code-reviewer
Analyzes code diffs and files to identify bugs, security vulnerabilities (SQL injection, XSS, insecure deserialization), code smells, N+1 queries, naming issues, and architectural concerns, then produces a structured review report with prioritized, actionable feedback. Use when reviewing pull requests, conducting code quality audits, identifying refactoring opportunities, or checking for security issues. Invoke for PR reviews, code quality checks, refactoring suggestions, review code, code quality. Complements specialized skills (security-reviewer, test-master) by providing broad-scope review across correctness, performance, maintainability, and test coverage in a single pass.
96
100%
Does it follow best practices?
Impact
93%
1.14xAverage score across 6 eval scenarios
Passed
No known issues
Evaluation results
100%
15%Code Review: User Post Feed Service
Code review report structure and feedback quality
Summary section
100%
100%
Critical issues section
100%
100%
Major issues section
100%
100%
Minor issues section
100%
100%
Positive feedback section
100%
100%
Questions for author
0%
100%
Verdict included
100%
100%
Severity labels
87%
100%
File:line references
100%
100%
Code examples in feedback
100%
100%
Security issue identified
100%
100%
N+1 query identified
100%
100%
Magic numbers flagged
20%
100%
94%
21%User Search API: Implementation Review
Spec compliance two-stage review
Stage 1 before Stage 2
66%
100%
Missing requirements found
100%
100%
Unnecessary addition flagged
100%
100%
Interpretation gap identified
100%
70%
Professional skepticism
100%
100%
Findings categorized
70%
70%
File:line references
20%
100%
Spec compliance verdict
100%
100%
Code quality stage present
0%
100%
98%
-2%Respond to Code Review Feedback
Responding to review feedback professionally
No agreement theater
100%
100%
All items addressed
100%
100%
Specific fix acknowledgment
100%
100%
Technical pushback format
100%
100%
Restatement or clarification
100%
75%
No vague pushback
100%
100%
Code or evidence cited
100%
100%
Verification claimed correctly
100%
100%
Output file present
100%
100%
77%
11%Review: User Authentication Service
Test quality review and behavioral assertions
Tests reviewed in depth
100%
100%
Implementation-detail assertion flagged
50%
50%
Missing edge case tests identified
0%
50%
Missing error path test identified
100%
100%
Mock appropriateness questioned
10%
0%
Test feedback actionable
80%
100%
Implementation issue found
100%
100%
Summary present
100%
100%
Positive feedback included
50%
100%
Verdict included
100%
100%
96%
10%Review: Pricing Engine Refactor
PR intent summary and linter-aware style restraint
PR intent summarized
100%
100%
No quote-style nitpicking
100%
100%
No trailing-comma nitpicking
100%
100%
No indentation nitpicking
0%
50%
Logic bug identified
100%
100%
Author reasoning acknowledged
100%
100%
Missing error handling flagged
100%
100%
Positive feedback included
25%
100%
Verdict included
100%
100%
97%
18%Review: User Onboarding Service
Common code smells detection and remediation guidance
Missing error handling flagged
83%
75%
Deep nesting identified
100%
100%
God function identified
16%
100%
Mutable shared state flagged
90%
100%
Missing null check identified
100%
100%
Sync file operation flagged
100%
100%
Code examples in suggestions
100%
100%
Severity categorized
100%
100%
Positive feedback included
0%
100%
Verdict included
100%
100%
- Repository
- jeffallan/claude-skills
- Commit
5b76101
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.