code-review_skill

Overview

This skill performs automated code reviews for pull requests using specialized review patterns focused on security, performance, quality, and testing. It produces structured, actionable feedback with prioritized findings and suggested fixes. Use it to accelerate reviews, enforce standards, and reduce regressions before merging.

How this skill works

The skill analyzes diff contents and inspects files for known anti-patterns: injection risks, inefficient queries, missing indexes, and poor error handling. It classifies findings into Critical, Suggestions, and Nits and outputs concise rationale and recommended fixes for each issue. A checklist and positives section help maintainers track required changes and recognize good patterns.

When to use it

• Reviewing pull requests or feature branches before merge
• Performing security-focused code audits or threat-modeling reviews
• Evaluating performance regressions after changes
• Validating new code for testing and type coverage
• Onboarding contributors to reinforce coding standards

Best practices

• Prioritize fixes labeled Critical; these usually block merging
• Include minimal code snippets for reproducing and fixing issues
• Reference specific lines/files so developers can act quickly
• Combine automated findings with a short human review for context
• Add tests and update documentation when fixing behavior-impacting issues

Example use cases

• Find and fix SQL/command injection and hardcoded secrets in a PR
• Detect N+1 queries and suggest batching or eager loading changes
• Identify missing tests for new logic and recommend cases to add
• Flag swallowed errors and propose proper logging or rethrowing
• Spot React unnecessary re-renders or large bundle artifacts and suggest improvements