Code review
A set of 8 global skills for Claude Code that enforce disciplined, test-driven agentic development. Install once, use in any project.
npx -y skills add burhankhatri/e2e-testing --skill code-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 10 stars10 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use when a major project step has been completed and needs review against the plan and coding standards. Also use when someone says 'review this', 'check my code', 'is this ready', or when a significant chunk of implementation is done. Use after completing tasks from an implementation plan, before creating PRs, or when asked to assess code quality.
SKILL.md
2.8 KB, as published. Nobody here has run it
Code Review
Two-Stage Review Process
Stage 1: Spec Compliance
Before assessing quality, verify the code does what was asked:
- Compare implementation against the spec/plan — requirement by requirement
- Is anything missing? — features specified but not implemented
- Is anything extra? — features added that weren't requested (YAGNI violation — remove them)
- Are deviations justified? — if the implementation differs from the plan, is it a genuine improvement or a problematic departure?
If spec compliance fails: Fix gaps before moving to Stage 2. Don't review quality of incomplete work.
Stage 2: Code Quality
- Error handling — are errors caught, logged, and handled appropriately? Are edge cases covered?
- Type safety — proper types, no
anyunless justified, interfaces match contracts - Naming — clear, descriptive, consistent with codebase conventions
- Organization — separation of concerns, single responsibility, loose coupling
- Test coverage — are tests meaningful? Do they test behavior, not implementation?
- Security — input validation, no hardcoded secrets, SQL injection, XSS
- Performance — obvious N+1 queries, unnecessary re-renders, missing indexes
Issue Categories
- Critical (must fix) — blocks merge, breaks functionality, security vulnerability
- Important (should fix) — code smell, missing edge case, poor naming, missing test
- Suggestion (nice to have) — style preference, minor optimization, alternative approach
Review Output Format
## Spec Compliance: ✅ PASS / ❌ FAIL
[If FAIL: list missing/extra items]
## Code Quality
### Strengths
- [What was done well — always acknowledge before critiquing]
### Critical Issues
- [File:line] Description. Fix: [specific suggestion]
### Important Issues
- [File:line] Description. Fix: [specific suggestion]
### Suggestions
- [File:line] Description. Consider: [alternative]
## Verdict: APPROVED / CHANGES REQUESTED
Principles
- Always acknowledge what was done well before highlighting issues
- Be specific — file, line, concrete suggestion, not vague "improve error handling"
- Provide code examples for non-obvious fixes
- Don't nitpick style if the codebase has no established convention
- Check the tests — are they testing real behavior or mock existence?
- Verify independently — don't trust claims, check the actual code/output