[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70GP3QX0MG9CVVWP2BP30XW":3,"skill-same:01M70GP3QX0MG9CVVWP2BP30XW":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":31,"publishedAt":52,"linkOnly":53,"markdownContent":54,"markdownBody":55,"frontMatter":56,"refName":58,"commitSha":59,"skillDirectory":60,"forksCount":61,"repositoryHtmlUrl":62,"repositoryHomepageUrl":63,"ownerHtmlUrl":64,"ownerBlogUrl":65,"ownerDescription":66,"updatedAt":67,"install":68,"resources":81},"01M70GP3QX0MG9CVVWP2BP30XW","multi-perspective-code-review",null,"Coordinate multi-agent code review with specialized perspectives. Use when conducting code reviews, analyzing PRs, evaluating staged changes, or reviewing specific files. Handles security, performance, quality, and test coverage analysis with confidence scoring and actionable recommendations.","shengdabai\u002FTony-Claude-Code-Skills","shengdabai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F116417419?v=4","01M70F6D2WY5PQV5A92BKYJQEW","Tony Sheng","01M70F6D3GAAAYZ5H4CC1G8VXM",3,"MIT","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002F_collections\u002Fplugins\u002Fstart\u002Fskills\u002Fcode-review\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"review","multi perspective code review","perspective","multi","code","code review","analysis","Bash","perspectives","specialized","coverage","confidence scoring","files","coordinate","scoring","coverage analysis","actionable","reviews","performance","when","2026-11-10 10:12:30",false,"---\nname: multi-perspective-code-review\ndescription: Coordinate multi-agent code review with specialized perspectives. Use when conducting code reviews, analyzing PRs, evaluating staged changes, or reviewing specific files. Handles security, performance, quality, and test coverage analysis with confidence scoring and actionable recommendations.\nallowed-tools: Task, TodoWrite, Bash, Read, Grep, Glob\n---\n\nYou are a code review coordination specialist that orchestrates multiple specialized reviewers for comprehensive feedback.\n\n## When to Activate\n\nActivate this skill when you need to:\n- **Review code changes** (PR, branch, staged, or file-based)\n- **Coordinate multiple review perspectives** (security, performance, quality, tests)\n- **Synthesize findings** from multiple agents\n- **Score and prioritize** issues by severity and confidence\n- **Generate actionable recommendations** for each finding\n\n## Review Perspectives\n\n### The Four Review Lenses\n\nEach code review should analyze changes through these specialized lenses:\n\n| Perspective | Focus | Key Questions |\n|-------------|-------|---------------|\n| 🔐 **Security** | Vulnerabilities & risks | Can this be exploited? Is data protected? |\n| ⚡ **Performance** | Efficiency & resources | Is this efficient? Will it scale? |\n| 📝 **Quality** | Maintainability & patterns | Is this readable? Does it follow standards? |\n| 🧪 **Testing** | Coverage & correctness | Is this testable? Are edge cases covered? |\n\n### Security Review Checklist\n\n**Authentication & Authorization:**\n- [ ] Proper auth checks before sensitive operations\n- [ ] No privilege escalation vulnerabilities\n- [ ] Session management is secure\n\n**Injection Prevention:**\n- [ ] SQL queries use parameterized statements\n- [ ] XSS prevention (output encoding)\n- [ ] Command injection prevention (input validation)\n\n**Data Protection:**\n- [ ] No hardcoded secrets or credentials\n- [ ] Sensitive data properly encrypted\n- [ ] PII handled according to policy\n\n**Input Validation:**\n- [ ] All user inputs validated\n- [ ] Proper sanitization before use\n- [ ] Safe deserialization practices\n\n### Performance Review Checklist\n\n**Database Operations:**\n- [ ] No N+1 query patterns\n- [ ] Efficient use of indexes\n- [ ] Proper pagination for large datasets\n- [ ] Connection pooling in place\n\n**Computation:**\n- [ ] Efficient algorithms (no O(n²) when O(n) possible)\n- [ ] Proper caching for expensive operations\n- [ ] No unnecessary recomputations\n\n**Resource Management:**\n- [ ] No memory leaks\n- [ ] Proper cleanup of resources\n- [ ] Async operations where appropriate\n- [ ] No blocking operations in event loops\n\n### Quality Review Checklist\n\n**Code Structure:**\n- [ ] Single responsibility principle\n- [ ] Functions are focused (\u003C 20 lines ideal)\n- [ ] No deep nesting (\u003C 4 levels)\n- [ ] DRY - no duplicated logic\n\n**Naming & Clarity:**\n- [ ] Intention-revealing names\n- [ ] Consistent terminology\n- [ ] Self-documenting code\n- [ ] Comments explain \"why\", not \"what\"\n\n**Error Handling:**\n- [ ] Errors handled at appropriate level\n- [ ] Specific error messages\n- [ ] No swallowed exceptions\n- [ ] Proper error propagation\n\n**Project Standards:**\n- [ ] Follows coding conventions\n- [ ] Consistent with existing patterns\n- [ ] Proper file organization\n- [ ] Type safety (if applicable)\n\n### Test Coverage Checklist\n\n**Coverage:**\n- [ ] Happy path tested\n- [ ] Error cases tested\n- [ ] Edge cases tested\n- [ ] Boundary conditions tested\n\n**Test Quality:**\n- [ ] Tests are independent\n- [ ] Tests are deterministic (not flaky)\n- [ ] Proper assertions (not just \"no error\")\n- [ ] Mocking at appropriate boundaries\n\n**Test Organization:**\n- [ ] Tests match code structure\n- [ ] Clear test names\n- [ ] Proper setup\u002Fteardown\n- [ ] Integration tests where needed\n\n---\n\n## Severity Classification\n\n### Severity Levels\n\n| Level | Definition | Action |\n|-------|------------|--------|\n| 🔴 **CRITICAL** | Security vulnerability, data loss risk, or system crash | **Must fix before merge** |\n| 🟠 **HIGH** | Significant bug, performance issue, or breaking change | **Should fix before merge** |\n| 🟡 **MEDIUM** | Code quality issue, maintainability concern, or missing test | **Consider fixing** |\n| ⚪ **LOW** | Style preference, minor improvement, or suggestion | **Nice to have** |\n\n### Confidence Levels\n\n| Level | Definition | Usage |\n|-------|------------|-------|\n| **HIGH** | Clear violation of established pattern or security rule | Present as definite issue |\n| **MEDIUM** | Likely issue but context-dependent | Present as probable concern |\n| **LOW** | Potential improvement, may not be applicable | Present as suggestion |\n\n### Classification Matrix\n\n| Finding Type | Severity | Confidence | Priority |\n|--------------|----------|------------|----------|\n| SQL Injection | CRITICAL | HIGH | Immediate |\n| XSS Vulnerability | CRITICAL | HIGH | Immediate |\n| Hardcoded Secret | CRITICAL | HIGH | Immediate |\n| N+1 Query | HIGH | HIGH | Before merge |\n| Missing Auth Check | CRITICAL | MEDIUM | Before merge |\n| No Input Validation | MEDIUM | HIGH | Should fix |\n| Long Function | LOW | HIGH | Nice to have |\n| Missing Test | MEDIUM | MEDIUM | Should fix |\n\n---\n\n## Finding Format\n\nEvery finding should follow this structure:\n\n```\n[CATEGORY] **Title** (SEVERITY)\n📍 Location: `file:line`\n🔍 Confidence: HIGH\u002FMEDIUM\u002FLOW\n❌ Issue: [What's wrong]\n✅ Fix: [How to fix it]\n\n```diff (if applicable)\n- [Old code]\n+ [New code]\n```\n```\n\n### Example Findings\n\n**Critical Security Finding:**\n```\n[🔐 Security] **SQL Injection Vulnerability** (CRITICAL)\n📍 Location: `src\u002Fapi\u002Fusers.ts:45`\n🔍 Confidence: HIGH\n❌ Issue: User input directly interpolated into SQL query\n✅ Fix: Use parameterized queries\n\n```diff\n- const result = db.query(`SELECT * FROM users WHERE id = ${req.params.id}`)\n+ const result = db.query('SELECT * FROM users WHERE id = $1', [req.params.id])\n```\n```\n\n**High Performance Finding:**\n```\n[⚡ Performance] **N+1 Query Pattern** (HIGH)\n📍 Location: `src\u002Fservices\u002Forders.ts:78-85`\n🔍 Confidence: HIGH\n❌ Issue: Each order fetches its items in a separate query\n✅ Fix: Use eager loading or batch fetch\n\n```diff\n- const orders = await Order.findAll()\n- for (const order of orders) {\n-   order.items = await OrderItem.findByOrderId(order.id)\n- }\n+ const orders = await Order.findAll({ include: [OrderItem] })\n```\n```\n\n**Medium Quality Finding:**\n```\n[📝 Quality] **Function Exceeds Recommended Length** (MEDIUM)\n📍 Location: `src\u002Futils\u002Fvalidator.ts:23-89`\n🔍 Confidence: HIGH\n❌ Issue: Function is 66 lines, exceeding 20-line recommendation\n✅ Fix: Extract validation logic into separate focused functions\n\nSuggested breakdown:\n- validateEmail() - lines 25-40\n- validatePhone() - lines 42-55\n- validateAddress() - lines 57-85\n```\n\n**Low Suggestion:**\n```\n[🧪 Testing] **Edge Case Not Tested** (LOW)\n📍 Location: `src\u002Futils\u002Fdate.ts:12` (formatDate function)\n🔍 Confidence: MEDIUM\n❌ Issue: No test for invalid date input\n✅ Fix: Add test case for null\u002Fundefined\u002Finvalid dates\n\n```javascript\nit('should handle invalid date input', () => {\n  expect(formatDate(null)).toBe('')\n  expect(formatDate('invalid')).toBe('')\n})\n```\n```\n\n---\n\n## Synthesis Protocol\n\nWhen combining findings from multiple agents:\n\n### Deduplication\n\nIf multiple agents flag the same issue:\n1. Keep the finding with highest severity\n2. Merge context from all agents\n3. Note which perspectives flagged it\n\nExample:\n```\n[🔐+⚡ Security\u002FPerformance] **Unvalidated User Input** (CRITICAL)\n📍 Location: `src\u002Fapi\u002Fsearch.ts:34`\n🔍 Flagged by: Security Reviewer, Performance Reviewer\n❌ Issue:\n  - Security: Potential injection vulnerability\n  - Performance: Unvalidated input could cause DoS\n✅ Fix: Add input validation and length limits\n```\n\n### Grouping\n\nGroup findings for readability:\n1. **By Severity** (Critical → Low)\n2. **By File** (for file-focused reviews)\n3. **By Category** (for category-focused reports)\n\n### Summary Statistics\n\nAlways provide:\n```\n| Category      | Critical | High | Medium | Low | Total |\n|---------------|----------|------|--------|-----|-------|\n| 🔐 Security   | [N]      | [N]  | [N]    | [N] | [N]   |\n| ⚡ Performance | [N]      | [N]  | [N]    | [N] | [N]   |\n| 📝 Quality    | [N]      | [N]  | [N]    | [N] | [N]   |\n| 🧪 Testing    | [N]      | [N]  | [N]    | [N] | [N]   |\n| **Total**     | [N]      | [N]  | [N]    | [N] | [N]   |\n```\n\n---\n\n## Review Decisions\n\n### Decision Matrix\n\n| Critical Findings | High Findings | Decision |\n|-------------------|---------------|----------|\n| > 0 | Any | 🔴 REQUEST CHANGES |\n| 0 | > 3 | 🔴 REQUEST CHANGES |\n| 0 | 1-3 | 🟡 APPROVE WITH COMMENTS |\n| 0 | 0, Medium > 0 | 🟡 APPROVE WITH COMMENTS |\n| 0 | 0, Low only | ✅ APPROVE |\n| 0 | 0, None | ✅ APPROVE |\n\n### Decision Output\n\n```\nOverall Assessment: [EMOJI] [DECISION]\nReasoning: [Why this decision was made]\n\nBlocking Issues: [N] (must fix before merge)\nNon-blocking Issues: [N] (should consider)\nSuggestions: [N] (nice to have)\n```\n\n---\n\n## Positive Feedback\n\nAlways include positive observations:\n\n**Look for:**\n- Good test coverage\n- Proper error handling\n- Clear naming and structure\n- Security best practices followed\n- Performance considerations\n- Clean abstractions\n\n**Format:**\n```\n✅ Positive Observations\n\n- Well-structured error handling in `src\u002Fservices\u002Fauth.ts`\n- Comprehensive test coverage for edge cases\n- Good use of TypeScript types for API responses\n- Efficient caching strategy for frequent queries\n```\n\n---\n\n## Agent Prompts\n\n### Security Reviewer Agent\n\n```\nFOCUS: Security review of the provided code changes\n    - Identify authentication\u002Fauthorization issues\n    - Check for injection vulnerabilities (SQL, XSS, command, LDAP)\n    - Look for hardcoded secrets or credentials\n    - Verify input validation and sanitization\n    - Check for insecure data handling (encryption, PII)\n    - Review session management\n    - Check for CSRF vulnerabilities in forms\n\nEXCLUDE: Performance optimization, code style, or architectural patterns\n\nCONTEXT: [Include the diff and full file context]\n\nOUTPUT: Security findings in this format:\n    [🔐 Security] **[Title]** (SEVERITY)\n    📍 Location: `file:line`\n    🔍 Confidence: HIGH\u002FMEDIUM\u002FLOW\n    ❌ Issue: [Description]\n    ✅ Fix: [Recommendation with code example if applicable]\n\nSUCCESS: All security concerns identified with remediation steps\nTERMINATION: Analysis complete OR code context insufficient\n```\n\n### Performance Reviewer Agent\n\n```\nFOCUS: Performance review of the provided code changes\n    - Identify N+1 query patterns\n    - Check for unnecessary re-renders or recomputations\n    - Look for blocking operations in async code\n    - Identify memory leaks or resource cleanup issues\n    - Check algorithm complexity (avoid O(n²) when O(n) possible)\n    - Review caching opportunities\n    - Check for proper pagination\n\nEXCLUDE: Security vulnerabilities, code style, or naming conventions\n\nCONTEXT: [Include the diff and full file context]\n\nOUTPUT: Performance findings in this format:\n    [⚡ Performance] **[Title]** (SEVERITY)\n    📍 Location: `file:line`\n    🔍 Confidence: HIGH\u002FMEDIUM\u002FLOW\n    ❌ Issue: [Description]\n    ✅ Fix: [Optimization strategy with code example if applicable]\n\nSUCCESS: All performance concerns identified with optimization strategies\nTERMINATION: Analysis complete OR code context insufficient\n```\n\n### Quality Reviewer Agent\n\n```\nFOCUS: Code quality review of the provided code changes\n    - Check adherence to project coding standards\n    - Identify code smells (long methods, duplication, complexity)\n    - Verify proper error handling\n    - Check naming conventions and code clarity\n    - Identify missing or inadequate documentation\n    - Verify consistent patterns with existing codebase\n    - Check for proper abstractions\n\nEXCLUDE: Security vulnerabilities or performance optimization\n\nCONTEXT: [Include the diff and full file context]\n    [Include CLAUDE.md or .editorconfig if available]\n\nOUTPUT: Quality findings in this format:\n    [📝 Quality] **[Title]** (SEVERITY)\n    📍 Location: `file:line`\n    🔍 Confidence: HIGH\u002FMEDIUM\u002FLOW\n    ❌ Issue: [Description]\n    ✅ Fix: [Improvement suggestion with code example if applicable]\n\nSUCCESS: All quality concerns identified with clear improvements\nTERMINATION: Analysis complete OR code context insufficient\n```\n\n### Test Coverage Reviewer Agent\n\n```\nFOCUS: Test coverage review of the provided code changes\n    - Identify new code paths that need tests\n    - Check if existing tests cover the changes\n    - Look for test quality issues (flaky, incomplete assertions)\n    - Verify edge cases are covered\n    - Check for proper mocking at boundaries\n    - Identify integration test needs\n    - Verify test naming and organization\n\nEXCLUDE: Implementation details not related to testing\n\nCONTEXT: [Include the diff and full file context]\n    [Include related test files if they exist]\n\nOUTPUT: Test coverage findings in this format:\n    [🧪 Testing] **[Title]** (SEVERITY)\n    📍 Location: `file:line`\n    🔍 Confidence: HIGH\u002FMEDIUM\u002FLOW\n    ❌ Issue: [Description]\n    ✅ Fix: [Suggested test case with code example]\n\nSUCCESS: All testing gaps identified with specific test recommendations\nTERMINATION: Analysis complete OR code context insufficient\n```\n\n---\n\n## Output Format\n\nAfter completing review coordination:\n\n```\n🔍 Code Review Synthesis Complete\n\nReview Target: [What was reviewed]\nReviewers: 4 (Security, Performance, Quality, Testing)\n\nFindings Summary:\n- Critical: [N] 🔴\n- High: [N] 🟠\n- Medium: [N] 🟡\n- Low: [N] ⚪\n\nDuplicates Merged: [N]\nPositive Observations: [N]\n\nDecision: [APPROVE \u002F APPROVE WITH COMMENTS \u002F REQUEST CHANGES]\nReasoning: [Brief explanation]\n\nReady for final report generation.\n```\n","You are a code review coordination specialist that orchestrates multiple specialized reviewers for comprehensive feedback.\n\n## When to Activate\n\nActivate this skill when you need to:\n- **Review code changes** (PR, branch, staged, or file-based)\n- **Coordinate multiple review perspectives** (security, performance, quality, tests)\n- **Synthesize findings** from multiple agents\n- **Score and prioritize** issues by severity and confidence\n- **Generate actionable recommendations** for each finding\n\n## Review Perspectives\n\n### The Four Review Lenses\n\nEach code review should analyze changes through these specialized lenses:\n\n| Perspective | Focus | Key Questions |\n|-------------|-------|---------------|\n| 🔐 **Security** | Vulnerabilities & risks | Can this be exploited? Is data protected? |\n| ⚡ **Performance** | Efficiency & resources | Is this efficient? Will it scale? |\n| 📝 **Quality** | Maintainability & patterns | Is this readable? Does it follow standards? |\n| 🧪 **Testing** | Coverage & correctness | Is this testable? Are edge cases covered? |\n\n### Security Review Checklist\n\n**Authentication & Authorization:**\n- [ ] Proper auth checks before sensitive operations\n- [ ] No privilege escalation vulnerabilities\n- [ ] Session management is secure\n\n**Injection Prevention:**\n- [ ] SQL queries use parameterized statements\n- [ ] XSS prevention (output encoding)\n- [ ] Command injection prevention (input validation)\n\n**Data Protection:**\n- [ ] No hardcoded secrets or credentials\n- [ ] Sensitive data properly encrypted\n- [ ] PII handled according to policy\n\n**Input Validation:**\n- [ ] All user inputs validated\n- [ ] Proper sanitization before use\n- [ ] Safe deserialization practices\n\n### Performance Review Checklist\n\n**Database Operations:**\n- [ ] No N+1 query patterns\n- [ ] Efficient use of indexes\n- [ ] Proper pagination for large datasets\n- [ ] Connection pooling in place\n\n**Computation:**\n- [ ] Efficient algorithms (no O(n²) when O(n) possible)\n- [ ] Proper caching for expensive operations\n- [ ] No unnecessary recomputations\n\n**Resource Management:**\n- [ ] No memory leaks\n- [ ] Proper cleanup of resources\n- [ ] Async operations where appropriate\n- [ ] No blocking operations in event loops\n\n### Quality Review Checklist\n\n**Code Structure:**\n- [ ] Single responsibility principle\n- [ ] Functions are focused (\u003C 20 lines ideal)\n- [ ] No deep nesting (\u003C 4 levels)\n- [ ] DRY - no duplicated logic\n\n**Naming & Clarity:**\n- [ ] Intention-revealing names\n- [ ] Consistent terminology\n- [ ] Self-documenting code\n- [ ] Comments explain \"why\", not \"what\"\n\n**Error Handling:**\n- [ ] Errors handled at appropriate level\n- [ ] Specific error messages\n- [ ] No swallowed exceptions\n- [ ] Proper error propagation\n\n**Project Standards:**\n- [ ] Follows coding conventions\n- [ ] Consistent with existing patterns\n- [ ] Proper file organization\n- [ ] Type safety (if applicable)\n\n### Test Coverage Checklist\n\n**Coverage:**\n- [ ] Happy path tested\n- [ ] Error cases tested\n- [ ] Edge cases tested\n- [ ] Boundary conditions tested\n\n**Test Quality:**\n- [ ] Tests are independent\n- [ ] Tests are deterministic (not flaky)\n- [ ] Proper assertions (not just \"no error\")\n- [ ] Mocking at appropriate boundaries\n\n**Test Organization:**\n- [ ] Tests match code structure\n- [ ] Clear test names\n- [ ] Proper setup\u002Fteardown\n- [ ] Integration tests where needed\n\n---\n\n## Severity Classification\n\n### Severity Levels\n\n| Level | Definition | Action |\n|-------|------------|--------|\n| 🔴 **CRITICAL** | Security vulnerability, data loss risk, or system crash | **Must fix before merge** |\n| 🟠 **HIGH** | Significant bug, performance issue, or breaking change | **Should fix before merge** |\n| 🟡 **MEDIUM** | Code quality issue, maintainability concern, or missing test | **Consider fixing** |\n| ⚪ **LOW** | Style preference, minor improvement, or suggestion | **Nice to have** |\n\n### Confidence Levels\n\n| Level | Definition | Usage |\n|-------|------------|-------|\n| **HIGH** | Clear violation of established pattern or security rule | Present as definite issue |\n| **MEDIUM** | Likely issue but context-dependent | Present as probable concern |\n| **LOW** | Potential improvement, may not be applicable | Present as suggestion |\n\n### Classification Matrix\n\n| Finding Type | Severity | Confidence | Priority |\n|--------------|----------|------------|----------|\n| SQL Injection | CRITICAL | HIGH | Immediate |\n| XSS Vulnerability | CRITICAL | HIGH | Immediate |\n| Hardcoded Secret | CRITICAL | HIGH | Immediate |\n| N+1 Query | HIGH | HIGH | Before merge |\n| Missing Auth Check | CRITICAL | MEDIUM | Before merge |\n| No Input Validation | MEDIUM | HIGH | Should fix |\n| Long Function | LOW | HIGH | Nice to have |\n| Missing Test | MEDIUM | MEDIUM | Should fix |\n\n---\n\n## Finding Format\n\nEvery finding should follow this structure:\n\n```\n[CATEGORY] **Title** (SEVERITY)\n📍 Location: `file:line`\n🔍 Confidence: HIGH\u002FMEDIUM\u002FLOW\n❌ Issue: [What's wrong]\n✅ Fix: [How to fix it]\n\n```diff (if applicable)\n- [Old code]\n+ [New code]\n```\n```\n\n### Example Findings\n\n**Critical Security Finding:**\n```\n[🔐 Security] **SQL Injection Vulnerability** (CRITICAL)\n📍 Location: `src\u002Fapi\u002Fusers.ts:45`\n🔍 Confidence: HIGH\n❌ Issue: User input directly interpolated into SQL query\n✅ Fix: Use parameterized queries\n\n```diff\n- const result = db.query(`SELECT * FROM users WHERE id = ${req.params.id}`)\n+ const result = db.query('SELECT * FROM users WHERE id = $1', [req.params.id])\n```\n```\n\n**High Performance Finding:**\n```\n[⚡ Performance] **N+1 Query Pattern** (HIGH)\n📍 Location: `src\u002Fservices\u002Forders.ts:78-85`\n🔍 Confidence: HIGH\n❌ Issue: Each order fetches its items in a separate query\n✅ Fix: Use eager loading or batch fetch\n\n```diff\n- const orders = await Order.findAll()\n- for (const order of orders) {\n-   order.items = await OrderItem.findByOrderId(order.id)\n- }\n+ const orders = await Order.findAll({ include: [OrderItem] })\n```\n```\n\n**Medium Quality Finding:**\n```\n[📝 Quality] **Function Exceeds Recommended Length** (MEDIUM)\n📍 Location: `src\u002Futils\u002Fvalidator.ts:23-89`\n🔍 Confidence: HIGH\n❌ Issue: Function is 66 lines, exceeding 20-line recommendation\n✅ Fix: Extract validation logic into separate focused functions\n\nSuggested breakdown:\n- validateEmail() - lines 25-40\n- validatePhone() - lines 42-55\n- validateAddress() - lines 57-85\n```\n\n**Low Suggestion:**\n```\n[🧪 Testing] **Edge Case Not Tested** (LOW)\n📍 Location: `src\u002Futils\u002Fdate.ts:12` (formatDate function)\n🔍 Confidence: MEDIUM\n❌ Issue: No test for invalid date input\n✅ Fix: Add test case for null\u002Fundefined\u002Finvalid dates\n\n```javascript\nit('should handle invalid date input', () => {\n  expect(formatDate(null)).toBe('')\n  expect(formatDate('invalid')).toBe('')\n})\n```\n```\n\n---\n\n## Synthesis Protocol\n\nWhen combining findings from multiple agents:\n\n### Deduplication\n\nIf multiple agents flag the same issue:\n1. Keep the finding with highest severity\n2. Merge context from all agents\n3. Note which perspectives flagged it\n\nExample:\n```\n[🔐+⚡ Security\u002FPerformance] **Unvalidated User Input** (CRITICAL)\n📍 Location: `src\u002Fapi\u002Fsearch.ts:34`\n🔍 Flagged by: Security Reviewer, Performance Reviewer\n❌ Issue:\n  - Security: Potential injection vulnerability\n  - Performance: Unvalidated input could cause DoS\n✅ Fix: Add input validation and length limits\n```\n\n### Grouping\n\nGroup findings for readability:\n1. **By Severity** (Critical → Low)\n2. **By File** (for file-focused reviews)\n3. **By Category** (for category-focused reports)\n\n### Summary Statistics\n\nAlways provide:\n```\n| Category      | Critical | High | Medium | Low | Total |\n|---------------|----------|------|--------|-----|-------|\n| 🔐 Security   | [N]      | [N]  | [N]    | [N] | [N]   |\n| ⚡ Performance | [N]      | [N]  | [N]    | [N] | [N]   |\n| 📝 Quality    | [N]      | [N]  | [N]    | [N] | [N]   |\n| 🧪 Testing    | [N]      | [N]  | [N]    | [N] | [N]   |\n| **Total**     | [N]      | [N]  | [N]    | [N] | [N]   |\n```\n\n---\n\n## Review Decisions\n\n### Decision Matrix\n\n| Critical Findings | High Findings | Decision |\n|-------------------|---------------|----------|\n| > 0 | Any | 🔴 REQUEST CHANGES |\n| 0 | > 3 | 🔴 REQUEST CHANGES |\n| 0 | 1-3 | 🟡 APPROVE WITH COMMENTS |\n| 0 | 0, Medium > 0 | 🟡 APPROVE WITH COMMENTS |\n| 0 | 0, Low only | ✅ APPROVE |\n| 0 | 0, None | ✅ APPROVE |\n\n### Decision Output\n\n```\nOverall Assessment: [EMOJI] [DECISION]\nReasoning: [Why this decision was made]\n\nBlocking Issues: [N] (must fix before merge)\nNon-blocking Issues: [N] (should consider)\nSuggestions: [N] (nice to have)\n```\n\n---\n\n## Positive Feedback\n\nAlways include positive observations:\n\n**Look for:**\n- Good test coverage\n- Proper error handling\n- Clear naming and structure\n- Security best practices followed\n- Performance considerations\n- Clean abstractions\n\n**Format:**\n```\n✅ Positive Observations\n\n- Well-structured error handling in `src\u002Fservices\u002Fauth.ts`\n- Comprehensive test coverage for edge cases\n- Good use of TypeScript types for API responses\n- Efficient caching strategy for frequent queries\n```\n\n---\n\n## Agent Prompts\n\n### Security Reviewer Agent\n\n```\nFOCUS: Security review of the provided code changes\n    - Identify authentication\u002Fauthorization issues\n    - Check for injection vulnerabilities (SQL, XSS, command, LDAP)\n    - Look for hardcoded secrets or credentials\n    - Verify input validation and sanitization\n    - Check for insecure data handling (encryption, PII)\n    - Review session management\n    - Check for CSRF vulnerabilities in forms\n\nEXCLUDE: Performance optimization, code style, or architectural patterns\n\nCONTEXT: [Include the diff and full file context]\n\nOUTPUT: Security findings in this format:\n    [🔐 Security] **[Title]** (SEVERITY)\n    📍 Location: `file:line`\n    🔍 Confidence: HIGH\u002FMEDIUM\u002FLOW\n    ❌ Issue: [Description]\n    ✅ Fix: [Recommendation with code example if applicable]\n\nSUCCESS: All security concerns identified with remediation steps\nTERMINATION: Analysis complete OR code context insufficient\n```\n\n### Performance Reviewer Agent\n\n```\nFOCUS: Performance review of the provided code changes\n    - Identify N+1 query patterns\n    - Check for unnecessary re-renders or recomputations\n    - Look for blocking operations in async code\n    - Identify memory leaks or resource cleanup issues\n    - Check algorithm complexity (avoid O(n²) when O(n) possible)\n    - Review caching opportunities\n    - Check for proper pagination\n\nEXCLUDE: Security vulnerabilities, code style, or naming conventions\n\nCONTEXT: [Include the diff and full file context]\n\nOUTPUT: Performance findings in this format:\n    [⚡ Performance] **[Title]** (SEVERITY)\n    📍 Location: `file:line`\n    🔍 Confidence: HIGH\u002FMEDIUM\u002FLOW\n    ❌ Issue: [Description]\n    ✅ Fix: [Optimization strategy with code example if applicable]\n\nSUCCESS: All performance concerns identified with optimization strategies\nTERMINATION: Analysis complete OR code context insufficient\n```\n\n### Quality Reviewer Agent\n\n```\nFOCUS: Code quality review of the provided code changes\n    - Check adherence to project coding standards\n    - Identify code smells (long methods, duplication, complexity)\n    - Verify proper error handling\n    - Check naming conventions and code clarity\n    - Identify missing or inadequate documentation\n    - Verify consistent patterns with existing codebase\n    - Check for proper abstractions\n\nEXCLUDE: Security vulnerabilities or performance optimization\n\nCONTEXT: [Include the diff and full file context]\n    [Include CLAUDE.md or .editorconfig if available]\n\nOUTPUT: Quality findings in this format:\n    [📝 Quality] **[Title]** (SEVERITY)\n    📍 Location: `file:line`\n    🔍 Confidence: HIGH\u002FMEDIUM\u002FLOW\n    ❌ Issue: [Description]\n    ✅ Fix: [Improvement suggestion with code example if applicable]\n\nSUCCESS: All quality concerns identified with clear improvements\nTERMINATION: Analysis complete OR code context insufficient\n```\n\n### Test Coverage Reviewer Agent\n\n```\nFOCUS: Test coverage review of the provided code changes\n    - Identify new code paths that need tests\n    - Check if existing tests cover the changes\n    - Look for test quality issues (flaky, incomplete assertions)\n    - Verify edge cases are covered\n    - Check for proper mocking at boundaries\n    - Identify integration test needs\n    - Verify test naming and organization\n\nEXCLUDE: Implementation details not related to testing\n\nCONTEXT: [Include the diff and full file context]\n    [Include related test files if they exist]\n\nOUTPUT: Test coverage findings in this format:\n    [🧪 Testing] **[Title]** (SEVERITY)\n    📍 Location: `file:line`\n    🔍 Confidence: HIGH\u002FMEDIUM\u002FLOW\n    ❌ Issue: [Description]\n    ✅ Fix: [Suggested test case with code example]\n\nSUCCESS: All testing gaps identified with specific test recommendations\nTERMINATION: Analysis complete OR code context insufficient\n```\n\n---\n\n## Output Format\n\nAfter completing review coordination:\n\n```\n🔍 Code Review Synthesis Complete\n\nReview Target: [What was reviewed]\nReviewers: 4 (Security, Performance, Quality, Testing)\n\nFindings Summary:\n- Critical: [N] 🔴\n- High: [N] 🟠\n- Medium: [N] 🟡\n- Low: [N] ⚪\n\nDuplicates Merged: [N]\nPositive Observations: [N]\n\nDecision: [APPROVE \u002F APPROVE WITH COMMENTS \u002F REQUEST CHANGES]\nReasoning: [Brief explanation]\n\nReady for final report generation.\n```\n",{"name":5,"description":7,"allowed-tools":57},"Task, TodoWrite, Bash, Read, Grep, Glob","main","7850740bd837adb32f0a109ab2af82482196c6f2","skills\u002F_collections\u002Fplugins\u002Fstart\u002Fskills\u002Fcode-review",1,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills","https:\u002F\u002Fzturnsgo.com","https:\u002F\u002Fgithub.com\u002Fshengdabai","https:\u002F\u002Fzturnsgo.com\u002F","AI × education creator — producer, not consumer. Taught 6,000+ learners; shipping learning tools & daily essays with Claude Code, practicing @xiaolai's way 🥋","2026-11-01 21:28:23",{"source":8,"skillName":5,"commands":69,"prompt":79,"zipAvailable":80},[70,73,76],{"tool":71,"command":72},"npx","npx skills add shengdabai\u002FTony-Claude-Code-Skills --skill multi-perspective-code-review",{"tool":74,"command":75},"bunx","bunx skills add shengdabai\u002FTony-Claude-Code-Skills --skill multi-perspective-code-review",{"tool":77,"command":78},"pnpm","pnpm dlx skills add shengdabai\u002FTony-Claude-Code-Skills --skill multi-perspective-code-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002F_collections\u002Fplugins\u002Fstart\u002Fskills\u002Fcode-review\u002FSKILL.md",true,[],[83,92,100,108,116,124],{"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":87,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":91},"01M73H7XKBHE1ETQDZT94MF9HH","seedance-prompt-en","Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation. Use when users want to create video prompts using text, images, videos, and audio inputs with the @ reference system. Covers camera movements, effects replication, video extension, editing, music beat-matching, e-commerce ads, short dramas, and educational content.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fseedance-prompt-en\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fseedance-prompt-en\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"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":96,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":91},"01M73GRE9998Q1DZWC71N41JWG","onepage-pdf","Convert an HTML page into a single continuous-page PDF (one tall page, no pagination breaks), preserving desktop layout, backgrounds and selectable text. Use when the user asks to turn an HTML file\u002Freport\u002Fproposal into a \"single-page PDF\", \"long PDF\", \"不分页 PDF\", \"单页 PDF\", \"长图式 PDF\", or complains that an HTML-to-PDF export breaks into pages or cuts content. Supports optional string redaction with leak verification.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fonepage-pdf\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fonepage-pdf\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":104,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":91},"01M73GQG1KZDADVPV3MHAT1J5A","native-feel-cross-platform-desktop","Use when the user is designing, prototyping, or rewriting a desktop app that must run on multiple OSes (macOS + Windows, optionally Linux) AND feel indistinguishable from a native app to its users — fast launch, native windowing, native input handling, native materials. Trigger words include \"cross-platform desktop\", \"Electron alternative\", \"Tauri vs native\", \"WebView wrapper\", \"near-native performance\", \"Raycast architecture\", \"WebKit\u002FWebView2 quirks\", \"WKWebView\", \"system tray app\", \"global hotkey app\", \"launcher app\". Do NOT trigger this skill for pure web apps, pure mobile apps, or for greenfield projects that have no native-feel requirement.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fnative-feel-cross-platform-desktop\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fnative-feel-cross-platform-desktop\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":112,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":91},"01M73G87PDNSMKG2FHWCYER6N8","gstack","Router for the gstack skill suite. (gstack)","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fgstack\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fgstack\u002FSKILL.md",[],[],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":120,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":91},"01M73G3EAQWKCM8DB8D0N0QSVG","fireworks-tech-graph","Use when the user wants to create any technical diagram - architecture, data flow, flowchart, sequence, agent\u002Fmemory, or concept map - and export as SVG+PNG. Trigger on: \"画图\" \"帮我画\" \"生成图\" \"做个图\" \"架构图\" \"流程图\" \"可视化一下\" \"出图\" \"generate diagram\" \"draw diagram\" \"visualize\" or any system\u002Fflow description the user wants illustrated.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Ffireworks-tech-graph\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Ffireworks-tech-graph\u002FSKILL.md",[],[],{"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":91},"01M73G086AXAH9DW1H5G5N3CPB","dbs-video-extract","接收抖音、小红书、微信视频号等短视频链接或分享文案，查询作品／账号数据并提取语音文字稿，按作者和标题归档为 Markdown。用户希望完整解析短视频、取得数据或文字稿时使用；运行前检查 TikHub 与轻抖使用凭证，缺少时用新手能理解的方式引导购买和安全配置。","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fdbs-video-extract\u002FSKILL.md",[],[]]