github-code-review

Automate GitHub pull-request reviews with multi-agent analysis and quality gates.

Updated Sep 21, 2025
One-click install
npx skills add https://github.com/bjpl/california_puzzle_game --skill github-code-review-bjpl
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: github-code-review
Source: https://github.com/bjpl/california_puzzle_game/tree/main/.claude/skills/github-code-review
Command: npx skills add https://github.com/bjpl/california_puzzle_game --skill github-code-review-bjpl

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manual code reviews are often slow, inconsistent, and can miss critical issues like security vulnerabilities or performance bottlenecks. This skill deploys specialized AI agents to perform comprehensive, intelligent code reviews.

Core Features & Use Cases

  • Multi-Agent Review System: Deploy specialized AI agents (security, performance, architecture, style, accessibility) for parallel, comprehensive analysis.
  • Automated PR Management: Integrate with GitHub CLI to initialize review swarms from PRs, post intelligent comments, and enforce quality gates.
  • Context-Aware Learning: Agents learn from past reviews and project context to provide more accurate and relevant suggestions.
  • Quality Gate Enforcement: Define and enforce quality thresholds for security, performance, and code coverage, blocking merges on critical issues.
  • Use Case: Automate the review of a security-critical pull request by deploying a security review agent to identify vulnerabilities, a performance agent to analyze impact, and an architecture agent to evaluate design patterns, all coordinating to provide a comprehensive, actionable review.

Quick Start

Initialize a review swarm for a given Pull Request (PR) by providing its files and diff. Then, post an initial comment to the PR indicating that a multi-agent code review has been initiated.

Frequently Asked Questions about github-code-review

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

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

Automated code reviews use AI agents to analyze PRs across security, performance, architecture, style, and accessibility dimensions in parallel. Initialize a review swarm by providing PR files and diffs, then agents coordinate to post intelligent comments and enforce quality gates without manual intervention.

Can I use AI agents to review pull requests for security vulnerabilities?

Yes. Specialized security agents analyze PRs to identify vulnerabilities as part of a multi-agent review system. They coordinate with performance and architecture agents to provide comprehensive, actionable feedback and can block merges on critical security issues through quality gate enforcement.

What's the best way to enforce code quality standards across pull requests?

Quality gates define and enforce thresholds for security, performance, and code coverage, blocking merges when critical issues arise. Multi-agent analysis provides consistent, intelligent feedback aligned with your project's standards, replacing manual review bottlenecks.

How do AI code reviews work with GitHub CLI?

The skill integrates with GitHub CLI to initialize review swarms directly from PRs, post review comments automatically, and manage PR state based on quality gate results. This enables end-to-end automation from PR detection through feedback delivery.

Can code review agents learn from past reviews in my project?

Yes. Context-aware learning allows agents to learn from your project's history and past reviews, enabling more accurate and relevant suggestions tailored to your codebase's patterns and standards over time.

What issues can automated code reviews detect?

Parallel agent analysis detects security vulnerabilities, performance bottlenecks, architecture misalignments, style violations, and accessibility issues. Specialized agents coordinate findings into comprehensive reviews that capture problems manual reviewers might miss.