[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KBDYCAR7YTHYKTHK7CQABB":3,"skill-same:01M6KBDYCAR7YTHYKTHK7CQABB":71},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":6,"updatedAt":56,"install":57,"resources":70},"01M6KBDYCAR7YTHYKTHK7CQABB","pr-review-expert",null,"Use when the user asks to review pull requests, analyze code changes, check for security issues in PRs, or assess code quality of diffs.","afaizalam2003\u002FMaster-claude-skill","afaizalam2003","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F222019359?v=4","01M6K8F2XNT0HKBPF00JQ78SV3","Faiz Alam","01M6K8F31EBXAPER0EG8R9HTR5",3,"MIT","https:\u002F\u002Fgithub.com\u002Fafaizalam2003\u002FMaster-claude-skill\u002Fblob\u002Fmain\u002Fengineering\u002Fpr-review-expert\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"pr review","pr","expert","pr review expert","review","analyze","changes","for","requests","assess","use","check","quality","pull","issues","code","code quality","pull requests","security","diffs","2026-11-10 10:12:30",false,"---\nname: \"pr-review-expert\"\ndescription: \"Use when the user asks to review pull requests, analyze code changes, check for security issues in PRs, or assess code quality of diffs.\"\n---\n\n# PR Review Expert\n\n**Tier:** POWERFUL\n**Category:** Engineering\n**Domain:** Code Review \u002F Quality Assurance\n\n---\n\n## Overview\n\nStructured, systematic code review for GitHub PRs and GitLab MRs. Goes beyond style nits — this skill\nperforms blast radius analysis, security scanning, breaking change detection, and test coverage delta\ncalculation. Produces a reviewer-ready report with a 30+ item checklist and prioritized findings.\n\n---\n\n## Core Capabilities\n\n- **Blast radius analysis** — trace which files, services, and downstream consumers could break\n- **Security scan** — SQL injection, XSS, auth bypass, secret exposure, dependency vulns\n- **Test coverage delta** — new code vs new tests ratio\n- **Breaking change detection** — API contracts, DB schema migrations, config keys\n- **Ticket linking** — verify Jira\u002FLinear ticket exists and matches scope\n- **Performance impact** — N+1 queries, bundle size regression, memory allocations\n\n---\n\n## When to Use\n\n- Before merging any PR\u002FMR that touches shared libraries, APIs, or DB schema\n- When a PR is large (>200 lines changed) and needs structured review\n- Onboarding new contributors whose PRs need thorough feedback\n- Security-sensitive code paths (auth, payments, PII handling)\n- After an incident — review similar PRs proactively\n\n---\n\n## Fetching the Diff\n\n### GitHub (gh CLI)\n```bash\n# View diff in terminal\ngh pr diff \u003CPR_NUMBER>\n\n# Get PR metadata (title, body, labels, linked issues)\ngh pr view \u003CPR_NUMBER> --json title,body,labels,assignees,milestone\n\n# List files changed\ngh pr diff \u003CPR_NUMBER> --name-only\n\n# Check CI status\ngh pr checks \u003CPR_NUMBER>\n\n# Download diff to file for analysis\ngh pr diff \u003CPR_NUMBER> > \u002Ftmp\u002Fpr-\u003CPR_NUMBER>.diff\n```\n\n### GitLab (glab CLI)\n```bash\n# View MR diff\nglab mr diff \u003CMR_IID>\n\n# MR details as JSON\nglab mr view \u003CMR_IID> --output json\n\n# List changed files\nglab mr diff \u003CMR_IID> --name-only\n\n# Download diff\nglab mr diff \u003CMR_IID> > \u002Ftmp\u002Fmr-\u003CMR_IID>.diff\n```\n\n---\n\n## Workflow\n\n### Step 1 — Fetch Context\n\n```bash\nPR=123\ngh pr view $PR --json title,body,labels,milestone,assignees | jq .\ngh pr diff $PR --name-only\ngh pr diff $PR > \u002Ftmp\u002Fpr-$PR.diff\n```\n\n### Step 2 — Blast Radius Analysis\n\nFor each changed file, identify:\n\n1. **Direct dependents** — who imports this file?\n```bash\n# Find all files importing a changed module\ngrep -r \"from ['\\\"].*changed-module['\\\"]\" src\u002F --include=\"*.ts\" -l\ngrep -r \"require(['\\\"].*changed-module\" src\u002F --include=\"*.js\" -l\n\n# Python\ngrep -r \"from changed_module import\\|import changed_module\" . --include=\"*.py\" -l\n```\n\n2. **Service boundaries** — does this change cross a service?\n```bash\n# Check if changed files span multiple services (monorepo)\ngh pr diff $PR --name-only | cut -d\u002F -f1-2 | sort -u\n```\n\n3. **Shared contracts** — types, interfaces, schemas\n```bash\ngh pr diff $PR --name-only | grep -E \"types\u002F|interfaces\u002F|schemas\u002F|models\u002F\"\n```\n\n**Blast radius severity:**\n- CRITICAL — shared library, DB model, auth middleware, API contract\n- HIGH     — service used by >3 others, shared config, env vars\n- MEDIUM   — single service internal change, utility function\n- LOW      — UI component, test file, docs\n\n### Step 3 — Security Scan\n\n```bash\nDIFF=\u002Ftmp\u002Fpr-$PR.diff\n\n# SQL Injection — raw query string interpolation\ngrep -n \"query\\|execute\\|raw(\" $DIFF | grep -E '\\$\\{|f\"|%s|format\\('\n\n# Hardcoded secrets\ngrep -nE \"(password|secret|api_key|token|private_key)\\s*=\\s*['\\\"][^'\\\"]{8,}\" $DIFF\n\n# AWS key pattern\ngrep -nE \"AKIA[0-9A-Z]{16}\" $DIFF\n\n# JWT secret in code\ngrep -nE \"jwt\\.sign\\(.*['\\\"][^'\\\"]{20,}['\\\"]\" $DIFF\n\n# XSS vectors\ngrep -n \"dangerouslySetInnerHTML\\|innerHTML\\s*=\" $DIFF\n\n# Auth bypass patterns\ngrep -n \"bypass\\|skip.*auth\\|noauth\\|TODO.*auth\" $DIFF\n\n# Insecure hash algorithms\ngrep -nE \"md5\\(|sha1\\(|createHash\\(['\\\"]md5|createHash\\(['\\\"]sha1\" $DIFF\n\n# eval \u002F exec\ngrep -nE \"\\beval\\(|\\bexec\\(|\\bsubprocess\\.call\\(\" $DIFF\n\n# Prototype pollution\ngrep -n \"__proto__\\|constructor\\[\" $DIFF\n\n# Path traversal risk\ngrep -nE \"path\\.join\\(.*req\\.|readFile\\(.*req\\.\" $DIFF\n```\n\n### Step 4 — Test Coverage Delta\n\n```bash\n# Count source vs test files changed\nCHANGED_SRC=$(gh pr diff $PR --name-only | grep -vE \"\\.test\\.|\\.spec\\.|__tests__\")\nCHANGED_TESTS=$(gh pr diff $PR --name-only | grep -E \"\\.test\\.|\\.spec\\.|__tests__\")\n\necho \"Source files changed: $(echo \"$CHANGED_SRC\" | wc -w)\"\necho \"Test files changed:   $(echo \"$CHANGED_TESTS\" | wc -w)\"\n\n# Lines of new logic vs new test lines\nLOGIC_LINES=$(grep \"^+\" \u002Ftmp\u002Fpr-$PR.diff | grep -v \"^+++\" | wc -l)\necho \"New lines added: $LOGIC_LINES\"\n\n# Run coverage locally\nnpm test -- --coverage --changedSince=main 2>\u002Fdev\u002Fnull | tail -20\npytest --cov --cov-report=term-missing 2>\u002Fdev\u002Fnull | tail -20\n```\n\n**Coverage delta rules:**\n- New function without tests → flag\n- Deleted tests without deleted code → flag\n- Coverage drop >5% → block merge\n- Auth\u002Fpayments paths → require 100% coverage\n\n### Step 5 — Breaking Change Detection\n\n#### API Contract Changes\n```bash\n# OpenAPI\u002FSwagger spec changes\ngrep -n \"openapi\\|swagger\" \u002Ftmp\u002Fpr-$PR.diff | head -20\n\n# REST route removals or renames\ngrep \"^-\" \u002Ftmp\u002Fpr-$PR.diff | grep -E \"router\\.(get|post|put|delete|patch)\\(\"\n\n# GraphQL schema removals\ngrep \"^-\" \u002Ftmp\u002Fpr-$PR.diff | grep -E \"^-\\s*(type |field |Query |Mutation )\"\n\n# TypeScript interface removals\ngrep \"^-\" \u002Ftmp\u002Fpr-$PR.diff | grep -E \"^-\\s*(export\\s+)?(interface|type) \"\n```\n\n#### DB Schema Changes\n```bash\n# Migration files added\ngh pr diff $PR --name-only | grep -E \"migrations?\u002F|alembic\u002F|knex\u002F\"\n\n# Destructive operations\ngrep -E \"DROP TABLE|DROP COLUMN|ALTER.*NOT NULL|TRUNCATE\" \u002Ftmp\u002Fpr-$PR.diff\n\n# Index removals (perf regression risk)\ngrep \"DROP INDEX\\|remove_index\" \u002Ftmp\u002Fpr-$PR.diff\n```\n\n#### Config \u002F Env Var Changes\n```bash\n# New env vars referenced in code (might be missing in prod)\ngrep \"^+\" \u002Ftmp\u002Fpr-$PR.diff | grep -oE \"process\\.env\\.[A-Z_]+\" | sort -u\n\n# Removed env vars (could break running instances)\ngrep \"^-\" \u002Ftmp\u002Fpr-$PR.diff | grep -oE \"process\\.env\\.[A-Z_]+\" | sort -u\n```\n\n### Step 6 — Performance Impact\n\n```bash\n# N+1 query patterns (DB calls inside loops)\ngrep -n \"\\.find\\|\\.findOne\\|\\.query\\|db\\.\" \u002Ftmp\u002Fpr-$PR.diff | grep \"^+\" | head -20\n# Then check surrounding context for forEach\u002Fmap\u002Ffor loops\n\n# Heavy new dependencies\ngrep \"^+\" \u002Ftmp\u002Fpr-$PR.diff | grep -E '\"[a-z@].*\":\\s*\"[0-9^~]' | head -20\n\n# Unbounded loops\ngrep -n \"while (true\\|while(true\" \u002Ftmp\u002Fpr-$PR.diff | grep \"^+\"\n\n# Missing await (accidentally sequential promises)\ngrep -n \"await.*await\" \u002Ftmp\u002Fpr-$PR.diff | grep \"^+\" | head -10\n\n# Large in-memory allocations\ngrep -n \"new Array([0-9]\\{4,\\}\\|Buffer\\.alloc\" \u002Ftmp\u002Fpr-$PR.diff | grep \"^+\"\n```\n\n---\n\n## Ticket Linking Verification\n\n```bash\n# Extract ticket references from PR body\ngh pr view $PR --json body | jq -r '.body' | \\\n  grep -oE \"(PROJ-[0-9]+|[A-Z]+-[0-9]+|https:\u002F\u002Flinear\\.app\u002F[^)\\\"]+)\" | sort -u\n\n# Verify Jira ticket exists (requires JIRA_API_TOKEN)\nTICKET=\"PROJ-123\"\ncurl -s -u \"user@company.com:$JIRA_API_TOKEN\" \\\n  \"https:\u002F\u002Fyour-org.atlassian.net\u002Frest\u002Fapi\u002F3\u002Fissue\u002F$TICKET\" | \\\n  jq '{key, summary: .fields.summary, status: .fields.status.name}'\n\n# Linear ticket\nLINEAR_ID=\"abc-123\"\ncurl -s -H \"Authorization: $LINEAR_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  --data \"{\\\"query\\\": \\\"{ issue(id: \\\\\\\"$LINEAR_ID\\\\\\\") { title state { name } } }\\\"}\" \\\n  https:\u002F\u002Fapi.linear.app\u002Fgraphql | jq .\n```\n\n---\n\n## Complete Review Checklist (30+ Items)\n\n```markdown\n## Code Review Checklist\n\n### Scope & Context\n- [ ] PR title accurately describes the change\n- [ ] PR description explains WHY, not just WHAT\n- [ ] Linked Jira\u002FLinear ticket exists and matches scope\n- [ ] No unrelated changes (scope creep)\n- [ ] Breaking changes documented in PR body\n\n### Blast Radius\n- [ ] Identified all files importing changed modules\n- [ ] Cross-service dependencies checked\n- [ ] Shared types\u002Finterfaces\u002Fschemas reviewed for breakage\n- [ ] New env vars documented in .env.example\n- [ ] DB migrations are reversible (have down() \u002F rollback)\n\n### Security\n- [ ] No hardcoded secrets or API keys\n- [ ] SQL queries use parameterized inputs (no string interpolation)\n- [ ] User inputs validated\u002Fsanitized before use\n- [ ] Auth\u002Fauthorization checks on all new endpoints\n- [ ] No XSS vectors (innerHTML, dangerouslySetInnerHTML)\n- [ ] New dependencies checked for known CVEs\n- [ ] No sensitive data in logs (PII, tokens, passwords)\n- [ ] File uploads validated (type, size, content-type)\n- [ ] CORS configured correctly for new endpoints\n\n### Testing\n- [ ] New public functions have unit tests\n- [ ] Edge cases covered (empty, null, max values)\n- [ ] Error paths tested (not just happy path)\n- [ ] Integration tests for API endpoint changes\n- [ ] No tests deleted without clear reason\n- [ ] Test names clearly describe what they verify\n\n### Breaking Changes\n- [ ] No API endpoints removed without deprecation notice\n- [ ] No required fields added to existing API responses\n- [ ] No DB columns removed without two-phase migration plan\n- [ ] No env vars removed that may be set in production\n- [ ] Backward-compatible for external API consumers\n\n### Performance\n- [ ] No N+1 query patterns introduced\n- [ ] DB indexes added for new query patterns\n- [ ] No unbounded loops on potentially large datasets\n- [ ] No heavy new dependencies without justification\n- [ ] Async operations correctly awaited\n- [ ] Caching considered for expensive repeated operations\n\n### Code Quality\n- [ ] No dead code or unused imports\n- [ ] Error handling present (no bare empty catch blocks)\n- [ ] Consistent with existing patterns and conventions\n- [ ] Complex logic has explanatory comments\n- [ ] No unresolved TODOs (or tracked in ticket)\n```\n\n---\n\n## Output Format\n\nStructure your review comment as:\n\n```\n## PR Review: [PR Title] (#NUMBER)\n\nBlast Radius: HIGH — changes lib\u002Fauth used by 5 services\nSecurity: 1 finding (medium severity)\nTests: Coverage delta +2%\nBreaking Changes: None detected\n\n--- MUST FIX (Blocking) ---\n\n1. SQL Injection risk in src\u002Fdb\u002Fusers.ts:42\n   Raw string interpolation in WHERE clause.\n   Fix: db.query(\"SELECT * WHERE id = $1\", [userId])\n\n--- SHOULD FIX (Non-blocking) ---\n\n2. Missing auth check on POST \u002Fapi\u002Fadmin\u002Freset\n   No role verification before destructive operation.\n\n--- SUGGESTIONS ---\n\n3. N+1 pattern in src\u002Fservices\u002Freports.ts:88\n   findUser() called inside results.map() — batch with findManyUsers(ids)\n\n--- LOOKS GOOD ---\n- Test coverage for new auth flow is thorough\n- DB migration has proper down() rollback method\n- Error handling consistent with rest of codebase\n```\n\n---\n\n## Common Pitfalls\n\n- **Reviewing style over substance** — let the linter handle style; focus on logic, security, correctness\n- **Missing blast radius** — a 5-line change in a shared utility can break 20 services\n- **Approving untested happy paths** — always verify error paths have coverage\n- **Ignoring migration risk** — NOT NULL additions need a default or two-phase migration\n- **Indirect secret exposure** — secrets in error messages\u002Flogs, not just hardcoded values\n- **Skipping large PRs** — if a PR is too large to review properly, request it be split\n\n---\n\n## Best Practices\n\n1. Read the linked ticket before looking at code — context prevents false positives\n2. Check CI status before reviewing — don't review code that fails to build\n3. Prioritize blast radius and security over style\n4. Reproduce locally for non-trivial auth or performance changes\n5. Label each comment clearly: \"nit:\", \"must:\", \"question:\", \"suggestion:\"\n6. Batch all comments in one review round — don't trickle feedback\n7. Acknowledge good patterns, not just problems — specific praise improves culture\n","# PR Review Expert\n\n**Tier:** POWERFUL\n**Category:** Engineering\n**Domain:** Code Review \u002F Quality Assurance\n\n---\n\n## Overview\n\nStructured, systematic code review for GitHub PRs and GitLab MRs. Goes beyond style nits — this skill\nperforms blast radius analysis, security scanning, breaking change detection, and test coverage delta\ncalculation. Produces a reviewer-ready report with a 30+ item checklist and prioritized findings.\n\n---\n\n## Core Capabilities\n\n- **Blast radius analysis** — trace which files, services, and downstream consumers could break\n- **Security scan** — SQL injection, XSS, auth bypass, secret exposure, dependency vulns\n- **Test coverage delta** — new code vs new tests ratio\n- **Breaking change detection** — API contracts, DB schema migrations, config keys\n- **Ticket linking** — verify Jira\u002FLinear ticket exists and matches scope\n- **Performance impact** — N+1 queries, bundle size regression, memory allocations\n\n---\n\n## When to Use\n\n- Before merging any PR\u002FMR that touches shared libraries, APIs, or DB schema\n- When a PR is large (>200 lines changed) and needs structured review\n- Onboarding new contributors whose PRs need thorough feedback\n- Security-sensitive code paths (auth, payments, PII handling)\n- After an incident — review similar PRs proactively\n\n---\n\n## Fetching the Diff\n\n### GitHub (gh CLI)\n```bash\n# View diff in terminal\ngh pr diff \u003CPR_NUMBER>\n\n# Get PR metadata (title, body, labels, linked issues)\ngh pr view \u003CPR_NUMBER> --json title,body,labels,assignees,milestone\n\n# List files changed\ngh pr diff \u003CPR_NUMBER> --name-only\n\n# Check CI status\ngh pr checks \u003CPR_NUMBER>\n\n# Download diff to file for analysis\ngh pr diff \u003CPR_NUMBER> > \u002Ftmp\u002Fpr-\u003CPR_NUMBER>.diff\n```\n\n### GitLab (glab CLI)\n```bash\n# View MR diff\nglab mr diff \u003CMR_IID>\n\n# MR details as JSON\nglab mr view \u003CMR_IID> --output json\n\n# List changed files\nglab mr diff \u003CMR_IID> --name-only\n\n# Download diff\nglab mr diff \u003CMR_IID> > \u002Ftmp\u002Fmr-\u003CMR_IID>.diff\n```\n\n---\n\n## Workflow\n\n### Step 1 — Fetch Context\n\n```bash\nPR=123\ngh pr view $PR --json title,body,labels,milestone,assignees | jq .\ngh pr diff $PR --name-only\ngh pr diff $PR > \u002Ftmp\u002Fpr-$PR.diff\n```\n\n### Step 2 — Blast Radius Analysis\n\nFor each changed file, identify:\n\n1. **Direct dependents** — who imports this file?\n```bash\n# Find all files importing a changed module\ngrep -r \"from ['\\\"].*changed-module['\\\"]\" src\u002F --include=\"*.ts\" -l\ngrep -r \"require(['\\\"].*changed-module\" src\u002F --include=\"*.js\" -l\n\n# Python\ngrep -r \"from changed_module import\\|import changed_module\" . --include=\"*.py\" -l\n```\n\n2. **Service boundaries** — does this change cross a service?\n```bash\n# Check if changed files span multiple services (monorepo)\ngh pr diff $PR --name-only | cut -d\u002F -f1-2 | sort -u\n```\n\n3. **Shared contracts** — types, interfaces, schemas\n```bash\ngh pr diff $PR --name-only | grep -E \"types\u002F|interfaces\u002F|schemas\u002F|models\u002F\"\n```\n\n**Blast radius severity:**\n- CRITICAL — shared library, DB model, auth middleware, API contract\n- HIGH     — service used by >3 others, shared config, env vars\n- MEDIUM   — single service internal change, utility function\n- LOW      — UI component, test file, docs\n\n### Step 3 — Security Scan\n\n```bash\nDIFF=\u002Ftmp\u002Fpr-$PR.diff\n\n# SQL Injection — raw query string interpolation\ngrep -n \"query\\|execute\\|raw(\" $DIFF | grep -E '\\$\\{|f\"|%s|format\\('\n\n# Hardcoded secrets\ngrep -nE \"(password|secret|api_key|token|private_key)\\s*=\\s*['\\\"][^'\\\"]{8,}\" $DIFF\n\n# AWS key pattern\ngrep -nE \"AKIA[0-9A-Z]{16}\" $DIFF\n\n# JWT secret in code\ngrep -nE \"jwt\\.sign\\(.*['\\\"][^'\\\"]{20,}['\\\"]\" $DIFF\n\n# XSS vectors\ngrep -n \"dangerouslySetInnerHTML\\|innerHTML\\s*=\" $DIFF\n\n# Auth bypass patterns\ngrep -n \"bypass\\|skip.*auth\\|noauth\\|TODO.*auth\" $DIFF\n\n# Insecure hash algorithms\ngrep -nE \"md5\\(|sha1\\(|createHash\\(['\\\"]md5|createHash\\(['\\\"]sha1\" $DIFF\n\n# eval \u002F exec\ngrep -nE \"\\beval\\(|\\bexec\\(|\\bsubprocess\\.call\\(\" $DIFF\n\n# Prototype pollution\ngrep -n \"__proto__\\|constructor\\[\" $DIFF\n\n# Path traversal risk\ngrep -nE \"path\\.join\\(.*req\\.|readFile\\(.*req\\.\" $DIFF\n```\n\n### Step 4 — Test Coverage Delta\n\n```bash\n# Count source vs test files changed\nCHANGED_SRC=$(gh pr diff $PR --name-only | grep -vE \"\\.test\\.|\\.spec\\.|__tests__\")\nCHANGED_TESTS=$(gh pr diff $PR --name-only | grep -E \"\\.test\\.|\\.spec\\.|__tests__\")\n\necho \"Source files changed: $(echo \"$CHANGED_SRC\" | wc -w)\"\necho \"Test files changed:   $(echo \"$CHANGED_TESTS\" | wc -w)\"\n\n# Lines of new logic vs new test lines\nLOGIC_LINES=$(grep \"^+\" \u002Ftmp\u002Fpr-$PR.diff | grep -v \"^+++\" | wc -l)\necho \"New lines added: $LOGIC_LINES\"\n\n# Run coverage locally\nnpm test -- --coverage --changedSince=main 2>\u002Fdev\u002Fnull | tail -20\npytest --cov --cov-report=term-missing 2>\u002Fdev\u002Fnull | tail -20\n```\n\n**Coverage delta rules:**\n- New function without tests → flag\n- Deleted tests without deleted code → flag\n- Coverage drop >5% → block merge\n- Auth\u002Fpayments paths → require 100% coverage\n\n### Step 5 — Breaking Change Detection\n\n#### API Contract Changes\n```bash\n# OpenAPI\u002FSwagger spec changes\ngrep -n \"openapi\\|swagger\" \u002Ftmp\u002Fpr-$PR.diff | head -20\n\n# REST route removals or renames\ngrep \"^-\" \u002Ftmp\u002Fpr-$PR.diff | grep -E \"router\\.(get|post|put|delete|patch)\\(\"\n\n# GraphQL schema removals\ngrep \"^-\" \u002Ftmp\u002Fpr-$PR.diff | grep -E \"^-\\s*(type |field |Query |Mutation )\"\n\n# TypeScript interface removals\ngrep \"^-\" \u002Ftmp\u002Fpr-$PR.diff | grep -E \"^-\\s*(export\\s+)?(interface|type) \"\n```\n\n#### DB Schema Changes\n```bash\n# Migration files added\ngh pr diff $PR --name-only | grep -E \"migrations?\u002F|alembic\u002F|knex\u002F\"\n\n# Destructive operations\ngrep -E \"DROP TABLE|DROP COLUMN|ALTER.*NOT NULL|TRUNCATE\" \u002Ftmp\u002Fpr-$PR.diff\n\n# Index removals (perf regression risk)\ngrep \"DROP INDEX\\|remove_index\" \u002Ftmp\u002Fpr-$PR.diff\n```\n\n#### Config \u002F Env Var Changes\n```bash\n# New env vars referenced in code (might be missing in prod)\ngrep \"^+\" \u002Ftmp\u002Fpr-$PR.diff | grep -oE \"process\\.env\\.[A-Z_]+\" | sort -u\n\n# Removed env vars (could break running instances)\ngrep \"^-\" \u002Ftmp\u002Fpr-$PR.diff | grep -oE \"process\\.env\\.[A-Z_]+\" | sort -u\n```\n\n### Step 6 — Performance Impact\n\n```bash\n# N+1 query patterns (DB calls inside loops)\ngrep -n \"\\.find\\|\\.findOne\\|\\.query\\|db\\.\" \u002Ftmp\u002Fpr-$PR.diff | grep \"^+\" | head -20\n# Then check surrounding context for forEach\u002Fmap\u002Ffor loops\n\n# Heavy new dependencies\ngrep \"^+\" \u002Ftmp\u002Fpr-$PR.diff | grep -E '\"[a-z@].*\":\\s*\"[0-9^~]' | head -20\n\n# Unbounded loops\ngrep -n \"while (true\\|while(true\" \u002Ftmp\u002Fpr-$PR.diff | grep \"^+\"\n\n# Missing await (accidentally sequential promises)\ngrep -n \"await.*await\" \u002Ftmp\u002Fpr-$PR.diff | grep \"^+\" | head -10\n\n# Large in-memory allocations\ngrep -n \"new Array([0-9]\\{4,\\}\\|Buffer\\.alloc\" \u002Ftmp\u002Fpr-$PR.diff | grep \"^+\"\n```\n\n---\n\n## Ticket Linking Verification\n\n```bash\n# Extract ticket references from PR body\ngh pr view $PR --json body | jq -r '.body' | \\\n  grep -oE \"(PROJ-[0-9]+|[A-Z]+-[0-9]+|https:\u002F\u002Flinear\\.app\u002F[^)\\\"]+)\" | sort -u\n\n# Verify Jira ticket exists (requires JIRA_API_TOKEN)\nTICKET=\"PROJ-123\"\ncurl -s -u \"user@company.com:$JIRA_API_TOKEN\" \\\n  \"https:\u002F\u002Fyour-org.atlassian.net\u002Frest\u002Fapi\u002F3\u002Fissue\u002F$TICKET\" | \\\n  jq '{key, summary: .fields.summary, status: .fields.status.name}'\n\n# Linear ticket\nLINEAR_ID=\"abc-123\"\ncurl -s -H \"Authorization: $LINEAR_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  --data \"{\\\"query\\\": \\\"{ issue(id: \\\\\\\"$LINEAR_ID\\\\\\\") { title state { name } } }\\\"}\" \\\n  https:\u002F\u002Fapi.linear.app\u002Fgraphql | jq .\n```\n\n---\n\n## Complete Review Checklist (30+ Items)\n\n```markdown\n## Code Review Checklist\n\n### Scope & Context\n- [ ] PR title accurately describes the change\n- [ ] PR description explains WHY, not just WHAT\n- [ ] Linked Jira\u002FLinear ticket exists and matches scope\n- [ ] No unrelated changes (scope creep)\n- [ ] Breaking changes documented in PR body\n\n### Blast Radius\n- [ ] Identified all files importing changed modules\n- [ ] Cross-service dependencies checked\n- [ ] Shared types\u002Finterfaces\u002Fschemas reviewed for breakage\n- [ ] New env vars documented in .env.example\n- [ ] DB migrations are reversible (have down() \u002F rollback)\n\n### Security\n- [ ] No hardcoded secrets or API keys\n- [ ] SQL queries use parameterized inputs (no string interpolation)\n- [ ] User inputs validated\u002Fsanitized before use\n- [ ] Auth\u002Fauthorization checks on all new endpoints\n- [ ] No XSS vectors (innerHTML, dangerouslySetInnerHTML)\n- [ ] New dependencies checked for known CVEs\n- [ ] No sensitive data in logs (PII, tokens, passwords)\n- [ ] File uploads validated (type, size, content-type)\n- [ ] CORS configured correctly for new endpoints\n\n### Testing\n- [ ] New public functions have unit tests\n- [ ] Edge cases covered (empty, null, max values)\n- [ ] Error paths tested (not just happy path)\n- [ ] Integration tests for API endpoint changes\n- [ ] No tests deleted without clear reason\n- [ ] Test names clearly describe what they verify\n\n### Breaking Changes\n- [ ] No API endpoints removed without deprecation notice\n- [ ] No required fields added to existing API responses\n- [ ] No DB columns removed without two-phase migration plan\n- [ ] No env vars removed that may be set in production\n- [ ] Backward-compatible for external API consumers\n\n### Performance\n- [ ] No N+1 query patterns introduced\n- [ ] DB indexes added for new query patterns\n- [ ] No unbounded loops on potentially large datasets\n- [ ] No heavy new dependencies without justification\n- [ ] Async operations correctly awaited\n- [ ] Caching considered for expensive repeated operations\n\n### Code Quality\n- [ ] No dead code or unused imports\n- [ ] Error handling present (no bare empty catch blocks)\n- [ ] Consistent with existing patterns and conventions\n- [ ] Complex logic has explanatory comments\n- [ ] No unresolved TODOs (or tracked in ticket)\n```\n\n---\n\n## Output Format\n\nStructure your review comment as:\n\n```\n## PR Review: [PR Title] (#NUMBER)\n\nBlast Radius: HIGH — changes lib\u002Fauth used by 5 services\nSecurity: 1 finding (medium severity)\nTests: Coverage delta +2%\nBreaking Changes: None detected\n\n--- MUST FIX (Blocking) ---\n\n1. SQL Injection risk in src\u002Fdb\u002Fusers.ts:42\n   Raw string interpolation in WHERE clause.\n   Fix: db.query(\"SELECT * WHERE id = $1\", [userId])\n\n--- SHOULD FIX (Non-blocking) ---\n\n2. Missing auth check on POST \u002Fapi\u002Fadmin\u002Freset\n   No role verification before destructive operation.\n\n--- SUGGESTIONS ---\n\n3. N+1 pattern in src\u002Fservices\u002Freports.ts:88\n   findUser() called inside results.map() — batch with findManyUsers(ids)\n\n--- LOOKS GOOD ---\n- Test coverage for new auth flow is thorough\n- DB migration has proper down() rollback method\n- Error handling consistent with rest of codebase\n```\n\n---\n\n## Common Pitfalls\n\n- **Reviewing style over substance** — let the linter handle style; focus on logic, security, correctness\n- **Missing blast radius** — a 5-line change in a shared utility can break 20 services\n- **Approving untested happy paths** — always verify error paths have coverage\n- **Ignoring migration risk** — NOT NULL additions need a default or two-phase migration\n- **Indirect secret exposure** — secrets in error messages\u002Flogs, not just hardcoded values\n- **Skipping large PRs** — if a PR is too large to review properly, request it be split\n\n---\n\n## Best Practices\n\n1. Read the linked ticket before looking at code — context prevents false positives\n2. Check CI status before reviewing — don't review code that fails to build\n3. Prioritize blast radius and security over style\n4. Reproduce locally for non-trivial auth or performance changes\n5. Label each comment clearly: \"nit:\", \"must:\", \"question:\", \"suggestion:\"\n6. Batch all comments in one review round — don't trickle feedback\n7. Acknowledge good patterns, not just problems — specific praise improves culture\n",{"name":5,"description":7},"main","0b48cbb0e6d5be6ff68c0f6b28bc0c65ee21c4a1","engineering\u002Fpr-review-expert",2,"https:\u002F\u002Fgithub.com\u002Fafaizalam2003\u002FMaster-claude-skill","https:\u002F\u002Fgithub.com\u002Fafaizalam2003","https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fmdfaizalam2003\u002F","2026-04-01 04:35:43",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add afaizalam2003\u002FMaster-claude-skill --skill pr-review-expert",{"tool":63,"command":64},"bunx","bunx skills add afaizalam2003\u002FMaster-claude-skill --skill pr-review-expert",{"tool":66,"command":67},"pnpm","pnpm dlx skills add afaizalam2003\u002FMaster-claude-skill --skill pr-review-expert","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fafaizalam2003\u002FMaster-claude-skill\u002Fblob\u002Fmain\u002Fengineering\u002Fpr-review-expert\u002FSKILL.md",true,[],[72,99,124,149,180,199],{"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":81,"publishedAt":44},"01M6KC4E8MYR9DBAZTAXHKYMMH","soc2-compliance","Use when the user asks to prepare for SOC 2 audits, map Trust Service Criteria, build control matrices, collect audit evidence, perform gap analysis, or assess SOC 2 Type I vs Type II readiness.","https:\u002F\u002Fgithub.com\u002Fafaizalam2003\u002FMaster-claude-skill\u002Fblob\u002Fmain\u002Fra-qm-team\u002Fsoc2-compliance\u002FSKILL.md",[78],{"categoryNo":79,"categoryName":80,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000037","律师与法务",[82,83,84,85,86,87,88,89,34,90,91,92,93,94,95,96,97,98,33,31],"compliance","soc2","soc2 compliance","audit evidence","audit","collect","soc","analysis","evidence","trust","build","map","control","type","gap","readiness","gap analysis",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":44},"01M6KC461R3GKGZ1TAYHVR1MW9","risk-management-specialist","Medical device risk management specialist implementing ISO 14971 throughout product lifecycle. Provides risk analysis, risk evaluation, risk control, and post-production information analysis. Use when user mentions risk management, ISO 14971, risk analysis, FMEA, fault tree analysis, hazard identification, risk control, risk matrix, benefit-risk analysis, residual risk, risk acceptability, or post-market risk.","https:\u002F\u002Fgithub.com\u002Fafaizalam2003\u002FMaster-claude-skill\u002Fblob\u002Fmain\u002Fra-qm-team\u002Frisk-management-specialist\u002FSKILL.md",[],[106,107,108,109,110,111,112,113,89,34,114,115,116,117,118,119,120,121,122,123],"risk","risk management specialist","management","risk management","risk evaluation","product","Evaluation","lifecycle","risk matrix","iso","medical","iso 14971","identification","information","post-production","tree","matrix","implementing",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":44},"01M6KC3HF5ZFSSP2NZF68PEPFB","regulatory-affairs-head","Senior Regulatory Affairs Manager for HealthTech and MedTech companies. Prepares FDA 510(k), De Novo, and PMA submission packages; analyzes regulatory pathways for new medical devices; drafts responses to FDA deficiency letters and Notified Body queries; develops CE marking technical documentation under EU MDR 2017\u002F745; coordinates multi-market approval strategies across FDA, EU, Health Canada, PMDA, and NMPA; and maintains regulatory intelligence on evolving standards. Use when users need to plan or execute FDA submissions, navigate 510(k) or PMA approval processes, achieve CE marking, prepare pre-submission meeting materials, write regulatory strategy documents, respond to agency queries, or manage compliance documentation for medical device market access.","https:\u002F\u002Fgithub.com\u002Fafaizalam2003\u002FMaster-claude-skill\u002Fblob\u002Fmain\u002Fra-qm-team\u002Fregulatory-affairs-head\u002FSKILL.md",[],[131,132,133,134,135,136,137,138,139,34,140,141,142,143,144,145,146,147,148,31],"regulatory affairs head","regulatory","head","documents","devices","health","plan","write","strategy","standards","queries","manage","strategies","de","users","respond","medical devices","manager",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":163,"publishedAt":44},"01M6KC34Z8M1559EY1CXYBJB1A","quality-manager-qms-iso13485","ISO 13485 Quality Management System implementation and maintenance for medical device organizations. Provides QMS design, documentation control, internal auditing, CAPA management, and certification support. Use when working with medical device quality systems, preparing for ISO 13485 audits, managing regulatory compliance documentation, setting up corrective actions, or building audit preparation programs. Useful for quality management, audit preparation, regulatory compliance, medical device documentation, and corrective action workflows.","https:\u002F\u002Fgithub.com\u002Fafaizalam2003\u002FMaster-claude-skill\u002Fblob\u002Fmain\u002Fra-qm-team\u002Fquality-manager-qms-iso13485\u002FSKILL.md",[155,160],{"categoryNo":156,"categoryName":157,"taxonomyType":158,"taxonomyTypeDesc":159},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":161,"categoryName":162,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000032","设计师",[164,36,148,165,166,167,168,169,170,34,171,172,173,174,175,176,177,178,31,179],"quality manager qms iso13485","design","workflows","validation","actions","certification","system","maintenance","document","systems","records","ISO 13485","organizations","corrective action","internal audit","preparation",{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":187,"publishedAt":44},"01M6KC2FXHBHXYX2ZZ17Y3GDB4","quality-manager-qmr","Senior Quality Manager Responsible Person (QMR) for HealthTech and MedTech companies. Provides quality system governance, management review leadership, regulatory compliance oversight, and quality performance monitoring per ISO 13485 Clause 5.5.2.","https:\u002F\u002Fgithub.com\u002Fafaizalam2003\u002FMaster-claude-skill\u002Fblob\u002Fmain\u002Fra-qm-team\u002Fquality-manager-qmr\u002FSKILL.md",[186],{"categoryNo":79,"categoryName":80,"taxonomyType":21,"taxonomyTypeDesc":22},[188,36,148,28,189,190,191,192,82,193,170,194,132,195,196,197,115,175,31,198],"quality manager qmr","policy","performance","governance","monitoring","regulatory compliance","oversight","cost","culture","leadership","person",{"skillNo":200,"name":201,"nameZh":6,"description":202,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":203,"categories":204,"keywords":212,"publishedAt":44},"01M6KC1VRR5JTDBNZANHPS6VR6","quality-documentation-manager","Document control system management for medical device QMS. Covers document numbering, version control, change management, and 21 CFR Part 11 compliance. Use for document control procedures, change control workflow, document numbering, version management, electronic signature compliance, or regulatory documentation review.","https:\u002F\u002Fgithub.com\u002Fafaizalam2003\u002FMaster-claude-skill\u002Fblob\u002Fmain\u002Fra-qm-team\u002Fquality-documentation-manager\u002FSKILL.md",[205,208,211],{"categoryNo":206,"categoryName":207,"taxonomyType":158,"taxonomyTypeDesc":159},"01JBSEEDCAT000000000000002","文档处理",{"categoryNo":209,"categoryName":210,"taxonomyType":158,"taxonomyTypeDesc":159},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":79,"categoryName":80,"taxonomyType":21,"taxonomyTypeDesc":22},[213,214,36,148,28,215,216,86,170,217,218,219,220,221,116,222,223,224,225,31],"documentation","quality documentation manager","workflow","change","change management","list","master","system management","documentation review","cfr","21 cfr part 11","change control","retention"]