review-code

Analyze code changes for security, performance, and correctness issues.

13|1|Updated Nov 18, 2025
One-click install
npx skills add https://github.com/haacked/review-code --skill review-code-haacked
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review-code
Source: https://github.com/haacked/review-code/tree/main/skills/review-code
Command: npx skills add https://github.com/haacked/review-code --skill review-code-haacked

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires gh, jq, git, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates code reviews, identifying potential issues across security, performance, correctness, and maintainability, significantly speeding up the review process and improving code quality.

Core Features & Use Cases

  • Comprehensive Analysis: Utilizes specialized AI agents for deep dives into security vulnerabilities, performance bottlenecks, code correctness, and maintainability.
  • Parallel Execution: Runs multiple review agents simultaneously for faster feedback (4-6x improvement).
  • Token Efficiency: Optimizes context loading and diff compression for significant token savings.
  • Use Case: Submit a pull request URL or local code changes to get detailed, actionable feedback from specialized AI agents, ensuring your code meets high standards before merging.

Quick Start

Run /review-code to perform a comprehensive review of your local code changes.

Frequently Asked Questions about review-code

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate code reviews for GitHub pull requests?

Automate code reviews by submitting a pull request URL or local changes to trigger specialized AI agents that analyze security, performance, correctness, and maintainability, optionally posting draft reviews directly to GitHub.

What is the best way to review local git changes for security vulnerabilities?

Review local git changes for security vulnerabilities by running the review command, which deploys specialized AI agents to analyze your diff context and identify potential security issues before merging.

Do I need to install gh and jq to analyze code architecture and performance?

Yes, you need gh, jq, and git installed to analyze code architecture and performance, as the AI agents leverage these dependencies to fetch pull request context, parse JSON outputs, and process local diffs.

Can I filter code quality analysis by specific file patterns?

Yes, you can filter code quality analysis by specific file patterns, allowing the AI agents to focus their performance optimization and maintainability checks exclusively on the targeted subset of changed files.

How does AI agent code review compare to manual code review?

AI agent code review runs multiple specialized agents in parallel for faster feedback across security and architecture, whereas manual code review relies on human reviewers sequentially checking diffs, which is slower and less consistent.

Can I review a specific commit range or branch instead of local changes?

Yes, you can review a specific commit range or branch instead of local changes by passing the appropriate commit references, allowing the AI agents to analyze the targeted diff for correctness and testing gaps.