pr-review

Coordinate three subagents to review GitHub pull requests for security, regressions, and performance.

2|Updated Apr 11, 2026
One-click install
npx skills add https://github.com/wilsonfaustino/ai-tools --skill pr-review-wilsonfaustino
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pr-review
Source: https://github.com/wilsonfaustino/ai-tools/tree/main/skills/claude-pr-review-setup/assets/skill
Command: npx skills add https://github.com/wilsonfaustino/ai-tools --skill pr-review-wilsonfaustino

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the tedious, inconsistent process of manual pull request reviews by coordinating three specialized subagents to audit code changes for security vulnerabilities, regressions, and performance issues, only activating when explicitly requested to avoid unnecessary overhead during regular development work.

Core Features & Use Cases

  • 3-Parallel Subagent Orchestration: Launches dedicated Security, Regression & Hallucination Detection, and Performance subagents simultaneously to cover all critical review dimensions in a single workflow.
  • Smart Duplicate & Gap Detection: Avoids reposting existing inline comments, deduplicates overlapping findings across agents, and flags files with no review comments for manual verification.
  • Consolidated PR Output: Posts a structured, severity-prioritized review summary directly to the GitHub PR, with actionable recommendations and positive highlights of well-implemented changes.
  • Use Case: When you finish a feature branch and want a comprehensive code review before merging, invoke this skill to get a thorough audit of security risks, unintended code changes, and performance bottlenecks without manual effort.

Quick Start

Ask Claude to review pull request #42 to trigger the multi-agent review workflow that posts a consolidated summary of findings directly to the PR.

Frequently Asked Questions about pr-review

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

FAQPage Schema
How do I automate GitHub pull request code reviews for security and performance issues?

Automated GitHub pull request code reviews use orchestrated subagents to detect security vulnerabilities, regressions, and performance issues simultaneously. This coordinates specialized audits to eliminate manual overhead, posting a consolidated, severity-prioritized summary directly to the PR interface.

How does multi-agent code review detect regressions and security vulnerabilities?

Multi-agent code review detects regressions and security vulnerabilities by launching parallel subagents specialized in security auditing, regression identification, and performance analysis. Each agent audits the code changes independently, and the system deduplicates overlapping findings before posting results.

Can I run a comprehensive security audit on a GitHub PR before merging?

Yes, you can run a comprehensive security audit on a GitHub PR by triggering a multi-agent review workflow. Dedicated subagents analyze code changes specifically for security vulnerabilities and flag them alongside performance bottlenecks in a structured, severity-prioritized output.

What is the best way to avoid duplicate comments during automated PR code reviews?

To avoid duplicate comments during automated PR code reviews, multi-agent workflows implement smart duplicate detection and gap analysis. The system checks for existing inline comments, deduplicates overlapping findings across agents, and flags unreviewed files for manual verification.

Does multi-agent PR review work without additional dependencies?

Multi-agent PR review works without additional dependencies, coordinating its specialized security, regression, and performance subagents natively. It activates only when explicitly requested, ensuring no unnecessary overhead runs during regular development work on your repository.