github-code-review

Coordinate multi-agent code reviews for GitHub pull requests.

4.4k|580|Updated Nov 19, 2025
One-click install
npx skills add https://github.com/ruvnet/ruvector --skill github-code-review-ruvnet
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: github-code-review
Source: https://github.com/ruvnet/ruvector/tree/main/.claude/skills/github-code-review
Command: npx skills add https://github.com/ruvnet/ruvector --skill github-code-review-ruvnet

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill automates AI-assisted code reviews by coordinating multiple specialized agents to analyze changes, enforce standards, and surface actionable feedback, significantly reducing cycle times.

Core Features & Use Cases

  • Multi-Agent Review System: Deploy specialized agents to review changes in parallel for security, performance, architecture, style, and accessibility.
  • PR-Based Workflows: Seamlessly integrate with GitHub CLI to initialize reviews, post updates, and apply quality gates during PRs.
  • Automated Comment Generation: Produce contextual inline comments and high-level summaries for stakeholders.
  • CI/CD Integration: Tie reviews into automated pipelines to gate merges based on predefined quality gates.

Quick Start

Use the github-code-review skill to initialize a swarm for PR 123 and post results to the PR: gh pr view 123 --json files,diff | npx ruv-swarm github review-init --pr 123 gh pr comment 123 --body "🔍 Multi-agent code review 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?

Automate code reviews for GitHub pull requests by orchestrating a multi-agent swarm to analyze PR diffs. The system delegates review tasks to specialized agents for security, performance, and architecture, then posts actionable inline comments and summaries directly to the PR via GitHub CLI.

Can I use multiple AI agents to review security and performance in a PR?

Yes, you can use multiple AI agents to review security, performance, architecture, style, and accessibility in a PR. The swarm framework deploys these specialized agents in parallel to analyze changes and consolidate findings into actionable feedback.

How do I integrate automated PR reviews into CI/CD pipelines?

Integrate automated PR reviews into CI/CD pipelines by applying predefined quality gates during the pull request process. The swarm framework evaluates consolidated findings from specialized agents to gate merges based on your configured quality standards.

What is the best way to generate inline review comments on a GitHub PR?

The best way to generate inline review comments on a GitHub PR is using an AI-powered multi-agent system. It analyzes PR diffs and produces contextual inline comments alongside high-level summaries for stakeholders, which are posted directly using GitHub CLI.

Does multi-agent code review work for large pull requests?

Yes, multi-agent code review works for large pull requests. The system applies across PRs of all sizes by delegating analysis to specialized agents that review changes in parallel, ensuring comprehensive coverage regardless of diff size.

How do I initialize a swarm for a specific GitHub PR review?

Initialize a swarm for a specific GitHub PR review by piping the PR diff data from GitHub CLI into the review-init command. This triggers the multi-agent analysis and allows you to post the review results directly back to the PR.