AI

Automated code review assistant for analyzing diffs and pull requests for quality and security.

Install

mkdir -p .claude/skills/aif-review && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/9775" && unzip -o skill.zip -d .claude/skills/aif-review && rm skill.zip

Installs to .claude/skills/aif-review

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Perform code review on staged changes or a pull request. Checks for bugs, security issues, performance problems, and best practices. Use when user says "review code", "check my code", "review PR", or "is this code okay".
220 chars✓ has a “when” trigger
Intermediate

Key capabilities

  • Analyze staged git changes for bugs
  • Scan code for SQL and command injection vulnerabilities
  • Identify performance bottlenecks like N+1 queries
  • Validate code against SOLID and DRY principles
  • Review pull requests via GitHub CLI

How it works

The skill inspects code changes using git or GitHub CLI tools against a predefined checklist covering correctness, security, performance, and best practices. It outputs a structured report categorized by issue severity.

Inputs & outputs

You give it
Staged git changes or PR identifier
You get back
Code review summary with risk level and actionable feedback

When to use aif-review

  • Reviewing pull requests
  • Analyzing staged changes
  • Code quality checks

About this skill

Code Review Assistant

Perform thorough code reviews focusing on correctness, security, performance, and maintainability.

Behavior

Without Arguments (Review Staged Changes)

  1. Run git diff --cached to get staged changes
  2. If nothing staged, run git diff for unstaged changes
  3. Analyze each file's changes

With PR Number/URL

  1. Use gh pr view <number> --json to get PR details
  2. Use gh pr diff <number> to get the diff
  3. Review all changes in the PR

Review Checklist

Correctness

  • Logic errors or bugs
  • Edge cases handling
  • Null/undefined checks
  • Error handling completeness
  • Type safety (if applicable)

Security

  • SQL injection vulnerabilities
  • XSS vulnerabilities
  • Command injection
  • Sensitive data exposure
  • Authentication/authorization issues
  • CSRF protection
  • Input validation

Performance

  • N+1 query problems
  • Unnecessary re-renders (React)
  • Memory leaks
  • Inefficient algorithms
  • Missing indexes (database)
  • Large payload sizes

Best Practices

  • Code duplication
  • Dead code
  • Magic numbers/strings
  • Proper naming conventions
  • SOLID principles
  • DRY principle

Testing

  • Test coverage for new code
  • Edge cases tested
  • Mocking appropriateness

Output Format

## Code Review Summary

**Files Reviewed:** [count]
**Risk Level:** 🟢 Low / 🟡 Medium / 🔴 High

### Critical Issues
[Must be fixed before merge]

### Suggestions
[Nice to have improvements]

### Questions
[Clarifications needed]

### Positive Notes
[Good patterns observed]

Review Style

  • Be constructive, not critical
  • Explain the "why" behind suggestions
  • Provide code examples when helpful
  • Acknowledge good code
  • Prioritize feedback by importance
  • Ask questions instead of making assumptions

Examples

User: /aif-review Review staged changes in current repository.

User: /aif-review 123 Review PR #123 using GitHub CLI.

User: /aif-review https://github.com/org/repo/pull/123 Review PR from URL.

Integration

If GitHub MCP is configured, can:

  • Post review comments directly to PR
  • Request changes or approve
  • Add labels based on review outcome

Tip: Context is heavy after code review. Consider /clear or /compact before continuing with other tasks.

When not to use it

  • Non-version-controlled code
  • Projects without a git repository

Prerequisites

gitGitHub CLI

Limitations

  • Requires git or GitHub CLI access
  • Cannot execute code to verify runtime behavior

How it compares

It automates the retrieval of diffs and provides a standardized risk-level assessment compared to manual line-by-line inspection.

Compared to similar skills

aif-review side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
aif-review (this skill)04moReviewIntermediate
github-code-review132moReviewAdvanced
reviewing-code218moNo flagsIntermediate
reviewing-nextjs-16-patterns118moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry