code-review-assistant
Conduct comprehensive code reviews identifying bugs, security issues, performance problems, code quality concerns, and best practice violations. Use when reviewing pull requests, examining code changes, evaluating new code, assessing code quality, or providing feedback on implementations. Analyzes code for correctness, security vulnerabilities, performance bottlenecks, maintainability issues, test coverage, documentation quality, and adherence to coding standards. Produces structured markdown reviews with categorized findings, severity ratings, specific examples, and actionable recommendations. Triggers when users ask to review code, check pull requests, evaluate implementations, find bugs, or assess code quality.
88
88%
Does it follow best practices?
Impact
83%
1.25xAverage score across 3 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 key criteria. It provides comprehensive specificity about what the skill does, includes abundant natural trigger terms users would actually say, explicitly addresses both 'what' and 'when' questions, and carves out a distinct niche for code review tasks. The description uses proper third-person voice throughout and avoids vague language.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'identifying bugs, security issues, performance problems, code quality concerns, and best practice violations' plus detailed analysis areas like 'correctness, security vulnerabilities, performance bottlenecks, maintainability issues, test coverage, documentation quality.' | 3 / 3 |
Completeness | Clearly answers both what ('Conduct comprehensive code reviews identifying bugs...') and when ('Use when reviewing pull requests...') with explicit trigger guidance ('Triggers when users ask to review code, check pull requests...'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'pull requests', 'code changes', 'code quality', 'review code', 'check pull requests', 'find bugs', 'evaluate implementations' - these are all phrases users naturally use when requesting code reviews. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on code review with distinct triggers like 'pull requests', 'review code', 'find bugs' - unlikely to conflict with general coding skills or documentation skills due to the specific review/evaluation focus. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive code review skill with excellent actionability and clear workflow structure. However, it suffers from verbosity - explaining concepts Claude already knows (security vulnerabilities, language patterns, testing principles) and including extensive inline content that would be better as separate reference files. The skill would benefit from aggressive trimming and splitting into a concise overview with linked reference materials.
Suggestions
Remove or drastically condense the 'Common Issues by Language' section - Claude knows these patterns; at most, provide a brief reminder list without full code examples
Extract the Security Checklist, Performance Review Points, and Code Quality Standards into separate reference files (e.g., SECURITY_CHECKLIST.md, PERFORMANCE.md) and link to them
Remove explanatory text that defines concepts Claude knows (e.g., 'DRY (Don't Repeat Yourself)', explanations of what SQL injection or XSS are)
Condense the review template to essential structure only - the current version is overly detailed for a template
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but overly verbose for Claude's capabilities. Many sections explain concepts Claude already knows (what SQL injection is, what DRY means, basic language-specific patterns). The common issues by language section and security checklist could be significantly condensed. | 2 / 3 |
Actionability | Provides fully executable code examples across multiple languages, specific bash commands for PR review, and copy-paste ready templates. The review template and example reviews are concrete and immediately usable. | 3 / 3 |
Workflow Clarity | Clear 4-step workflow (Understand Context → Read Code → Identify Issues → Provide Feedback) with explicit sub-steps. Severity categorization (Critical/Important/Minor/Suggestion) provides clear decision framework. The workflow is well-sequenced for the review process. | 3 / 3 |
Progressive Disclosure | Content is monolithic - over 400 lines in a single file with no references to external files. The language-specific examples, security checklist, and performance review points could be split into separate reference files. The structure uses headers well but everything is inline. | 2 / 3 |
Total | 10 / 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (526 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- ArabelaTso/Skills-4-SE
- Commit
0f00a4f
- 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.