pr-review-swarm

Coordinate parallel code review specialists to produce a unified PR verdict.

1|Updated Feb 27, 2026
One-click install
npx skills add https://github.com/justsml/ai-team-skills --skill pr-review-swarm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pr-review-swarm
Source: https://github.com/justsml/ai-team-skills/tree/main/legacy/pr-review-swarm
Command: npx skills add https://github.com/justsml/ai-team-skills --skill pr-review-swarm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrate a parallel team of code review specialists — correctness, performance, maintainability, and domain logic — to thoroughly review a PR or branch, then synthesize findings into a unified, actionable review.

Core Features & Use Cases

  • Parallel, multi-dimension PR reviews where specialists independently assess correctness, performance, maintainability, and domain logic.
  • Synthesis of findings into a single prioritized verdict with actionable remediation steps.
  • Suitable for full PR reviews, critical fixes, or post-change audits across large codebases.

Quick Start

Initiate the pr-review swarm on the changed files to produce a unified, multi-specialist verdict.

Frequently Asked Questions about pr-review-swarm

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

FAQPage Schema
How do I automate multi-dimensional code review for pull requests?

Automated multi-dimensional code review coordinates parallel specialists to assess correctness, performance, maintainability, and domain logic, synthesizing findings into a single prioritized verdict with actionable remediation steps.

What is parallel code review and how does it handle large pull requests?

Parallel code review deploys independent specialist agents to assess different dimensions of a PR simultaneously. It scales across large codebases by reading full PR context and consolidating findings into Must Fix, Should Fix, and Nits categories.

Can I run a post-change audit on a branch to check maintainability and performance?

Yes, you can run post-change audits on branches. The review evaluates maintainability and performance alongside domain logic, producing a consolidated verdict and concrete repair suggestions for the changed files.

How do I structure pull request feedback into prioritized categories?

Pull request feedback is structured by synthesizing parallel specialist findings into prioritized categories: Must Fix, Should Fix, and Nits, delivering concrete repair suggestions and a unified remediation plan.

What is the best way to review critical fixes across multiple domain logic areas?

The best way to review critical fixes is using a parallel multi-specialist approach. Independent agents assess domain logic, correctness, and performance, then synthesize actionable findings into a unified review verdict.