code-review
Guide for making code reviews. Use this when asked to make code reviews, or ask to use it before committing changes.
When & Why to Use This Skill
This Claude skill automates and enhances the code review process by deploying a multi-agent system to inspect git diffs. By utilizing competing subagents to analyze both architecture and implementation, it ensures a rigorous evaluation of code changes, helping developers identify bugs and structural issues before committing to the main branch.
Use Cases
- Pre-commit Quality Assurance: Use the skill to automatically review staged changes or git diffs to catch errors before they are finalized in the version control system.
- Architectural Integrity Checks: Evaluate how new branch changes impact the overall software architecture compared to the main codebase.
- Automated Peer Review: Supplement human code reviews with an AI-driven dual-agent analysis that provides diverse perspectives on implementation efficiency and best practices.
- Continuous Integration Support: Integrate the review logic into development workflows to maintain high coding standards and reduce technical debt.
| name | code-review |
|---|---|
| description | Guide for making code reviews. Use this when asked to make code reviews, or ask to use it before committing changes. |
| license | MIT |
Code review
Always start by inspecting the changes. If you're on the main git branch, typically the (staged) git diff. If you're on a different branch, the committed and uncommitted changes compared to the main branch.
Method
Please dispatch two subagents to carefully review the code changes. Tell them that they're competing with another agent. Make sure they look at both architecture and implementation. Tell them that whomever finds more issues wins honour and glory.