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
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that hits all the marks. It provides highly specific capabilities with concrete examples (SQL injection, XSS, N+1 queries), includes comprehensive trigger terms that users would naturally say, explicitly states when to use it, and even clarifies its relationship to other skills to prevent conflicts.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: '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.' | 3 / 3 |
Completeness | Clearly answers both what (analyzes diffs, identifies bugs/vulnerabilities/smells, produces structured report) AND when with explicit 'Use when...' clause covering PR reviews, code audits, refactoring, and security checks. Also includes 'Invoke for...' with additional trigger terms. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'pull requests', 'PR reviews', 'code quality checks', 'refactoring suggestions', 'review code', 'code quality', 'security issues'. These are terms users naturally use when requesting code review. | 3 / 3 |
Distinctiveness Conflict Risk | Explicitly distinguishes itself from related skills by stating 'Complements specialized skills (security-reviewer, test-master) by providing broad-scope review' - clearly defining its niche as comprehensive multi-dimensional review versus specialized single-focus tools. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an exemplary skill file that demonstrates best practices across all dimensions. It provides a clear workflow with validation checkpoints, concrete code examples for common issues, and well-organized progressive disclosure through the reference table. The constraints section with MUST DO/MUST NOT DO lists adds clear guardrails without being verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, avoiding explanations of concepts Claude already knows. Each section serves a clear purpose with no padding or unnecessary context about what code review is. | 3 / 3 |
Actionability | Provides concrete, executable code examples for common issues (N+1 queries, magic numbers, SQL injection) with clear bad vs good patterns. The workflow steps are specific with explicit checkpoints and questions to ask. | 3 / 3 |
Workflow Clarity | Clear 5-step workflow with explicit checkpoints ('Summarize the PR's intent in one sentence before proceeding'), validation gates, and feedback loops. Includes guidance on when to escalate critical issues immediately rather than waiting. | 3 / 3 |
Progressive Disclosure | Excellent structure with a concise overview and a clear reference table pointing to one-level-deep detailed guides. The 'Load When' column helps Claude know exactly when to access each reference file. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- jeffallan/claude-skills
- Commit
5b76101
- Reviewed
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.