agentsclimarketplace
Sign in

Code reviewer

Skill claude-world/director-mode-lite/skills/code-reviewer

Code review knowledge base: quality, security (OWASP Top 10), error-handling, performance, and test-coverage checklists with severity-ranked output format. Use when reviewing code changes, PRs, or before commits. Loaded automatically by the code-reviewer agent.From its SKILL.md

Install
npx -y skills add claude-world/director-mode-lite --skill code-reviewer

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

2.6 KB, 547 tokens by cl100k_base, as published. Nobody here has run it

Code Reviewer Skill

Director Mode Lite - Code Review Specialist

Review Checklist

Canonical checklist for reviewing code changes. Work through every section.

1. Code Quality

  • Clear, descriptive naming for functions and variables
  • Proper function/method length (< 30 lines), focused and single-purpose
  • Single responsibility principle
  • No code duplication (DRY)
  • Code is simple, readable, and self-documenting
  • Comments explain "why", not "what"

2. Security (OWASP Top 10)

  • Input validation at system boundaries
  • SQL injection prevention (parameterized queries)
  • XSS prevention
  • Command injection prevention
  • No exposed secrets, API keys, or credentials
  • Authentication/Authorization checks
  • Sensitive data handled securely (no data exposure)

3. Error Handling

  • Appropriate error handling for edge cases
  • Meaningful error messages
  • Graceful degradation where appropriate
  • No silent failures

4. Performance

  • No N+1 queries; efficient database queries
  • Efficient algorithms
  • Proper caching where beneficial
  • Memory leak prevention
  • No unnecessary loops or computations

5. Testing

  • Tests exist for new code
  • Happy path and edge cases covered
  • Test names clearly describe what is being tested

6. Documentation

  • Complex logic is commented
  • Public APIs are documented
  • README updated if needed

Review Process

Step 1: Read the code changes
Step 2: Run through the checklist
Step 3: Provide feedback with:
        - Category (Quality/Security/Error Handling/Performance/Testing/Docs)
        - Severity (Critical/Major/Minor/Suggestion)
        - Specific line reference
        - Suggested fix

Output Format

## Code Review Summary

### Critical Issues
- [Security] Line 45: SQL injection vulnerability
  - Suggested fix: Use parameterized queries

### Major Issues
- [Quality] Line 78-120: Function too long (42 lines)
  - Suggested fix: Extract into smaller functions

### Minor Issues
- [Docs] Line 10: Missing JSDoc for public function

### Suggestions
- Consider adding input validation at line 23

### Approved
- [ ] Ready to merge (no critical/major issues)

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most test skills give in 547 tokens

Counted across 1,201 of the 2,096 authors here whose files we hold, read 2026-09-06

  • Write a failing test before writing codein 43 of 1201, across 36 files
  • Run the full test suitein 36 of 1201, across 35 files
  • Test only one variable per experimentin 34 of 1201, across 17 files
  • Read product marketing context before asking questionsin 34 of 1201, across 14 files
  • Mock external dependenciesin 34 of 1201, across 30 files
  • Define primary, secondary, and guardrail metricsin 33 of 1201, across 16 files
  • Pre-determine sample size before startingin 31 of 1201, across 14 files
  • Test behavior rather than implementationin 31 of 1201, across 29 files
  • Formulate a hypothesis before designing a testin 30 of 1201, across 13 files
  • Document every test hypothesis, variant, and resultin 29 of 1201, across 11 files
  • Use descriptive test function namesin 25 of 1201, across 21 files
  • Commit to the methodology without stopping earlyin 24 of 1201, across 8 files

Said here and by no other author read

  • Read the code changes
  • Check code quality
  • Verify security against OWASP Top 10
  • Check for performance issues
  • Provide feedback with category and severity
  • Suggest fixes for issues

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.