Summary
This automates the tedious parts of code review by running git diff against your base branch and systematically checking for common issues across security, performance, code quality, and testing. It looks for hardcoded secrets, SQL injection risks, N+1 queries, missing error handling, and test coverage gaps, then gives you a structured markdown summary with critical issues, warnings, and suggestions. The checklist approach is solid because it catches things you might miss at 4pm on a Friday. Works best when you want a second pair of eyes before merging or need to review a large PR where manual inspection would take forever.
Install to Claude Code
npx -y skills add onewave-ai/claude-skills --skill git-pr-reviewer --agent claude-codeInstalls into .claude/skills of the current project.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Files
SKILL.mdView on GitHub
Git PR Reviewer
Instructions
When reviewing a pull request:
- Get the diff: Run
git diff main...HEADorgit diff <base-branch>...HEAD - Analyze changed files: Identify all modified, added, and deleted files
- Review each file for:
- Logic errors and bugs
- Security vulnerabilities (SQL injection, XSS, hardcoded secrets)
- Performance issues (N+1 queries, unnecessary re-renders, memory leaks)
- Code style and consistency
- Missing error handling
- Test coverage gaps
Review Checklist
Security
- No hardcoded credentials or API keys
- Input validation on user data
- Proper authentication/authorization checks
- No SQL injection vulnerabilities
- XSS prevention in place
Code Quality
- Functions are small and focused
- No code duplication
- Clear variable/function naming
- Proper error handling
- No unused imports or dead code
Performance
- No unnecessary database queries
- Efficient algorithms used
- Proper caching where needed
- No memory leaks
Testing
- New code has tests
- Edge cases covered
- Tests are meaningful, not just for coverage
Output Format
## PR Review Summary
### Overview
[Brief summary of changes]
### Issues Found
#### Critical
- [Issue description + file:line]
#### Warnings
- [Issue description + file:line]
#### Suggestions
- [Improvement ideas]
### Approval Status
[APPROVE / REQUEST CHANGES / NEEDS DISCUSSION]
Example
# Review current branch against main
git diff main...HEAD --stat
git diff main...HEAD
Featured
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
