Agent skill
coderabbit-review
Use CodeRabbit CLI to receive external code review feedback and address identified issues. Invoke this skill when the user requests CodeRabbit review, or proactively after implementing significant code changes to get feedback and improve code quality.
Stars
163
Forks
31
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/coderabbit-review
SKILL.md
Coderabbit Review
Workflow
- After implementing code changes, request a review from CodeRabbit
- Analyze the review results and understand the feedback
- Fix the identified issues
- Re-run the review if necessary to confirm fixes
Command Reference
--prompt-only: Show only AI agent prompts (implies --plain)--plain: Output in plain text format with human-friendly formatting--type <type>: Review type: all, committed, uncommitted (default: "all")--base <branch>: Base branch for comparison--base-commit <commit>: Base commit on current branch for comparison--cwd <path>: Working directory path (default: current directory)
Command Selection
Review all changes (default):
bash
coderabbit review --prompt-only
Review uncommitted changes only:
bash
coderabbit review --prompt-only --type uncommitted
Review committed changes only:
bash
coderabbit review --prompt-only --type committed
Compare against base branch:
bash
coderabbit review --prompt-only --base <branch>
Handling Review Feedback
When review feedback is received, address issues in the following priority order:
- Security issues - Fix immediately
- Bugs/regressions - High priority fixes
- Missing tests - Add required test coverage
- Code quality - Implement refactoring and improvements
- Style/conventions - Align with project standards
Verification
After addressing the feedback, re-run coderabbit review --prompt-only to confirm that the issues have been resolved.
Didn't find tool you were looking for?