Agent skill · Code Review & Quality

github-code-review

Comprehensive GitHub code review with AI-powered swarm coordination

rUv71,307★ · +1,002/wk · 3 repos on radarProfile →
claude-codecodexMIT
Install
npx skills add ruvnet/ruflo --skill github-code-review --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 25 KB
Bundled scripts: none
Version: 1.0.0
Declared author: Claude Code Flow
Path: .agents/skills/github-code-review/SKILL.md
Open the folder on GitHub →
Where it comes from
Source: ruvnet/ruflo
Stars: 67,015 · +629 this week
Language: TypeScript
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Deploy specialized AI agents to perform comprehensive code reviews on GitHub PRs, coordinating via a swarm to analyze security, performance, style, architecture, and accessibility, and enforce quality gates.

How it works

  • Initializes a review swarm for a PR using commands like gh pr view and npx ruv-swarm github review-init with --pr, --pr-data, --diff, --agents, and --depth.
  • Uses specialized agents (security, performance, architecture, style, accessibility) to perform domain-specific checks, each invoked via ruv-swarm review-* commands and relevant PR data (files, diff, context).
  • Posts findings and decisions back to the PR via gh pr comment, gh pr review, and label updates, including conditional actions (request-changes for critical issues, or comments for non-critical issues).
  • Manages PR-based swarm orchestration, including auto-spawn from PR labels, topology selection by PR size, and swarm status queries.
  • Provides automated workflows, comment generation, and quality gates to enforce security, performance, and architectural standards.

When to use it

  • When a PR requires a coordinated, multi-domain review across security, performance, style, architecture, and accessibility.
  • When automated PR management and swarm-based orchestration are desired to speed up reviews.
  • When enforcing predefined quality gates and status checks tied to review outcomes.

What it can touch

  • Commands and tools: "gh", "npx ruv-swarm", "claude-flow" (via tools requiring), and various PR-related GitHub interactions (pr view, pr diff, pr comment, pr review, pr edit).
  • It references files and PR data via standard GitHub CLI outputs (e.g., --json files, additions, deletions, title, body) and PR diffs.

Caveats

  • Requires installation and availability of tools: "github-cli", "ruv-swarm", and "claude-flow".
  • Behavior depends on swarm availability and PR context; outcomes (e.g., merge decisions) are contingent on configured thresholds and agent results.
  • Contains many sample scripts and templates for command usage and webhook handling; actual execution requires environment support and proper permissions.
From the SKILL.md

# 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 ```bash # 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 ```bash # 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 <details> <summary><strong>Core Features<$strong><$summary> - [Multi-Agent Review System](#multi-agent-review-system) - [Specialized Review Agents](#specialized-review-agents) - [PR-Based Swarm Management](#pr-based-swarm-management) - [Automated Workflows](#automated-workflows) - [Quality Gates & Checks](#quality-gates--checks) <$details> <details> <summary><stro

What's inside
Steps it walks through
  1. 🎯 Quick Start
  2. Simple Review
  3. Complete Review Workflow
  4. 📚 Table of Contents
  5. 🚀 Core Features
  6. Multi-Agent Review System
  7. 🤖 Specialized Review Agents
  8. Security Review Agent
  9. Performance Review Agent
  10. Architecture Review Agent
  11. Style & Convention Agent
  12. 🔄 PR-Based Swarm Management
  13. Create Swarm from PR
  14. Label-Based Agent Assignment
Commands it runs
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"
Get PR context with gh CLI
Initialize comprehensive review
npx ruv-swarm github review-init \
Initialize review swarm with GitHub CLI integration
Start multi-agent review
Post initial review status
More from ruflo
All skills →
About this skill
What does the github-code-review skill do?

Comprehensive GitHub code review with AI-powered swarm coordination

How do I install it?

Run `npx skills add ruvnet/ruflo --skill github-code-review --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From ruvnet/ruflo, a repository with 67,015 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going