Github Code Review

This deploys multiple specialized AI agents to review your PRs in parallel, each focused on a different concern like security, performance, or architecture. You feed it PR data from the GitHub CLI and it coordinates a swarm of reviewers that can block on critical security issues, suggest optimizations, or auto-fix style violations. The label-based agent assignment is smart: tag something "security" and it automatically spawns authentication and audit agents. Best for teams that want deeper code review than linters provide but don't have bandwidth for manual deep dives on every PR. The multi-agent approach means you get security, performance, and architecture feedback simultaneously instead of sequentially.

skills.sh installs: 1.3K
GitHub stars: 81.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ruvnet/ruflo --skill github-code-review --agent claude-code

Installs into .claude/skills of the current project.

Files

GitHub Code Review Skill

AI-Powered Code Review: Deploy specialized review agents to perform comprehensive, intelligent code reviews that go beyond traditional static analysis.

🎯 Quick Start

Simple Review

# Initialize review swarm for PR
gh pr view 123 --json files,diff | npx ruv-swarm github review-init --pr 123

# Post review status
gh pr comment 123 --body "🔍 Multi-agent code review initiated"

Complete Review Workflow

# Get PR context with gh CLI
PR_DATA=$(gh pr view 123 --json files,additions,deletions,title,body)
PR_DIFF=$(gh pr diff 123)

# Initialize comprehensive review
npx ruv-swarm github review-init \
  --pr 123 \
  --pr-data "$PR_DATA" \
  --diff "$PR_DIFF" \
  --agents "security,performance,style,architecture,accessibility" \
  --depth comprehensive

📚 Table of Contents

Core Features<$strong><$summary>

Multi-Agent Review System

Specialized Review Agents

PR-Based Swarm Management

Automated Workflows

Quality Gates & Checks

<$details>

SKILL.md on GitHub