dyad:swarm-pr-review

Orchestrate a three-teammate Claude Code swarm to analyze GitHub PR diffs and post a consensus summary.

21.2k|2.6k|Updated Apr 11, 2025
One-click install
npx skills add https://github.com/dyad-sh/dyad --skill dyad-swarm-pr-review
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dyad:swarm-pr-review
Source: https://github.com/dyad-sh/dyad/tree/main/.claude/skills/swarm-pr-review
Command: npx skills add https://github.com/dyad-sh/dyad --skill dyad-swarm-pr-review

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill coordinates a multi-agent PR review workflow to ensure thorough, balanced feedback across correctness, code health, and user experience, reducing time to merge and improving review quality.

Core Features & Use Cases

  • Automated, multi-perspective PR review with specialized teammates (correctness, code health, UX) that discuss and reach consensus.
  • Generates a final summary with inline comments and a merge verdict for GitHub PRs.
  • Applicable to PRs of varying size and complexity requiring thorough validation and traceable review history.

Quick Start

Invoke swarm-pr-review on a GitHub PR to start the three-teammate review, fetch the diff, and post a summarized verdict.

Frequently Asked Questions about dyad:swarm-pr-review

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

FAQPage Schema
How do I automate GitHub PR reviews with multiple AI agents?

Automated GitHub PR reviews use a three-teammate AI agent swarm to analyze diffs, discuss correctness, code health, and UX, then post a final summary with inline comments and a merge verdict.

How does a swarm-based code review process work?

A swarm-based code review orchestrates specialized AI teammates that fetch the pull request diff, evaluate it from correctness, code health, and UX perspectives, reach consensus, and post a summarized verdict to GitHub.

Can I use multi-agent AI review for pull requests of varying size and complexity?

Multi-agent AI review applies to pull requests of varying size and complexity, orchestrating teammates to validate diffs and build team-wide consensus for thorough validation and traceable review history.

What is the best way to get inline PR comments and a merge verdict from an AI team?

The best way to get inline PR comments and a merge verdict is orchestrating a multi-agent swarm that fetches diffs, compiles findings from correctness, code health, and UX perspectives, and posts a final summary to GitHub.

Do I need to manually fetch diffs before starting an automated PR review?

No, you do not need to manually fetch diffs; the automated PR review orchestration fetches the pull request diff itself before the three-teammate swarm analyzes it and posts the final summary.

Why use a three-teammate AI swarm instead of a single AI agent for code review?

A three-teammate AI swarm ensures thorough, balanced feedback across correctness, code health, and user experience by simulating team-wide discussion and consensus-building, reducing time to merge compared to a single agent.