code-reviewer · zhaono1 — Claude Code skill: what it does, how to install
Reviews Git diffs and pull requests for security vulnerabilities, logic flaws, test coverage, and code quality.
npx skills add zhaono1/agent-playbook --skill code-reviewer -a claude-codeWhat code-reviewer does
This skill guides coding agents through reviewing branch changes before merging. It runs git diff main...HEAD to inspect changes alongside modified file paths and commit logs. The inspection checks for core issues: logic edge cases, unhandled errors, hardcoded credentials, injection risks, and performance traps such as N+1 database queries.
Findings are grouped into a standardized report sorted by severity: Critical, High, Medium, and Low. Each issue references the exact file and line number. The output concludes with positive highlights, optional tips, and an explicit approval status. Specific checks adapt to TypeScript, React, Python, and Go conventions.
Running the bundled checklist script requires Python 3. The agent also needs access to Bash, Read, and Grep tools to read repository history, failing whenever Git lacks a comparison target like main.
What it helps with
- spot hardcoded secrets and security flaws before merging
- detect N+1 database queries and performance bottlenecks
- verify test coverage and edge case handling across changes
- organize pull request feedback by severity levels
Example prompts for the agent
- Review changes in the current branch against main
- Check this pull request for bugs and security risks
- Run a code review on the latest diff and group issues by severity
How to install code-reviewer
1Skills CLI (Vercel)
npx skills add zhaono1/agent-playbook --skill code-reviewer -a claude-code2Manually: put the files in place
~/.claude/skills/code-reviewer/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/code-reviewer/
1Skills CLI (Vercel)
npx skills add zhaono1/agent-playbook --skill code-reviewer -a codex2Manually: put the files in place
.agents/skills/code-reviewer/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add zhaono1/agent-playbook --skill code-reviewer -a cursor2Manually: put the files in place
.cursor/skills/code-reviewer/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install zhaono1/agent-playbook code-reviewer2Manually: put the files in place
.github/skills/code-reviewer/SKILL.md1Skills CLI (Vercel)
npx skills add zhaono1/agent-playbook --skill code-reviewer -a gemini-cli2Platform CLI
gemini skills install https://github.com/zhaono1/agent-playbook --path skills/code-reviewerManually: put the files in place
.devin/skills/code-reviewer/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add zhaono1/agent-playbook --skill code-reviewer -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about code-reviewer
How to install code-reviewer in Claude Code?
Run npx skills add zhaono1/agent-playbook --skill code-reviewer -a claude-code in your terminal, or place the skill at ~/.claude/skills/code-reviewer/SKILL.md.
What issues does code-reviewer look for?
It inspects pull requests for logic errors, hardcoded secrets, injection vulnerabilities, missing tests, and stack-specific conventions across TypeScript, React, Python, and Go.
Does code-reviewer require external dependencies?
The agent needs Git with a base branch like main and access to Bash, Read, and Grep tools. Generating checklist files with scripts/review_checklist.py requires Python 3.
Source text
SKILL.md · MIT
---
name: code-reviewer
description: Reviews pull requests and code changes for quality, security, and best practices. Use when user asks for code review, PR review, or mentions reviewing changes.
allowed-tools: Read, Grep, Glob, Bash, WebFetch, WebSearch
metadata:
hooks:
after_complete:
- trigger: self-improving-agent
mode: background
reason: "Learn from review patterns"
- trigger: session-logger
mode: auto
reason: "Log review activity"
---
# Code Reviewer
A comprehensive code review skill that analyzes pull requests and code changes for quality, security, maintainability, and best practices.
## When This Skill Activates
This skill activates when you:
- Ask for a code review
- Request a PR review
- Mention reviewing changes
- Say "review this" or "check this code"
## Review Process
### Phase 1: Context Gathering
1. **Get changed files**
```bash
git diff main...HEAD --name-only
git log main...HEAD --oneline
```
2. **Get the diff**
```bash
git diff main...HEAD
```
3. **Understand project context**
- Read relevant documentation
- Check existing patterns in similar files
- Identify project-specific conventions
### Phase 2: Analysis Categories
#### 1. Correctness
- [ ] Logic is sound and matches requirements
- [ ] Edge cases are handled
- [ ] Error handling is appropriate
- [ ] No obvious bugs or typos
#### 2. Security
- [ ] No hardcoded secrets or credentials
- [ ] Input validation and sanitization
- [ ] SQL injection prevention
- [ ] XSS prevention (for frontend)
- [ ] Authentication/authorization checks
- [ ] Safe handling of user data
#### 3. Performance
- [ ] No N+1 queries
- [ ] Appropriate caching
- [ ] Efficient algorithms
- [ ] No unnecessary computations
- [ ] Memory efficiency
#### 4. Code Quality
- [ ] Follows DRY principle
- [ ] Follows KISS principle
- [ ] Appropriate abstractions
- [ ] Clear naming conventions
- [ ] Proper typing (if TypeScript)
- [ ] No commented-out code
#### 5. Testing
- [ ] Tests cover new functionality
- [ ] Tests cover edge cases
- [ ] Test assertions are meaningful
- [ ] No brittle tests
#### 6. Documentation
- [ ] Complex logic is explained
- [ ] Public APIs have documentation
- [ ] JSDoc/TSDoc for functions
- [ ] README updated if needed
#### 7. Maintainability
- [ ] Code is readable
- [ ] Consistent style
- [ ] Modular design
- [ ] Separation of concerns
### Phase 3: Output Format
Use this structured format for review feedback:
```markdown
# Code Review
## Summary
Brief overview of the changes (2-3 sentences).
## Issues by Severity
### Critical
Must fix before merge.
- [ ] **Issue Title**: Description with file:line reference
### High
Should fix before merge unless there's a good reason.
- [ ] **Issue Title**: Description with file:line reference
### Medium
Consider fixing, can be done in follow-up.
- [ ] **Issue Title**: Description with file:line reference
### Low
Nice to have improvements.
- [ ] **Issue Title**: Description with file:line reference
## Positive Highlights
What was done well in this PR.
## Suggestions
Optional improvements that don't require immediate action.
## Approval Status
- [ ] Approved
- [ ] Approved with suggestions
- [ ] Request changes
```
## Common Issues to Check
### Security Issues
| Issue | Pattern | Recommendation |
|-------|----------|----------------|
| Hardcoded secrets | `const API_KEY = "sk-"` | Use environment variables |
| SQL injection | `\"SELECT * FROM...\" + user_input` | Use parameterized queries |
| XSS vulnerability | `innerHTML = user_input` | Sanitize or use textContent |
| Missing auth check | New endpoint without `@RequireAuth` | Add authentication middleware |
### Performance Issues
| Issue | Pattern | Recommendation |
|-------|----------|----------------|
| N+1 query | Loop with database call | Use eager loading or batch queries |
| Unnecessary re-render | Missing dependencies in `useEffect` | Fix dependency array |
| Memory leak | Event listener not removed | Add cleanup in useEffect return |
| Inefficient loop | Nested loops O(n²) | Consider hash map or different algorithm |
### Code Quality Issues
| Issue | Pattern | Recommendation |
|-------|----------|----------------|
| Duplicate code | Similar blocks repeated | Extract to function |
| Magic number | `if (status === 5)` | Use named constant |
| Long function | Function >50 lines | Split into smaller functions |
| Complex condition | `a && b || c && d` | Extract to variable with descriptive name |
### Testing Issues
| Issue | Pattern | Recommendation |
|-------|----------|----------------|
| No tests | New feature without test file | Add unit tests |
| Untested edge case | Test only covers happy path | Add edge case tests |
| Brittle test | Test relies on implementation details | Test behavior, not implementation |
| Missing assertion | Test doesn't assert anything | Add proper assertions |
## Language-Specific Guidelines
### TypeScript
- Use `unknown` instead of `any` for untyped values
- Prefer `interface` for public APIs, `type` for unions
- Use strict mode settings
- Avoid `as` assertions when possible
### React
- Follow Hooks rules
- Use `useCallback`/`useMemo` appropriately (not prematurely)
- Prefer function components
- Use proper key props in lists
- Avoid prop drilling with Context
### Python
- Follow PEP 8 style guide
- Use type hints
- Use f-strings for formatting
- Prefer list comprehensions over map/filter
- Use context managers for resources
### Go
- Handle errors explicitly
- Use named returns for clarity
- Keep goroutines simple
- Use channels for communication
- Avoid package-level state
## Before Approving
Confirm the following:
- [ ] All critical issues are addressed
- [ ] Tests pass locally
- [ ] No merge conflicts
- [ ] Commit messages are clear
- [ ] Documentation is updated
- [ ] Breaking changes are documented
## Scripts
Run the review checklist script:
```bash
python3 scripts/review_checklist.py --base main --output review-checklist.md
```
## References
- `references/checklist.md` - Complete review checklist
- `references/security.md` - Security review guidelines
- `references/patterns.md` - Common patterns and anti-patterns
© zhaono1 · MIT · zhaono1/agent-playbook
Similar skills
All skills for Code review and refactoring →code-reviewer by other authors comes first.