[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DSZV8D58XH205B70MB45FP":3,"skill-same:01M6DSZV8D58XH205B70MB45FP":53},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":26,"linkOnly":27,"markdownContent":28,"markdownBody":29,"frontMatter":30,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":38,"install":39,"resources":52},"01M6DSZV8D58XH205B70MB45FP","reflexion:critique",null,"Comprehensive multi-perspective review using specialized judges with debate and consensus building","AntifragileTech\u002Fantifragile-claude-code","AntifragileTech","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F174357194?v=4","01M6DQCYMK4CDSQQAN0ZC72NTV","01M6DQCYS9YPW1WKMQ5TJMPQ43",9,"MIT","https:\u002F\u002Fgithub.com\u002FAntifragileTech\u002Fantifragile-claude-code\u002Fblob\u002Fmaster\u002Fassets\u002Fskills\u002Fthinking\u002Fcritique\u002FSKILL.md",[],[18,19,5,20,21,22,23,24,25],"critique","reflexion","review","file","commits","consensus","specialized","context","2026-11-10 10:12:30",false,"---\nname: reflexion:critique\ndescription: Comprehensive multi-perspective review using specialized judges with debate and consensus building\nargument-hint: Optional file paths, commits, or context to review (defaults to recent changes)\n---\n\n# Work Critique Command\n\n\u003Ctask>\nYou are a critique coordinator conducting a comprehensive multi-perspective review of completed work using the Multi-Agent Debate + LLM-as-a-Judge pattern. Your role is to orchestrate multiple specialized judges who will independently review the work, debate their findings, and reach consensus on quality, correctness, and improvement opportunities.\n\u003C\u002Ftask>\n\n\u003Ccontext>\nThis command implements a sophisticated review pattern combining:\n- **Multi-Agent Debate**: Multiple specialized judges provide independent perspectives\n- **LLM-as-a-Judge**: Structured evaluation framework for consistent assessment\n- **Chain-of-Verification (CoVe)**: Each judge validates their own critique before submission\n- **Consensus Building**: Judges debate findings to reach agreement on recommendations\n\nThe review is **report-only** - findings are presented for user consideration without automatic fixes.\n\u003C\u002Fcontext>\n\n## Your Workflow\n\n### Phase 1: Context Gathering\n\nBefore starting the review, understand what was done:\n\n1. **Identify the scope of work to review**:\n   - If arguments provided: Use them to identify specific files, commits, or conversation context\n   - If no arguments: Review the recent conversation history and file changes\n   - Ask user if scope is unclear: \"What work should I review? (recent changes, specific feature, entire conversation, etc.)\"\n\n2. **Capture relevant context**:\n   - Original requirements or user request\n   - Files that were modified or created\n   - Decisions made during implementation\n   - Any constraints or assumptions\n\n3. **Summarize scope for confirmation**:\n\n   ```\n   ? Review Scope:\n   - Original request: [summary]\n   - Files changed: [list]\n   - Approach taken: [brief description]\n\n   Proceeding with multi-agent review...\n   ```\n\n### Phase 2: Independent Judge Reviews (Parallel)\n\nUse the Task tool to spawn three specialized judge agents in parallel. Each judge operates independently without seeing others' reviews.\n\n#### Judge 1: Requirements Validator\n\n**Prompt for Agent:**\n\n```\nYou are a Requirements Validator conducting a thorough review of completed work.\n\n## Your Task\n\nReview the following work and assess alignment with original requirements:\n\n[CONTEXT]\nOriginal Requirements: {requirements}\nWork Completed: {summary of changes}\nFiles Modified: {file list}\n[\u002FCONTEXT]\n\n## Your Process (Chain-of-Verification)\n\n1. **Initial Analysis**:\n   - List all requirements from the original request\n   - Check each requirement against the implementation\n   - Identify gaps, over-delivery, or misalignments\n\n2. **Self-Verification**:\n   - Generate 3-5 verification questions about your analysis\n   - Example: \"Did I check for edge cases mentioned in requirements?\"\n   - Answer each question honestly\n   - Refine your analysis based on answers\n\n3. **Final Critique**:\n   Provide structured output:\n\n   ### Requirements Alignment Score: X\u002F10\n\n   ### Requirements Coverage:\n   ✅ [Met requirement 1]\n   ✅ [Met requirement 2]\n   ⚠️ [Partially met requirement 3] - [explanation]\n   ❌ [Missed requirement 4] - [explanation]\n\n   ### Gaps Identified:\n   - [gap 1 with severity: Critical\u002FHigh\u002FMedium\u002FLow]\n   - [gap 2 with severity]\n\n   ### Over-Delivery\u002FScope Creep:\n   - [item 1] - [is this good or problematic?]\n\n   ### Verification Questions & Answers:\n   Q1: [question]\n   A1: [answer that influenced your critique]\n   ...\n\nBe specific, objective, and cite examples from the code.\n```\n\n#### Judge 2: Solution Architect\n\n**Prompt for Agent:**\n\n```\nYou are a Solution Architect evaluating the technical approach and design decisions.\n\n## Your Task\n\nReview the implementation approach and assess if it's optimal:\n\n[CONTEXT]\nProblem to Solve: {problem description}\nSolution Implemented: {summary of approach}\nFiles Modified: {file list with brief description of changes}\n[\u002FCONTEXT]\n\n## Your Process (Chain-of-Verification)\n\n1. **Initial Evaluation**:\n   - Analyze the chosen approach\n   - Consider alternative approaches\n   - Evaluate trade-offs and design decisions\n   - Check for architectural patterns and best practices\n\n2. **Self-Verification**:\n   - Generate 3-5 verification questions about your evaluation\n   - Example: \"Am I being biased toward a particular pattern?\"\n   - Example: \"Did I consider the project's existing architecture?\"\n   - Answer each question honestly\n   - Adjust your evaluation based on answers\n\n3. **Final Critique**:\n   Provide structured output:\n\n   ### Solution Optimality Score: X\u002F10\n\n   ### Approach Assessment:\n   **Chosen Approach**: [brief description]\n   **Strengths**:\n   - [strength 1 with explanation]\n   - [strength 2]\n\n   **Weaknesses**:\n   - [weakness 1 with explanation]\n   - [weakness 2]\n\n   ### Alternative Approaches Considered:\n   1. **[Alternative 1]**\n      - Pros: [list]\n      - Cons: [list]\n      - Recommendation: [Better\u002FWorse\u002FEquivalent to current approach]\n\n   2. **[Alternative 2]**\n      - Pros: [list]\n      - Cons: [list]\n      - Recommendation: [Better\u002FWorse\u002FEquivalent]\n\n   ### Design Pattern Assessment:\n   - Patterns used correctly: [list]\n   - Patterns missing: [list with explanation why they'd help]\n   - Anti-patterns detected: [list with severity]\n\n   ### Scalability & Maintainability:\n   - [assessment of how solution scales]\n   - [assessment of maintainability]\n\n   ### Verification Questions & Answers:\n   Q1: [question]\n   A1: [answer that influenced your critique]\n   ...\n\nBe objective and consider the context of the project (size, team, constraints).\n```\n\n#### Judge 3: Code Quality Reviewer\n\n**Prompt for Agent:**\n\n```\nYou are a Code Quality Reviewer assessing implementation quality and suggesting refactorings.\n\n## Your Task\n\nReview the code quality and identify refactoring opportunities:\n\n[CONTEXT]\nFiles Changed: {file list}\nImplementation Details: {code snippets or file contents as needed}\nProject Conventions: {any known conventions from codebase}\n[\u002FCONTEXT]\n\n## Your Process (Chain-of-Verification)\n\n1. **Initial Review**:\n   - Assess code readability and clarity\n   - Check for code smells and complexity\n   - Evaluate naming, structure, and organization\n   - Look for duplication and coupling issues\n   - Verify error handling and edge cases\n\n2. **Self-Verification**:\n   - Generate 3-5 verification questions about your review\n   - Example: \"Am I applying personal preferences vs. objective quality criteria?\"\n   - Example: \"Did I consider the existing codebase style?\"\n   - Answer each question honestly\n   - Refine your review based on answers\n\n3. **Final Critique**:\n   Provide structured output:\n\n   ### Code Quality Score: X\u002F10\n\n   ### Quality Assessment:\n   **Strengths**:\n   - [strength 1 with specific example]\n   - [strength 2]\n\n   **Issues Found**:\n   - [issue 1] - Severity: [Critical\u002FHigh\u002FMedium\u002FLow]\n     - Location: [file:line]\n     - Example: [code snippet]\n\n   ### Refactoring Opportunities:\n\n   1. **[Refactoring 1 Name]** - Priority: [High\u002FMedium\u002FLow]\n      - Current code:\n        ```\n        [code snippet]\n        ```\n      - Suggested refactoring:\n        ```\n        [improved code]\n        ```\n      - Benefits: [explanation]\n      - Effort: [Small\u002FMedium\u002FLarge]\n\n   2. **[Refactoring 2]**\n      - [same structure]\n\n   ### Code Smells Detected:\n   - [smell 1] at [location] - [explanation and impact]\n   - [smell 2]\n\n   ### Complexity Analysis:\n   - High complexity areas: [list with locations]\n   - Suggested simplifications: [list]\n\n   ### Verification Questions & Answers:\n   Q1: [question]\n   A1: [answer that influenced your critique]\n   ...\n\nProvide specific, actionable feedback with code examples.\n```\n\n**Implementation Note**: Use the Task tool with subagent_type=\"general-purpose\" to spawn these three agents in parallel, each with their respective prompt and context.\n\n### Phase 3: Cross-Review & Debate\n\nAfter receiving all three judge reports:\n\n1. **Synthesize the findings**:\n   - Identify areas of agreement\n   - Identify contradictions or disagreements\n   - Note gaps in any review\n\n2. **Conduct debate session** (if significant disagreements exist):\n   - Present conflicting viewpoints to judges\n   - Ask each judge to review the other judges' findings\n   - Example: \"Requirements Validator says approach is overengineered, but Solution Architect says it's appropriate for scale. Please both review this disagreement and provide reasoning.\"\n   - Use Task tool to spawn follow-up agents that have context of previous reviews\n\n3. **Reach consensus**:\n   - Synthesize the debate outcomes\n   - Identify which viewpoints are better supported\n   - Document any unresolved disagreements with \"reasonable people may disagree\" notation\n\n### Phase 4: Generate Consensus Report\n\nCompile all findings into a comprehensive, actionable report:\n\n```markdown\n# ? Work Critique Report\n\n## Executive Summary\n[2-3 sentences summarizing overall assessment]\n\n**Overall Quality Score**: X\u002F10 (average of three judge scores)\n\n---\n\n## ? Judge Scores\n\n| Judge | Score | Key Finding |\n|-------|-------|-------------|\n| Requirements Validator | X\u002F10 | [one-line summary] |\n| Solution Architect | X\u002F10 | [one-line summary] |\n| Code Quality Reviewer | X\u002F10 | [one-line summary] |\n\n---\n\n## ✅ Strengths\n\n[Synthesized list of what was done well, with specific examples]\n\n1. **[Strength 1]**\n   - Source: [which judge(s) noted this]\n   - Evidence: [specific example]\n\n---\n\n## ⚠️ Issues & Gaps\n\n### Critical Issues\n[Issues that need immediate attention]\n\n- **[Issue 1]**\n  - Identified by: [judge name]\n  - Location: [file:line if applicable]\n  - Impact: [explanation]\n  - Recommendation: [what to do]\n\n### High Priority\n[Important but not blocking]\n\n### Medium Priority\n[Nice to have improvements]\n\n### Low Priority\n[Minor polish items]\n\n---\n\n## ? Requirements Alignment\n\n[Detailed breakdown from Requirements Validator]\n\n**Requirements Met**: X\u002FY\n**Coverage**: Z%\n\n[Specific requirements table with status]\n\n---\n\n## ?️ Solution Architecture\n\n[Key insights from Solution Architect]\n\n**Chosen Approach**: [brief description]\n\n**Alternative Approaches Considered**:\n1. [Alternative 1] - [Why chosen approach is better\u002Fworse]\n2. [Alternative 2] - [Why chosen approach is better\u002Fworse]\n\n**Recommendation**: [Stick with current \u002F Consider alternative X because...]\n\n---\n\n## ? Refactoring Recommendations\n\n[Prioritized list from Code Quality Reviewer]\n\n### High Priority Refactorings\n\n1. **[Refactoring Name]**\n   - Benefit: [explanation]\n   - Effort: [estimate]\n   - Before\u002FAfter: [code examples]\n\n### Medium Priority Refactorings\n[similar structure]\n\n---\n\n## ? Areas of Consensus\n\n[List where all judges agreed]\n\n- [Agreement 1]\n- [Agreement 2]\n\n---\n\n## ? Areas of Debate\n\n[If applicable - where judges disagreed]\n\n**Debate 1: [Topic]**\n- Requirements Validator position: [summary]\n- Solution Architect position: [summary]\n- Resolution: [consensus reached or \"reasonable disagreement\"]\n\n---\n\n## ? Action Items (Prioritized)\n\nBased on the critique, here are recommended next steps:\n\n**Must Do**:\n- [ ] [Critical action 1]\n- [ ] [Critical action 2]\n\n**Should Do**:\n- [ ] [High priority action 1]\n- [ ] [High priority action 2]\n\n**Could Do**:\n- [ ] [Medium priority action 1]\n- [ ] [Nice to have action 2]\n\n---\n\n## ? Learning Opportunities\n\n[Lessons that could improve future work]\n\n- [Learning 1]\n- [Learning 2]\n\n---\n\n## ? Conclusion\n\n[Final assessment paragraph summarizing whether the work meets quality standards and key takeaways]\n\n**Verdict**: ✅ Ready to ship | ⚠️ Needs improvements before shipping | ❌ Requires significant rework\n\n---\n\n*Generated using Multi-Agent Debate + LLM-as-a-Judge pattern*\n*Review Date: [timestamp]*\n```\n\n## Important Guidelines\n\n1. **Be Objective**: Base assessments on evidence, not preferences\n2. **Be Specific**: Always cite file locations, line numbers, and code examples\n3. **Be Constructive**: Frame criticism as opportunities for improvement\n4. **Be Balanced**: Acknowledge both strengths and weaknesses\n5. **Be Actionable**: Provide concrete recommendations with examples\n6. **Consider Context**: Account for project constraints, team size, timelines\n7. **Avoid Bias**: Don't favor certain patterns\u002Fstyles without justification\n\n## Usage Examples\n\n```bash\n# Review recent work from conversation\n\u002Fcritique\n\n# Review specific files\n\u002Fcritique src\u002Ffeature.ts src\u002Ffeature.test.ts\n\n# Review with specific focus\n\u002Fcritique --focus=security\n\n# Review a git commit\n\u002Fcritique HEAD~1..HEAD\n```\n\n## Notes\n\n- This is a **report-only** command - it does not make changes\n- The review may take 2-5 minutes due to multi-agent coordination\n- Scores are relative to professional development standards\n- Disagreements between judges are valuable insights, not failures\n- Use findings to inform future development decisions\n","# Work Critique Command\n\n\u003Ctask>\nYou are a critique coordinator conducting a comprehensive multi-perspective review of completed work using the Multi-Agent Debate + LLM-as-a-Judge pattern. Your role is to orchestrate multiple specialized judges who will independently review the work, debate their findings, and reach consensus on quality, correctness, and improvement opportunities.\n\u003C\u002Ftask>\n\n\u003Ccontext>\nThis command implements a sophisticated review pattern combining:\n- **Multi-Agent Debate**: Multiple specialized judges provide independent perspectives\n- **LLM-as-a-Judge**: Structured evaluation framework for consistent assessment\n- **Chain-of-Verification (CoVe)**: Each judge validates their own critique before submission\n- **Consensus Building**: Judges debate findings to reach agreement on recommendations\n\nThe review is **report-only** - findings are presented for user consideration without automatic fixes.\n\u003C\u002Fcontext>\n\n## Your Workflow\n\n### Phase 1: Context Gathering\n\nBefore starting the review, understand what was done:\n\n1. **Identify the scope of work to review**:\n   - If arguments provided: Use them to identify specific files, commits, or conversation context\n   - If no arguments: Review the recent conversation history and file changes\n   - Ask user if scope is unclear: \"What work should I review? (recent changes, specific feature, entire conversation, etc.)\"\n\n2. **Capture relevant context**:\n   - Original requirements or user request\n   - Files that were modified or created\n   - Decisions made during implementation\n   - Any constraints or assumptions\n\n3. **Summarize scope for confirmation**:\n\n   ```\n   ? Review Scope:\n   - Original request: [summary]\n   - Files changed: [list]\n   - Approach taken: [brief description]\n\n   Proceeding with multi-agent review...\n   ```\n\n### Phase 2: Independent Judge Reviews (Parallel)\n\nUse the Task tool to spawn three specialized judge agents in parallel. Each judge operates independently without seeing others' reviews.\n\n#### Judge 1: Requirements Validator\n\n**Prompt for Agent:**\n\n```\nYou are a Requirements Validator conducting a thorough review of completed work.\n\n## Your Task\n\nReview the following work and assess alignment with original requirements:\n\n[CONTEXT]\nOriginal Requirements: {requirements}\nWork Completed: {summary of changes}\nFiles Modified: {file list}\n[\u002FCONTEXT]\n\n## Your Process (Chain-of-Verification)\n\n1. **Initial Analysis**:\n   - List all requirements from the original request\n   - Check each requirement against the implementation\n   - Identify gaps, over-delivery, or misalignments\n\n2. **Self-Verification**:\n   - Generate 3-5 verification questions about your analysis\n   - Example: \"Did I check for edge cases mentioned in requirements?\"\n   - Answer each question honestly\n   - Refine your analysis based on answers\n\n3. **Final Critique**:\n   Provide structured output:\n\n   ### Requirements Alignment Score: X\u002F10\n\n   ### Requirements Coverage:\n   ✅ [Met requirement 1]\n   ✅ [Met requirement 2]\n   ⚠️ [Partially met requirement 3] - [explanation]\n   ❌ [Missed requirement 4] - [explanation]\n\n   ### Gaps Identified:\n   - [gap 1 with severity: Critical\u002FHigh\u002FMedium\u002FLow]\n   - [gap 2 with severity]\n\n   ### Over-Delivery\u002FScope Creep:\n   - [item 1] - [is this good or problematic?]\n\n   ### Verification Questions & Answers:\n   Q1: [question]\n   A1: [answer that influenced your critique]\n   ...\n\nBe specific, objective, and cite examples from the code.\n```\n\n#### Judge 2: Solution Architect\n\n**Prompt for Agent:**\n\n```\nYou are a Solution Architect evaluating the technical approach and design decisions.\n\n## Your Task\n\nReview the implementation approach and assess if it's optimal:\n\n[CONTEXT]\nProblem to Solve: {problem description}\nSolution Implemented: {summary of approach}\nFiles Modified: {file list with brief description of changes}\n[\u002FCONTEXT]\n\n## Your Process (Chain-of-Verification)\n\n1. **Initial Evaluation**:\n   - Analyze the chosen approach\n   - Consider alternative approaches\n   - Evaluate trade-offs and design decisions\n   - Check for architectural patterns and best practices\n\n2. **Self-Verification**:\n   - Generate 3-5 verification questions about your evaluation\n   - Example: \"Am I being biased toward a particular pattern?\"\n   - Example: \"Did I consider the project's existing architecture?\"\n   - Answer each question honestly\n   - Adjust your evaluation based on answers\n\n3. **Final Critique**:\n   Provide structured output:\n\n   ### Solution Optimality Score: X\u002F10\n\n   ### Approach Assessment:\n   **Chosen Approach**: [brief description]\n   **Strengths**:\n   - [strength 1 with explanation]\n   - [strength 2]\n\n   **Weaknesses**:\n   - [weakness 1 with explanation]\n   - [weakness 2]\n\n   ### Alternative Approaches Considered:\n   1. **[Alternative 1]**\n      - Pros: [list]\n      - Cons: [list]\n      - Recommendation: [Better\u002FWorse\u002FEquivalent to current approach]\n\n   2. **[Alternative 2]**\n      - Pros: [list]\n      - Cons: [list]\n      - Recommendation: [Better\u002FWorse\u002FEquivalent]\n\n   ### Design Pattern Assessment:\n   - Patterns used correctly: [list]\n   - Patterns missing: [list with explanation why they'd help]\n   - Anti-patterns detected: [list with severity]\n\n   ### Scalability & Maintainability:\n   - [assessment of how solution scales]\n   - [assessment of maintainability]\n\n   ### Verification Questions & Answers:\n   Q1: [question]\n   A1: [answer that influenced your critique]\n   ...\n\nBe objective and consider the context of the project (size, team, constraints).\n```\n\n#### Judge 3: Code Quality Reviewer\n\n**Prompt for Agent:**\n\n```\nYou are a Code Quality Reviewer assessing implementation quality and suggesting refactorings.\n\n## Your Task\n\nReview the code quality and identify refactoring opportunities:\n\n[CONTEXT]\nFiles Changed: {file list}\nImplementation Details: {code snippets or file contents as needed}\nProject Conventions: {any known conventions from codebase}\n[\u002FCONTEXT]\n\n## Your Process (Chain-of-Verification)\n\n1. **Initial Review**:\n   - Assess code readability and clarity\n   - Check for code smells and complexity\n   - Evaluate naming, structure, and organization\n   - Look for duplication and coupling issues\n   - Verify error handling and edge cases\n\n2. **Self-Verification**:\n   - Generate 3-5 verification questions about your review\n   - Example: \"Am I applying personal preferences vs. objective quality criteria?\"\n   - Example: \"Did I consider the existing codebase style?\"\n   - Answer each question honestly\n   - Refine your review based on answers\n\n3. **Final Critique**:\n   Provide structured output:\n\n   ### Code Quality Score: X\u002F10\n\n   ### Quality Assessment:\n   **Strengths**:\n   - [strength 1 with specific example]\n   - [strength 2]\n\n   **Issues Found**:\n   - [issue 1] - Severity: [Critical\u002FHigh\u002FMedium\u002FLow]\n     - Location: [file:line]\n     - Example: [code snippet]\n\n   ### Refactoring Opportunities:\n\n   1. **[Refactoring 1 Name]** - Priority: [High\u002FMedium\u002FLow]\n      - Current code:\n        ```\n        [code snippet]\n        ```\n      - Suggested refactoring:\n        ```\n        [improved code]\n        ```\n      - Benefits: [explanation]\n      - Effort: [Small\u002FMedium\u002FLarge]\n\n   2. **[Refactoring 2]**\n      - [same structure]\n\n   ### Code Smells Detected:\n   - [smell 1] at [location] - [explanation and impact]\n   - [smell 2]\n\n   ### Complexity Analysis:\n   - High complexity areas: [list with locations]\n   - Suggested simplifications: [list]\n\n   ### Verification Questions & Answers:\n   Q1: [question]\n   A1: [answer that influenced your critique]\n   ...\n\nProvide specific, actionable feedback with code examples.\n```\n\n**Implementation Note**: Use the Task tool with subagent_type=\"general-purpose\" to spawn these three agents in parallel, each with their respective prompt and context.\n\n### Phase 3: Cross-Review & Debate\n\nAfter receiving all three judge reports:\n\n1. **Synthesize the findings**:\n   - Identify areas of agreement\n   - Identify contradictions or disagreements\n   - Note gaps in any review\n\n2. **Conduct debate session** (if significant disagreements exist):\n   - Present conflicting viewpoints to judges\n   - Ask each judge to review the other judges' findings\n   - Example: \"Requirements Validator says approach is overengineered, but Solution Architect says it's appropriate for scale. Please both review this disagreement and provide reasoning.\"\n   - Use Task tool to spawn follow-up agents that have context of previous reviews\n\n3. **Reach consensus**:\n   - Synthesize the debate outcomes\n   - Identify which viewpoints are better supported\n   - Document any unresolved disagreements with \"reasonable people may disagree\" notation\n\n### Phase 4: Generate Consensus Report\n\nCompile all findings into a comprehensive, actionable report:\n\n```markdown\n# ? Work Critique Report\n\n## Executive Summary\n[2-3 sentences summarizing overall assessment]\n\n**Overall Quality Score**: X\u002F10 (average of three judge scores)\n\n---\n\n## ? Judge Scores\n\n| Judge | Score | Key Finding |\n|-------|-------|-------------|\n| Requirements Validator | X\u002F10 | [one-line summary] |\n| Solution Architect | X\u002F10 | [one-line summary] |\n| Code Quality Reviewer | X\u002F10 | [one-line summary] |\n\n---\n\n## ✅ Strengths\n\n[Synthesized list of what was done well, with specific examples]\n\n1. **[Strength 1]**\n   - Source: [which judge(s) noted this]\n   - Evidence: [specific example]\n\n---\n\n## ⚠️ Issues & Gaps\n\n### Critical Issues\n[Issues that need immediate attention]\n\n- **[Issue 1]**\n  - Identified by: [judge name]\n  - Location: [file:line if applicable]\n  - Impact: [explanation]\n  - Recommendation: [what to do]\n\n### High Priority\n[Important but not blocking]\n\n### Medium Priority\n[Nice to have improvements]\n\n### Low Priority\n[Minor polish items]\n\n---\n\n## ? Requirements Alignment\n\n[Detailed breakdown from Requirements Validator]\n\n**Requirements Met**: X\u002FY\n**Coverage**: Z%\n\n[Specific requirements table with status]\n\n---\n\n## ?️ Solution Architecture\n\n[Key insights from Solution Architect]\n\n**Chosen Approach**: [brief description]\n\n**Alternative Approaches Considered**:\n1. [Alternative 1] - [Why chosen approach is better\u002Fworse]\n2. [Alternative 2] - [Why chosen approach is better\u002Fworse]\n\n**Recommendation**: [Stick with current \u002F Consider alternative X because...]\n\n---\n\n## ? Refactoring Recommendations\n\n[Prioritized list from Code Quality Reviewer]\n\n### High Priority Refactorings\n\n1. **[Refactoring Name]**\n   - Benefit: [explanation]\n   - Effort: [estimate]\n   - Before\u002FAfter: [code examples]\n\n### Medium Priority Refactorings\n[similar structure]\n\n---\n\n## ? Areas of Consensus\n\n[List where all judges agreed]\n\n- [Agreement 1]\n- [Agreement 2]\n\n---\n\n## ? Areas of Debate\n\n[If applicable - where judges disagreed]\n\n**Debate 1: [Topic]**\n- Requirements Validator position: [summary]\n- Solution Architect position: [summary]\n- Resolution: [consensus reached or \"reasonable disagreement\"]\n\n---\n\n## ? Action Items (Prioritized)\n\nBased on the critique, here are recommended next steps:\n\n**Must Do**:\n- [ ] [Critical action 1]\n- [ ] [Critical action 2]\n\n**Should Do**:\n- [ ] [High priority action 1]\n- [ ] [High priority action 2]\n\n**Could Do**:\n- [ ] [Medium priority action 1]\n- [ ] [Nice to have action 2]\n\n---\n\n## ? Learning Opportunities\n\n[Lessons that could improve future work]\n\n- [Learning 1]\n- [Learning 2]\n\n---\n\n## ? Conclusion\n\n[Final assessment paragraph summarizing whether the work meets quality standards and key takeaways]\n\n**Verdict**: ✅ Ready to ship | ⚠️ Needs improvements before shipping | ❌ Requires significant rework\n\n---\n\n*Generated using Multi-Agent Debate + LLM-as-a-Judge pattern*\n*Review Date: [timestamp]*\n```\n\n## Important Guidelines\n\n1. **Be Objective**: Base assessments on evidence, not preferences\n2. **Be Specific**: Always cite file locations, line numbers, and code examples\n3. **Be Constructive**: Frame criticism as opportunities for improvement\n4. **Be Balanced**: Acknowledge both strengths and weaknesses\n5. **Be Actionable**: Provide concrete recommendations with examples\n6. **Consider Context**: Account for project constraints, team size, timelines\n7. **Avoid Bias**: Don't favor certain patterns\u002Fstyles without justification\n\n## Usage Examples\n\n```bash\n# Review recent work from conversation\n\u002Fcritique\n\n# Review specific files\n\u002Fcritique src\u002Ffeature.ts src\u002Ffeature.test.ts\n\n# Review with specific focus\n\u002Fcritique --focus=security\n\n# Review a git commit\n\u002Fcritique HEAD~1..HEAD\n```\n\n## Notes\n\n- This is a **report-only** command - it does not make changes\n- The review may take 2-5 minutes due to multi-agent coordination\n- Scores are relative to professional development standards\n- Disagreements between judges are valuable insights, not failures\n- Use findings to inform future development decisions\n",{"name":5,"description":7,"argument-hint":31},"Optional file paths, commits, or context to review (defaults to recent changes)","master","c73386b305dec167db7654e0e6feacb462d4f9dc","assets\u002Fskills\u002Fthinking\u002Fcritique",1,"https:\u002F\u002Fgithub.com\u002FAntifragileTech\u002Fantifragile-claude-code","https:\u002F\u002Fgithub.com\u002FAntifragileTech","2026-10-02 14:22:14",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add AntifragileTech\u002Fantifragile-claude-code --skill \"reflexion:critique\"",{"tool":45,"command":46},"bunx","bunx skills add AntifragileTech\u002Fantifragile-claude-code --skill \"reflexion:critique\"",{"tool":48,"command":49},"pnpm","pnpm dlx skills add AntifragileTech\u002Fantifragile-claude-code --skill \"reflexion:critique\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAntifragileTech\u002Fantifragile-claude-code\u002Fblob\u002Fmaster\u002Fassets\u002Fskills\u002Fthinking\u002Fcritique\u002FSKILL.md",true,[],[54,80,95,110,123,136],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":73,"publishedAt":26},"01M6DT9Q6VYA615SCXR757TZZ7","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002FAntifragileTech\u002Fantifragile-claude-code\u002Fblob\u002Fmaster\u002Fassets\u002Fskills\u002Fthinking\u002Fwriting-skills\u002FSKILL.md",[60,65,68],{"categoryNo":61,"categoryName":62,"taxonomyType":63,"taxonomyTypeDesc":64},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":66,"categoryName":67,"taxonomyType":63,"taxonomyTypeDesc":64},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":69,"categoryName":70,"taxonomyType":71,"taxonomyTypeDesc":72},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[74,75,76,77,78,79],"writing skills","writing","use","editing","work","deployment",{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":88,"publishedAt":26},"01M6DT9GFHDNY90P41WGAE1TV0","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002FAntifragileTech\u002Fantifragile-claude-code\u002Fblob\u002Fmaster\u002Fassets\u002Fskills\u002Fthinking\u002Fwriting-plans\u002FSKILL.md",[86,87],{"categoryNo":66,"categoryName":67,"taxonomyType":63,"taxonomyTypeDesc":64},{"categoryNo":69,"categoryName":70,"taxonomyType":71,"taxonomyTypeDesc":72},[89,90,75,91,92,76,93,94],"plans","writing plans","requirements","task","code","spec",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":103,"publishedAt":26},"01M6DT9C6PFGD86WS3HY7YE3XG","docs:write-concisely","Apply writing rules to any documentation that humans will read. Makes your writing clearer, stronger, and more professional.","https:\u002F\u002Fgithub.com\u002FAntifragileTech\u002Fantifragile-claude-code\u002Fblob\u002Fmaster\u002Fassets\u002Fskills\u002Fthinking\u002Fwrite-concisely\u002FSKILL.md",[101,102],{"categoryNo":66,"categoryName":67,"taxonomyType":63,"taxonomyTypeDesc":64},{"categoryNo":69,"categoryName":70,"taxonomyType":71,"taxonomyTypeDesc":72},[104,105,106,107,108,109,75],"docs:write concisely","write","docs","read","Rules","documentation",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":26},"01M6DT98AWQ27P0N1CG97WAG66","kaizen:why","Iterative Five Whys root cause analysis drilling from symptoms to fundamentals","https:\u002F\u002Fgithub.com\u002FAntifragileTech\u002Fantifragile-claude-code\u002Fblob\u002Fmaster\u002Fassets\u002Fskills\u002Fthinking\u002Fwhy\u002FSKILL.md",[],[112,117,118,119,120,121,122],"why","kaizen","issue","five whys","analysis","root cause analysis",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":26},"01M6DT93EH25NAX19R3WGE1P53","verification-loop","A comprehensive verification system for Claude Code sessions.","https:\u002F\u002Fgithub.com\u002FAntifragileTech\u002Fantifragile-claude-code\u002Fblob\u002Fmaster\u002Fassets\u002Fskills\u002Fthinking\u002Fverification-loop\u002FSKILL.md",[],[130,131,132,133,93,134,135],"verification loop","verification","loop","sessions","claude code sessions","system",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":26},"01M6DT90GW7Z7VCN98P9DVYSNC","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002FAntifragileTech\u002Fantifragile-claude-code\u002Fblob\u002Fmaster\u002Fassets\u002Fskills\u002Fthinking\u002Fverification-before-completion\u002FSKILL.md",[],[143,131,144,78,76,145,146,147],"verification before completion","commands","evidence","claim","complete"]