github-code-review

Coordinate multi-agent swarm reviews on GitHub pull requests.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/wedosoft/project-a --skill github-code-review-wedosoft
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: github-code-review
Source: https://github.com/wedosoft/project-a/tree/main/.claude/skills/github-code-review
Command: npx skills add https://github.com/wedosoft/project-a --skill github-code-review-wedosoft

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Multi-agent GitHub code reviews with swarm coordination, automated PR management, security checks, and quality gates.

Core Features & Use Cases

  • Swarm-based PR review with specialized agents (security, performance, style, architecture).
  • Automated fixes and comments; integration with CI checks.
  • Context-aware reviews and learning from history.

Quick Start

Simple: gh pr view 123 --json files | npx ruv-swarm github review-init --pr 123.

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 on GitHub pull requests?

Automate code reviews by coordinating multiple specialized AI agents through swarm orchestration on GitHub PRs. This Skill leverages PR data, file diffs, and metadata to run parallel reviews across security, performance, architecture, style, and accessibility dimensions, delivering fast feedback without manual inspection.

Can I integrate automated code review with GitHub CI checks and quality gates?

Yes. This Skill integrates with GitHub CLI and CI workflows to enforce quality gates, apply automated fixes, and post actionable comments directly on PRs. It coordinates swarm reviews with CI metadata to block merges when quality thresholds fail.

What's the best way to review pull requests across multiple dimensions like security and performance?

Use swarm-based multi-agent review to delegate specialized analysis: one agent handles security, another performance, another architecture, style, and accessibility. Swarm coordination orchestrates these agents in parallel, then consolidates findings into a single actionable review faster than sequential review.

Do I need GitHub CLI and additional tools to use multi-agent PR reviews?

Yes. This Skill requires GitHub CLI for PR data access, ruv-swarm for agent orchestration, and claude-flow for workflow management. These dependencies enable PR context ingestion, swarm initialization, and automated PR actions like commenting and status updates.

How does this approach differ from manual code review or single-agent analysis?

Swarm-based review runs specialized agents in parallel rather than sequentially, covering security, performance, architecture, style, and accessibility simultaneously. This delivers comprehensive feedback faster and catches cross-cutting issues a single reviewer might miss.

Can this automate fixes and enforce quality standards on every PR?

Yes. The Skill automates PR management by generating fixes, posting comments, and enforcing quality gates. Context-aware reviews learn from PR history, allowing consistent standards and automated remediation before merge decisions.