[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M752HMVSENMHWY00JAX4EQDM":3,"skill-same:01M752HMVSENMHWY00JAX4EQDM":57},{"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":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":35,"ownerDescription":36,"updatedAt":37,"install":38,"resources":50},"01M752HMVSENMHWY00JAX4EQDM","x-fix-pr",null,"Reads PR review comments and fixes actionable ones automatically. Detects PR from argument or branch, classifies comments (actionable\u002Fsuggestion\u002Fquestion\u002Fpraise), implements fixes, and commits with proper conventional commit messages.","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-clickhouse\u002F.claude\u002Fskills\u002Fx-fix-pr\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: x-fix-pr\ndescription: \"Reads PR review comments and fixes actionable ones automatically. Detects PR from argument or branch, classifies comments (actionable\u002Fsuggestion\u002Fquestion\u002Fpraise), implements fixes, and commits with proper conventional commit messages.\"\nuser-invocable: true\nallowed-tools: Read, Write, Edit, Bash, Grep, Glob\nargument-hint: \"[PR-number]\"\ncontext-budget: medium\nrequires-capabilities: []\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: Fix PR Comments\n\n## Purpose\n\nAutomates the process of addressing PR review comments for {{PROJECT_NAME}}. Reads all review comments from a pull request, classifies them by type, and implements fixes for actionable feedback.\n\n## Triggers\n\n- `\u002Fx-fix-pr` — fix comments on current branch's PR\n- `\u002Fx-fix-pr 123` — fix comments on PR #123\n\n## Parameters\n\n| Parameter | Required | Description |\n|-----------|----------|-------------|\n| `PR-number` | No | PR number to process. If omitted, detect from current branch. |\n\n## Workflow\n\n```\n1. DETECT     -> Identify PR (argument or branch)\n2. FETCH      -> Get all review comments via GitHub CLI\n3. CLASSIFY   -> Categorize each comment (actionable\u002Fsuggestion\u002Fquestion\u002Fpraise\u002Fresolved)\n4. FIX        -> Implement fixes for actionable comments\n5. VERIFY     -> Compile and test after each fix\n6. REPLY      -> Reply to each comment thread in PT-BR (fix summary or rejection reason)\n7. COMMIT     -> Commit with conventional commit message\n8. REPORT     -> Summarize actions taken\n```\n\n### Step 1 — Detect PR\n\nDetermine which PR to process:\n\n```bash\n# If argument is a number, use it directly\nPR_NUMBER=$1\n\n# If no argument, detect from current branch\nif [ -z \"$PR_NUMBER\" ]; then\n  gh pr view --json number --jq '.number'\nfi\n```\n\nIf no PR found, abort: `No PR found for current branch. Provide a PR number as argument.`\n\n### Step 2 — Fetch Review Comments\n\n```bash\n# Get all review comments (not issue comments)\ngh api repos\u002F{owner}\u002F{repo}\u002Fpulls\u002F{PR_NUMBER}\u002Fcomments \\\n  --jq '.[] | {id: .id, path: .path, line: .line, body: .body, user: .user.login, created_at: .created_at}'\n\n# Also get PR review threads for context\ngh api repos\u002F{owner}\u002F{repo}\u002Fpulls\u002F{PR_NUMBER}\u002Freviews \\\n  --jq '.[] | {id: .id, state: .state, body: .body, user: .user.login}'\n```\n\n### Step 3 — Classify Comments\n\nFor each comment, classify into one of:\n\n| Type | Description | Action |\n|------|-------------|--------|\n| **Actionable** | Clear request to change code (fix bug, rename, refactor) | Implement the fix |\n| **Suggestion** | Optional improvement with rationale | Implement if aligns with project standards |\n| **Question** | Reviewer asking for clarification | Skip (requires human response) |\n| **Praise** | Positive feedback | Skip |\n| **Resolved** | Already addressed or outdated | Skip |\n\n**Classification rules:**\n- Contains \"please change\", \"should be\", \"must\", \"fix\", \"bug\", \"wrong\" — Actionable\n- Contains \"consider\", \"maybe\", \"could\", \"suggestion\", \"nit\" — Suggestion\n- Contains \"?\", \"why\", \"what\", \"how does\" — Question\n- Contains \"LGTM\", \"nice\", \"good\", \"great\" — Praise\n- Thread is marked as resolved — Resolved\n\n### Step 4 — Implement Fixes\n\nFor each actionable\u002Fsuggestion comment:\n\n1. Read the file at the specified path and line:\n   ```bash\n   # Comment metadata provides path and line\n   cat -n {path} | sed -n '{line-5},{line+5}p'\n   ```\n\n2. Understand the reviewer's request\n\n3. Implement the fix using Edit tool\n\n4. If the fix requires understanding broader context, read surrounding code first\n\n**Ordering:** Process comments file-by-file to minimize context switching. Within a file, process top-to-bottom to avoid line number shifts.\n\n### Step 5 — Verify\n\nAfter each fix (or batch of fixes per file):\n\n```bash\n{{COMPILE_COMMAND}}\n{{TEST_COMMAND}}\n```\n\nIf compilation fails, revert the last change and try an alternative approach.\nIf tests fail, analyze the failure and adjust the fix.\n\n### Step 6 — Reply to Comments (PT-BR)\n\nAfter each comment is processed (fixed, skipped, or rejected), reply to the review comment thread **in Portuguese (pt-BR)** explaining the action taken.\n\n**Reply command:**\n```bash\n# Reply to an inline review comment thread\ngh api repos\u002F{owner}\u002F{repo}\u002Fpulls\u002F{PR_NUMBER}\u002Fcomments\u002F{comment_id}\u002Freplies \\\n  -f body=\"{message_in_portuguese}\"\n```\n\n**Reply templates by classification:**\n\n| Classification | Reply Template (PT-BR) |\n|---------------|----------------------|\n| **Actionable (fixed)** | `Corrigido. {descricao da alteracao feita}. Commit: {short_hash}` |\n| **Suggestion (accepted)** | `Sugestao aceita. {descricao da alteracao feita}. Commit: {short_hash}` |\n| **Suggestion (rejected)** | `Sugestao analisada, mas nao aplicada. Motivo: {razao tecnica pela qual nao faz sentido no contexto atual}` |\n| **Actionable (rejected)** | `Observacao analisada, mas nao faz sentido neste contexto. Motivo: {explicacao tecnica detalhada}` |\n| **Actionable (failed)** | `Tentei corrigir, mas a alteracao causou falha na compilacao\u002Ftestes. Necessita intervencao manual.` |\n| **Question** | _(no reply — requires human response)_ |\n| **Praise** | _(no reply)_ |\n| **Resolved** | _(no reply — already resolved)_ |\n\n**Rules:**\n- ALL replies MUST be in Portuguese (pt-BR)\n- Be specific: describe exactly what was changed and why\n- When rejecting, provide technical justification (reference project rules, architecture constraints, or coding standards)\n- Include commit hash when a fix was applied\n- Never reply to praise or already-resolved comments\n\n**Examples:**\n\nFix applied:\n```\nCorrigido. Renomeei a variavel `d` para `elapsedTimeInMs` conforme padrao de naming do projeto. Commit: abc1234\n```\n\nSuggestion rejected:\n```\nSugestao analisada, mas nao aplicada. Motivo: o metodo precisa ser publico porque implementa a interface Assembler, que define o contrato do pipeline. Tornar package-private quebraria o polimorfismo.\n```\n\nComment doesn't make sense:\n```\nObservacao analisada, mas nao faz sentido neste contexto. Motivo: o null check sugerido e desnecessario aqui — o parametro vem de um Optional.orElseThrow() na linha 42, garantindo que nunca sera null neste ponto.\n```\n\n### Step 7 — Commit\n\nAfter all fixes for a logical group are verified:\n\n```bash\ngit add {modified-files}\ngit commit -m \"fix({scope}): address PR review comments\n\n- {summary of change 1}\n- {summary of change 2}\n\nAddresses review comments on PR #{PR_NUMBER}\"\n```\n\n**Scope** should match the module\u002Flayer affected (e.g., `domain`, `api`, `config`).\n\n### Step 8 — Report\n\nOutput a summary table:\n\n```markdown\n## PR Review Comments — Fix Report\n\n**PR:** #{PR_NUMBER}\n**Total comments:** N\n**Processed:** M\n\n| # | File | Line | Type | Action | Status | Reply |\n|---|------|------|------|--------|--------|-------|\n| 1 | src\u002Fmain\u002FFoo.java | 42 | Actionable | Renamed variable | Fixed | Replied |\n| 2 | src\u002Fmain\u002FBar.java | 15 | Suggestion | Added null check | Fixed | Replied |\n| 3 | src\u002Fmain\u002FBaz.java | 20 | Actionable | — | Rejected | Replied |\n| 4 | src\u002Fmain\u002FBaz.java | 88 | Question | — | Skipped | — |\n| 5 | src\u002Fmain\u002FQux.java | 3 | Praise | — | Skipped | — |\n\n### Questions Requiring Human Response\n\n- **src\u002Fmain\u002FBaz.java:88** (@reviewer): \"Why is this method public?\"\n```\n\n## Error Handling\n\n| Scenario | Action |\n|----------|--------|\n| PR not found | Abort with message |\n| No comments on PR | Report \"No review comments found\" |\n| Comment references deleted file | Skip with warning |\n| Fix causes compilation failure | Revert and report as \"Unable to fix automatically\" |\n| Fix causes test failure | Revert and report as \"Fix caused regression\" |\n| API rate limit | Wait and retry (max 3 attempts) |\n\n## Integration Notes\n\n| Skill | Relationship | Context |\n|-------|-------------|---------|\n| `x-implement-story` | called-by | Invoked during Phase 4 (fix review comments) |\n| `x-fix-epic-pr` | called-by | Batch mode processes multiple PRs from an epic |\n| `x-push-branch` | calls | Uses Conventional Commits format for fix commits |\n| `x-review-codebase` | reads | Processes comments produced by specialist reviews |\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: Fix PR Comments\n\n## Purpose\n\nAutomates the process of addressing PR review comments for {{PROJECT_NAME}}. Reads all review comments from a pull request, classifies them by type, and implements fixes for actionable feedback.\n\n## Triggers\n\n- `\u002Fx-fix-pr` — fix comments on current branch's PR\n- `\u002Fx-fix-pr 123` — fix comments on PR #123\n\n## Parameters\n\n| Parameter | Required | Description |\n|-----------|----------|-------------|\n| `PR-number` | No | PR number to process. If omitted, detect from current branch. |\n\n## Workflow\n\n```\n1. DETECT     -> Identify PR (argument or branch)\n2. FETCH      -> Get all review comments via GitHub CLI\n3. CLASSIFY   -> Categorize each comment (actionable\u002Fsuggestion\u002Fquestion\u002Fpraise\u002Fresolved)\n4. FIX        -> Implement fixes for actionable comments\n5. VERIFY     -> Compile and test after each fix\n6. REPLY      -> Reply to each comment thread in PT-BR (fix summary or rejection reason)\n7. COMMIT     -> Commit with conventional commit message\n8. REPORT     -> Summarize actions taken\n```\n\n### Step 1 — Detect PR\n\nDetermine which PR to process:\n\n```bash\n# If argument is a number, use it directly\nPR_NUMBER=$1\n\n# If no argument, detect from current branch\nif [ -z \"$PR_NUMBER\" ]; then\n  gh pr view --json number --jq '.number'\nfi\n```\n\nIf no PR found, abort: `No PR found for current branch. Provide a PR number as argument.`\n\n### Step 2 — Fetch Review Comments\n\n```bash\n# Get all review comments (not issue comments)\ngh api repos\u002F{owner}\u002F{repo}\u002Fpulls\u002F{PR_NUMBER}\u002Fcomments \\\n  --jq '.[] | {id: .id, path: .path, line: .line, body: .body, user: .user.login, created_at: .created_at}'\n\n# Also get PR review threads for context\ngh api repos\u002F{owner}\u002F{repo}\u002Fpulls\u002F{PR_NUMBER}\u002Freviews \\\n  --jq '.[] | {id: .id, state: .state, body: .body, user: .user.login}'\n```\n\n### Step 3 — Classify Comments\n\nFor each comment, classify into one of:\n\n| Type | Description | Action |\n|------|-------------|--------|\n| **Actionable** | Clear request to change code (fix bug, rename, refactor) | Implement the fix |\n| **Suggestion** | Optional improvement with rationale | Implement if aligns with project standards |\n| **Question** | Reviewer asking for clarification | Skip (requires human response) |\n| **Praise** | Positive feedback | Skip |\n| **Resolved** | Already addressed or outdated | Skip |\n\n**Classification rules:**\n- Contains \"please change\", \"should be\", \"must\", \"fix\", \"bug\", \"wrong\" — Actionable\n- Contains \"consider\", \"maybe\", \"could\", \"suggestion\", \"nit\" — Suggestion\n- Contains \"?\", \"why\", \"what\", \"how does\" — Question\n- Contains \"LGTM\", \"nice\", \"good\", \"great\" — Praise\n- Thread is marked as resolved — Resolved\n\n### Step 4 — Implement Fixes\n\nFor each actionable\u002Fsuggestion comment:\n\n1. Read the file at the specified path and line:\n   ```bash\n   # Comment metadata provides path and line\n   cat -n {path} | sed -n '{line-5},{line+5}p'\n   ```\n\n2. Understand the reviewer's request\n\n3. Implement the fix using Edit tool\n\n4. If the fix requires understanding broader context, read surrounding code first\n\n**Ordering:** Process comments file-by-file to minimize context switching. Within a file, process top-to-bottom to avoid line number shifts.\n\n### Step 5 — Verify\n\nAfter each fix (or batch of fixes per file):\n\n```bash\n{{COMPILE_COMMAND}}\n{{TEST_COMMAND}}\n```\n\nIf compilation fails, revert the last change and try an alternative approach.\nIf tests fail, analyze the failure and adjust the fix.\n\n### Step 6 — Reply to Comments (PT-BR)\n\nAfter each comment is processed (fixed, skipped, or rejected), reply to the review comment thread **in Portuguese (pt-BR)** explaining the action taken.\n\n**Reply command:**\n```bash\n# Reply to an inline review comment thread\ngh api repos\u002F{owner}\u002F{repo}\u002Fpulls\u002F{PR_NUMBER}\u002Fcomments\u002F{comment_id}\u002Freplies \\\n  -f body=\"{message_in_portuguese}\"\n```\n\n**Reply templates by classification:**\n\n| Classification | Reply Template (PT-BR) |\n|---------------|----------------------|\n| **Actionable (fixed)** | `Corrigido. {descricao da alteracao feita}. Commit: {short_hash}` |\n| **Suggestion (accepted)** | `Sugestao aceita. {descricao da alteracao feita}. Commit: {short_hash}` |\n| **Suggestion (rejected)** | `Sugestao analisada, mas nao aplicada. Motivo: {razao tecnica pela qual nao faz sentido no contexto atual}` |\n| **Actionable (rejected)** | `Observacao analisada, mas nao faz sentido neste contexto. Motivo: {explicacao tecnica detalhada}` |\n| **Actionable (failed)** | `Tentei corrigir, mas a alteracao causou falha na compilacao\u002Ftestes. Necessita intervencao manual.` |\n| **Question** | _(no reply — requires human response)_ |\n| **Praise** | _(no reply)_ |\n| **Resolved** | _(no reply — already resolved)_ |\n\n**Rules:**\n- ALL replies MUST be in Portuguese (pt-BR)\n- Be specific: describe exactly what was changed and why\n- When rejecting, provide technical justification (reference project rules, architecture constraints, or coding standards)\n- Include commit hash when a fix was applied\n- Never reply to praise or already-resolved comments\n\n**Examples:**\n\nFix applied:\n```\nCorrigido. Renomeei a variavel `d` para `elapsedTimeInMs` conforme padrao de naming do projeto. Commit: abc1234\n```\n\nSuggestion rejected:\n```\nSugestao analisada, mas nao aplicada. Motivo: o metodo precisa ser publico porque implementa a interface Assembler, que define o contrato do pipeline. Tornar package-private quebraria o polimorfismo.\n```\n\nComment doesn't make sense:\n```\nObservacao analisada, mas nao faz sentido neste contexto. Motivo: o null check sugerido e desnecessario aqui — o parametro vem de um Optional.orElseThrow() na linha 42, garantindo que nunca sera null neste ponto.\n```\n\n### Step 7 — Commit\n\nAfter all fixes for a logical group are verified:\n\n```bash\ngit add {modified-files}\ngit commit -m \"fix({scope}): address PR review comments\n\n- {summary of change 1}\n- {summary of change 2}\n\nAddresses review comments on PR #{PR_NUMBER}\"\n```\n\n**Scope** should match the module\u002Flayer affected (e.g., `domain`, `api`, `config`).\n\n### Step 8 — Report\n\nOutput a summary table:\n\n```markdown\n## PR Review Comments — Fix Report\n\n**PR:** #{PR_NUMBER}\n**Total comments:** N\n**Processed:** M\n\n| # | File | Line | Type | Action | Status | Reply |\n|---|------|------|------|--------|--------|-------|\n| 1 | src\u002Fmain\u002FFoo.java | 42 | Actionable | Renamed variable | Fixed | Replied |\n| 2 | src\u002Fmain\u002FBar.java | 15 | Suggestion | Added null check | Fixed | Replied |\n| 3 | src\u002Fmain\u002FBaz.java | 20 | Actionable | — | Rejected | Replied |\n| 4 | src\u002Fmain\u002FBaz.java | 88 | Question | — | Skipped | — |\n| 5 | src\u002Fmain\u002FQux.java | 3 | Praise | — | Skipped | — |\n\n### Questions Requiring Human Response\n\n- **src\u002Fmain\u002FBaz.java:88** (@reviewer): \"Why is this method public?\"\n```\n\n## Error Handling\n\n| Scenario | Action |\n|----------|--------|\n| PR not found | Abort with message |\n| No comments on PR | Report \"No review comments found\" |\n| Comment references deleted file | Skip with warning |\n| Fix causes compilation failure | Revert and report as \"Unable to fix automatically\" |\n| Fix causes test failure | Revert and report as \"Fix caused regression\" |\n| API rate limit | Wait and retry (max 3 attempts) |\n\n## Integration Notes\n\n| Skill | Relationship | Context |\n|-------|-------------|---------|\n| `x-implement-story` | called-by | Invoked during Phase 4 (fix review comments) |\n| `x-fix-epic-pr` | called-by | Batch mode processes multiple PRs from an epic |\n| `x-push-branch` | calls | Uses Conventional Commits format for fix commits |\n| `x-review-codebase` | reads | Processes comments produced by specialist reviews |\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25,"context-budget":26,"user-invocable":27,"requires-capabilities":28},"Read, Write, Edit, Bash, Grep, Glob","[PR-number]","medium",true,[],"main","952a630c6f38d193a349d86fa18db1de8843e837","src\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring-clickhouse\u002F.claude\u002Fskills\u002Fx-fix-pr",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":39,"prompt":49,"zipAvailable":27},[40,43,46],{"tool":41,"command":42},"npx","npx skills add review-bench\u002Federcnj_ia-dev-environment --skill x-fix-pr",{"tool":44,"command":45},"bunx","bunx skills add review-bench\u002Federcnj_ia-dev-environment --skill x-fix-pr",{"tool":47,"command":48},"pnpm","pnpm dlx skills add review-bench\u002Federcnj_ia-dev-environment --skill x-fix-pr","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-clickhouse\u002F.claude\u002Fskills\u002Fx-fix-pr\u002FSKILL.md",[51],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"README.md","REFERENCE","参考文档",1692,"https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring-clickhouse\u002F.claude\u002Fskills\u002Fx-fix-pr\u002FREADME.md",[58,65,72,79,86,93],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"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":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"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":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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",[],[]]