -> Launch N parallel subagents (one per rule + one per KP) in SINGLE message\n3. AGGREGATE  -> Collect results, deduplicate, generate report + stories (inline)\n```\n\n### Step 1 — Discovery (Orchestrator — Inline)\n\n#### 1.1 — Discover Rules\n\n```bash\nls -1 .claude\u002Frules\u002F*.md\n```\n\nFilter by `--rules` argument if provided. Parse each filename to extract rule number and name.\n\n#### 1.2 — Discover Knowledge Packs\n\n```bash\nfind .claude\u002Fskills\u002F*\u002Freferences -name \"*.md\" 2>\u002Fdev\u002Fnull | sort\n```\n\nGroup by knowledge pack (parent directory). Skip packs with no reference files.\n\n#### 1.3 — Build Scan Plan\n\n```\nScan Plan:\n  Rules: [01, 02, 03, ...] (N rules)\n  Knowledge Packs:\n    - architecture-patterns (N refs)\n    - database-patterns (N refs)\n    - ...\n  Total subagents to launch: N\n```\n\n### Step 2 — Parallel Scanning (Subagents via Task Tool)\n\n**CRITICAL: ALL subagents MUST be launched in a SINGLE message for true parallelism.**\n\nLaunch one `general-purpose` subagent per rule and one per knowledge pack, all in the same message.\n\n#### 2.1 — Subagent: Rule Scanner\n\n**Launch:** One per rule file discovered in Phase 1a.\n**Type:** `general-purpose`\n\n**Prompt template (substitute `{RULE_PATH}` and `{RULE_NAME}`):**\n\n> You are a codebase compliance auditor. Your task is to audit source code against a single project rule.\n>\n> **Rule to audit:** Read `{RULE_PATH}` completely.\n>\n> **Scan targets based on rule type:**\n> - Coding\u002FSOLID\u002FClean Code → `src\u002Fmain\u002F`, `src\u002Ftest\u002F` source files\n> - Testing → `src\u002Ftest\u002F`, build config (coverage thresholds)\n> - Architecture → Package imports, dependency directions\n> - Git → Recent commit messages (`git log --oneline -20`)\n> - Infrastructure → Dockerfiles, K8s manifests, build files\n> - Database → Migrations, entity classes, repository queries\n> - API Design → REST controllers, DTOs, error handlers\n> - Security → Logging statements, error responses, data masking\n> - Observability → Span attributes, metric definitions, log format\n>\n> **For each violation found, report:**\n> - File path and line number\n> - Violation description (1 sentence)\n> - Severity: CRITICAL (blocks build\u002Fdeploy), HIGH (quality\u002Fsecurity risk), MEDIUM (convention), LOW (improvement)\n> - Rule section reference\n>\n> **Anti-patterns:** Do NOT flag test fixtures for production rules. Do NOT flag generated\u002Fthird-party code. Be precise — no false positives.\n>\n> **Output format (strict):**\n> ```\n> RULE: {RULE_NAME}\n> STATUS: PASS|FAIL\n> VIOLATIONS: N\n> ---\n> [SEVERITY] path\u002Ffile:line — Description [Section X]\n> [SEVERITY] path\u002Ffile:line — Description [Section Y]\n> ```\n> If no violations, output STATUS: PASS and VIOLATIONS: 0.\n\n#### 2.2 — Subagent: Knowledge Pack Scanner\n\n**Launch:** One per knowledge pack with reference files, discovered in Phase 1b.\n**Type:** `general-purpose`\n\n**Prompt template (substitute `{KP_NAME}`, `{KP_SKILL_PATH}`, `{KP_REF_FILES}`):**\n\n> You are a codebase pattern compliance auditor. Your task is to audit source code against a knowledge pack's patterns and anti-patterns.\n>\n> **Knowledge Pack:** `{KP_NAME}`\n>\n> **Step 1:** Read the SKILL.md at `{KP_SKILL_PATH}` to understand scope.\n> **Step 2:** Read ALL reference files: {KP_REF_FILES}\n> **Step 3:** From the references, extract:\n> - Concrete implementation patterns (GOOD examples)\n> - Anti-patterns (FORBIDDEN sections)\n> - \"When to Use\" criteria\n> **Step 4:** Scan relevant source files for violations.\n>\n> **Scan targets by pack type:**\n> - `architecture-patterns` → Package structure, imports, class design\n> - `database-patterns` → Entities, repositories, migrations, queries\n> - `{framework}-patterns` → DI beans, config classes, REST resources\n> - `layer-templates` → All layers (domain, adapter, application)\n> - `dockerfile` → Dockerfiles, .dockerignore\n> - `k8s-*` → K8s manifests (YAML)\n> - `infra-*` → IaC files (Terraform, Crossplane)\n>\n> **Severity:**\n> - CRITICAL: Anti-pattern from FORBIDDEN section actively present\n> - HIGH: Required pattern missing when project context demands it\n> - MEDIUM: Deviation from recommended pattern without justification\n> - LOW: Improvement opportunity\n>\n> **Important:** Only flag missing patterns when project context requires them (check project identity for `event_driven`, `domain_driven`, etc.). Skip findings already covered by project rules (rules take precedence).\n>\n> **Output format (strict):**\n> ```\n> KNOWLEDGE_PACK: {KP_NAME}\n> STATUS: PASS|FAIL\n> VIOLATIONS: N\n> ---\n> [SEVERITY] path\u002Ffile:line — Description [reference-file.md, Section]\n> [SEVERITY] path\u002Ffile:line — Description [reference-file.md]\n> ```\n> If no violations, output STATUS: PASS and VIOLATIONS: 0.\n\n### Step 3 — Aggregation and Report (Orchestrator — Inline)\n\n#### 3.1 — Collect and Deduplicate\n\n1. Collect all subagent outputs\n2. Deduplicate: if same file:line appears in both rule and KP findings, keep the rule finding only\n3. Count totals per source, per severity\n\n#### 3.2 — Generate Report\n\n```markdown\n# Codebase Compliance Report\n\n**Date:** YYYY-MM-DD\n**Branch:** {current branch}\n**Scope:** rules + patterns | rules only | patterns only\n\n## Executive Summary\n\n| Source | Type | Violations | Critical | High | Medium | Low | Status |\n|--------|------|-----------|----------|------|--------|-----|--------|\n| Rule 01 — Name | Rule | N | N | N | N | N | PASS\u002FFAIL |\n| ... | ... | ... | ... | ... | ... | ... | ... |\n| kp-name | Knowledge Pack | N | N | N | N | N | PASS\u002FFAIL |\n\n**Overall:** X PASS, Y FAIL, Z violations (A rules, B patterns)\n\n## Section 1: Rule Findings\n(group by rule, then by severity descending)\n\n## Section 2: Knowledge Pack Findings\n(group by pack, then by severity descending)\n\n## Suggested Stories\n(group by source, estimate effort S\u002FM\u002FL)\n```\n\n#### 3.3 — Story Creation (if `--fix`)\n\nWhen `--fix` and user approves:\n1. One story per source with CRITICAL\u002FHIGH violations\n2. Consolidated story for MEDIUM\u002FLOW (if \u003C 10 total) or per-source (if > 10)\n3. Max ~15 violations per story\n4. Tag: `[Rule]` or `[Pattern]`\n\n### Anti-Patterns\n\n- Do NOT report false positives (read code carefully, understand context)\n- Do NOT flag test code for production rules (magic numbers in fixtures are OK)\n- Do NOT flag generated or third-party code\n- Do NOT create stories for violations that already have an open story\n- Do NOT flag missing patterns when project context does not require them\n- Do NOT duplicate findings between rules and knowledge packs\n- Do NOT scan knowledge packs that have no reference files\n\n## Error Handling\n\n| Scenario | Action |\n|----------|--------|\n| No rules files found in `.claude\u002Frules\u002F` | Abort with message: \"No rules found. Verify `.claude\u002Frules\u002F` directory.\" |\n| No knowledge packs with reference files found | Skip KP scanning, proceed with rules only (if scope allows) |\n| Subagent fails or times out | Log warning with failed rule\u002FKP name, continue with remaining subagents |\n| `--fix` with zero CRITICAL\u002FHIGH findings | Skip story creation, report clean results |\n| All subagents fail | Abort with message: \"All scan subagents failed. Check system resources.\" |\n\n## Integration Notes\n\n| Skill | Relationship | Context |\n|-------|-------------|---------|\n| x-audit-code | called-by | Invoked as part of full codebase compliance review |\n| x-review-codebase | complements | `\u002Fx-review-codebase` is diff-based; this skill scans the full codebase |\n| x-implement-story | produces-for | Generated stories can be implemented via lifecycle |\n| x-implement-task | produces-for | Generated stories can be implemented directly |\n\n- Can be run independently of the feature lifecycle\n- Run with `--scope patterns` after adding new knowledge packs\n","## Global Output Policy\n\n- **Language**: English ONLY.\n- **Tone**: Technical, Direct, and Concise.\n- **Efficiency**: Remove all conversational fillers and greetings to save tokens.\n\n# Skill: Audit Rules (Library)\n\n## Purpose\n\nAudit compliance of all project rules AND knowledge packs against source code. Launch parallel subagents (one per rule\u002Fknowledge-pack) for scanning, then aggregate into a unified report with severity classification and story suggestions.\n\n## When Called\n\n| Caller Skill | Context |\n|-------------|---------|\n| x-audit-code | Full codebase compliance review |\n| (standalone) | Independent audit of rules and patterns |\n\n## Inputs\n\n| Input | Type | Default | Description |\n|-------|------|---------|-------------|\n| `--scope` | `all\\|rules\\|patterns` | `all` | Review rules + knowledge packs, rules only, or patterns only |\n| `--rules` | `all\\|comma-separated` | `all` | Review all rules or specific rules only (e.g., `01,02,03`) |\n| `--fix` | boolean | `false` | After report, prompt user to create stories |\n\n## Procedure\n\n```\n1. DISCOVER   -> List rules + knowledge packs (inline, lightweight)\n2. SCAN       -> Launch N parallel subagents (one per rule + one per KP) in SINGLE message\n3. AGGREGATE  -> Collect results, deduplicate, generate report + stories (inline)\n```\n\n### Step 1 — Discovery (Orchestrator — Inline)\n\n#### 1.1 — Discover Rules\n\n```bash\nls -1 .claude\u002Frules\u002F*.md\n```\n\nFilter by `--rules` argument if provided. Parse each filename to extract rule number and name.\n\n#### 1.2 — Discover Knowledge Packs\n\n```bash\nfind .claude\u002Fskills\u002F*\u002Freferences -name \"*.md\" 2>\u002Fdev\u002Fnull | sort\n```\n\nGroup by knowledge pack (parent directory). Skip packs with no reference files.\n\n#### 1.3 — Build Scan Plan\n\n```\nScan Plan:\n  Rules: [01, 02, 03, ...] (N rules)\n  Knowledge Packs:\n    - architecture-patterns (N refs)\n    - database-patterns (N refs)\n    - ...\n  Total subagents to launch: N\n```\n\n### Step 2 — Parallel Scanning (Subagents via Task Tool)\n\n**CRITICAL: ALL subagents MUST be launched in a SINGLE message for true parallelism.**\n\nLaunch one `general-purpose` subagent per rule and one per knowledge pack, all in the same message.\n\n#### 2.1 — Subagent: Rule Scanner\n\n**Launch:** One per rule file discovered in Phase 1a.\n**Type:** `general-purpose`\n\n**Prompt template (substitute `{RULE_PATH}` and `{RULE_NAME}`):**\n\n> You are a codebase compliance auditor. Your task is to audit source code against a single project rule.\n>\n> **Rule to audit:** Read `{RULE_PATH}` completely.\n>\n> **Scan targets based on rule type:**\n> - Coding\u002FSOLID\u002FClean Code → `src\u002Fmain\u002F`, `src\u002Ftest\u002F` source files\n> - Testing → `src\u002Ftest\u002F`, build config (coverage thresholds)\n> - Architecture → Package imports, dependency directions\n> - Git → Recent commit messages (`git log --oneline -20`)\n> - Infrastructure → Dockerfiles, K8s manifests, build files\n> - Database → Migrations, entity classes, repository queries\n> - API Design → REST controllers, DTOs, error handlers\n> - Security → Logging statements, error responses, data masking\n> - Observability → Span attributes, metric definitions, log format\n>\n> **For each violation found, report:**\n> - File path and line number\n> - Violation description (1 sentence)\n> - Severity: CRITICAL (blocks build\u002Fdeploy), HIGH (quality\u002Fsecurity risk), MEDIUM (convention), LOW (improvement)\n> - Rule section reference\n>\n> **Anti-patterns:** Do NOT flag test fixtures for production rules. Do NOT flag generated\u002Fthird-party code. Be precise — no false positives.\n>\n> **Output format (strict):**\n> ```\n> RULE: {RULE_NAME}\n> STATUS: PASS|FAIL\n> VIOLATIONS: N\n> ---\n> [SEVERITY] path\u002Ffile:line — Description [Section X]\n> [SEVERITY] path\u002Ffile:line — Description [Section Y]\n> ```\n> If no violations, output STATUS: PASS and VIOLATIONS: 0.\n\n#### 2.2 — Subagent: Knowledge Pack Scanner\n\n**Launch:** One per knowledge pack with reference files, discovered in Phase 1b.\n**Type:** `general-purpose`\n\n**Prompt template (substitute `{KP_NAME}`, `{KP_SKILL_PATH}`, `{KP_REF_FILES}`):**\n\n> You are a codebase pattern compliance auditor. Your task is to audit source code against a knowledge pack's patterns and anti-patterns.\n>\n> **Knowledge Pack:** `{KP_NAME}`\n>\n> **Step 1:** Read the SKILL.md at `{KP_SKILL_PATH}` to understand scope.\n> **Step 2:** Read ALL reference files: {KP_REF_FILES}\n> **Step 3:** From the references, extract:\n> - Concrete implementation patterns (GOOD examples)\n> - Anti-patterns (FORBIDDEN sections)\n> - \"When to Use\" criteria\n> **Step 4:** Scan relevant source files for violations.\n>\n> **Scan targets by pack type:**\n> - `architecture-patterns` → Package structure, imports, class design\n> - `database-patterns` → Entities, repositories, migrations, queries\n> - `{framework}-patterns` → DI beans, config classes, REST resources\n> - `layer-templates` → All layers (domain, adapter, application)\n> - `dockerfile` → Dockerfiles, .dockerignore\n> - `k8s-*` → K8s manifests (YAML)\n> - `infra-*` → IaC files (Terraform, Crossplane)\n>\n> **Severity:**\n> - CRITICAL: Anti-pattern from FORBIDDEN section actively present\n> - HIGH: Required pattern missing when project context demands it\n> - MEDIUM: Deviation from recommended pattern without justification\n> - LOW: Improvement opportunity\n>\n> **Important:** Only flag missing patterns when project context requires them (check project identity for `event_driven`, `domain_driven`, etc.). Skip findings already covered by project rules (rules take precedence).\n>\n> **Output format (strict):**\n> ```\n> KNOWLEDGE_PACK: {KP_NAME}\n> STATUS: PASS|FAIL\n> VIOLATIONS: N\n> ---\n> [SEVERITY] path\u002Ffile:line — Description [reference-file.md, Section]\n> [SEVERITY] path\u002Ffile:line — Description [reference-file.md]\n> ```\n> If no violations, output STATUS: PASS and VIOLATIONS: 0.\n\n### Step 3 — Aggregation and Report (Orchestrator — Inline)\n\n#### 3.1 — Collect and Deduplicate\n\n1. Collect all subagent outputs\n2. Deduplicate: if same file:line appears in both rule and KP findings, keep the rule finding only\n3. Count totals per source, per severity\n\n#### 3.2 — Generate Report\n\n```markdown\n# Codebase Compliance Report\n\n**Date:** YYYY-MM-DD\n**Branch:** {current branch}\n**Scope:** rules + patterns | rules only | patterns only\n\n## Executive Summary\n\n| Source | Type | Violations | Critical | High | Medium | Low | Status |\n|--------|------|-----------|----------|------|--------|-----|--------|\n| Rule 01 — Name | Rule | N | N | N | N | N | PASS\u002FFAIL |\n| ... | ... | ... | ... | ... | ... | ... | ... |\n| kp-name | Knowledge Pack | N | N | N | N | N | PASS\u002FFAIL |\n\n**Overall:** X PASS, Y FAIL, Z violations (A rules, B patterns)\n\n## Section 1: Rule Findings\n(group by rule, then by severity descending)\n\n## Section 2: Knowledge Pack Findings\n(group by pack, then by severity descending)\n\n## Suggested Stories\n(group by source, estimate effort S\u002FM\u002FL)\n```\n\n#### 3.3 — Story Creation (if `--fix`)\n\nWhen `--fix` and user approves:\n1. One story per source with CRITICAL\u002FHIGH violations\n2. Consolidated story for MEDIUM\u002FLOW (if \u003C 10 total) or per-source (if > 10)\n3. Max ~15 violations per story\n4. Tag: `[Rule]` or `[Pattern]`\n\n### Anti-Patterns\n\n- Do NOT report false positives (read code carefully, understand context)\n- Do NOT flag test code for production rules (magic numbers in fixtures are OK)\n- Do NOT flag generated or third-party code\n- Do NOT create stories for violations that already have an open story\n- Do NOT flag missing patterns when project context does not require them\n- Do NOT duplicate findings between rules and knowledge packs\n- Do NOT scan knowledge packs that have no reference files\n\n## Error Handling\n\n| Scenario | Action |\n|----------|--------|\n| No rules files found in `.claude\u002Frules\u002F` | Abort with message: \"No rules found. Verify `.claude\u002Frules\u002F` directory.\" |\n| No knowledge packs with reference files found | Skip KP scanning, proceed with rules only (if scope allows) |\n| Subagent fails or times out | Log warning with failed rule\u002FKP name, continue with remaining subagents |\n| `--fix` with zero CRITICAL\u002FHIGH findings | Skip story creation, report clean results |\n| All subagents fail | Abort with message: \"All scan subagents failed. Check system resources.\" |\n\n## Integration Notes\n\n| Skill | Relationship | Context |\n|-------|-------------|---------|\n| x-audit-code | called-by | Invoked as part of full codebase compliance review |\n| x-review-codebase | complements | `\u002Fx-review-codebase` is diff-based; this skill scans the full codebase |\n| x-implement-story | produces-for | Generated stories can be implemented via lifecycle |\n| x-implement-task | produces-for | Generated stories can be implemented directly |\n\n- Can be run independently of the feature lifecycle\n- Run with `--scope patterns` after adding new knowledge packs\n",{"name":5,"description":7,"allowed-tools":24,"context-budget":25,"user-invocable":20,"requires-capabilities":26},"Read, Bash, Grep, Glob, Write","medium",[],"main","952a630c6f38d193a349d86fa18db1de8843e837","src\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring-fintech-pci\u002F.claude\u002Fskills\u002Flib\u002Fx-lib-audit-rules",1,"https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment","https:\u002F\u002Fgithub.com\u002Freview-bench","https:\u002F\u002Freview-bench.ai","An open benchmark for AI code review.","2026-10-27 06:56:37",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add review-bench\u002Federcnj_ia-dev-environment --skill x-lib-audit-rules",{"tool":42,"command":43},"bunx","bunx skills add review-bench\u002Federcnj_ia-dev-environment --skill x-lib-audit-rules",{"tool":45,"command":46},"pnpm","pnpm dlx skills add review-bench\u002Federcnj_ia-dev-environment --skill x-lib-audit-rules","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring-fintech-pci\u002F.claude\u002Fskills\u002Flib\u002Fx-lib-audit-rules\u002FSKILL.md",true,[50],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"README.md","REFERENCE","参考文档",2207,"https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring-fintech-pci\u002F.claude\u002Fskills\u002Flib\u002Fx-lib-audit-rules\u002FREADME.md",[57,64,71,78,85,92],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M757M8J48TQ1Y3X25GSJBXAS","x-parallel-eval","Detects and classifies file-collision risks between work units (tasks, stories, or epic phases) before parallel execution. Reads ## File Footprint blocks produced by x-task-plan \u002F x-story-plan, applies the parallelism-heuristics knowledge pack (hard \u002F regen \u002F soft categories + hotspot overrides), and emits a collision matrix + serialization recommendation in Markdown (default) or JSON.","https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fx-parallel-eval\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M757M57XMR9546S69466HDWT","parallelism-heuristics","Canonical catalog of file-collision heuristics for parallel task, story, and epic execution. Defines the File Footprint block format, the three Conflict Categories (hard \u002F regen \u002F soft), a hotspot list of high-contention paths, and the degrade-with-warning policy. Consumed by x-task-plan, x-story-plan, x-epic-map, x-parallel-eval, and x-dev-*-implement.","https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fparallelism-heuristics\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M757M11SZ8P1VCQABT08QVYA","x-watch-pr-ci","Polls a PR's CI checks and Copilot review status, blocking until checks complete or timeout. Returns one of 8 stable exit codes (SUCCESS=0, CI_PENDING_PROCEED=10, CI_FAILED=20, TIMEOUT=30, PR_ALREADY_MERGED=40, NO_CI_CONFIGURED=50, PR_CLOSED=60, PR_NOT_FOUND=70). Writes a versioned state-file for session resume.","https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring\u002Fplatform-claude-code\u002F.claude\u002Fskills\u002Fx-watch-pr-ci\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M757KW53K8KFPGADFB4PH949","x-validate-docs","Documentation freshness gate: validates 6 dimensions (readme, api-specs, grpc-proto, adr, skill-docs, system-architecture) against code changes in a PR. Stack-aware — only validates targets declared\u002Fauto-detected from ProjectConfig.documentation.targets. Returns exit non-zero on staleness; produces structured report.","https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring\u002Fplatform-claude-code\u002F.claude\u002Fskills\u002Fx-validate-docs\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M757KQZHSA10MKC0CR571D60","x-update-system-architecture","Incrementally updates docs\u002Farchitecture\u002Fsystem.md after an epic completes. Appends new entries to the Decision Log (§11) using x-internal-write-report --append (dedup by ## ID: marker) and surgically inserts component\u002Fintegration changes into sections 1-10 via Edit. Idempotent: re-running with the same epic produces a byte-identical system.md.","https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring\u002Fplatform-claude-code\u002F.claude\u002Fskills\u002Fx-update-system-architecture\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M757KKBT5Q1SVF8DMJBVF46M","x-update-architecture","Incrementally updates the service architecture document with changes from architecture plans. Adds new components, integrations, flows, and ADR references without rewriting existing content. Use after implementation to keep architecture documentation current.","https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring\u002Fplatform-claude-code\u002F.claude\u002Fskills\u002Fx-update-architecture\u002FSKILL.md",[],[]]