review-team

Orchestrate multi-agent PR reviews with adversarial filtering and confidence-rated findings.

Updated Mar 11, 2026
One-click install
npx skills add https://github.com/8GG-Git/Test_Team --skill review-team
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review-team
Source: https://github.com/8GG-Git/Test_Team/tree/main/skills/review-team
Command: npx skills add https://github.com/8GG-Git/Test_Team --skill review-team

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of getting high-quality, critically reviewed feedback on your code changes before merging, reducing the risk of introducing bugs or architectural flaws.

Core Features & Use Cases

  • Adversarial Review: Employs a "Devil's Advocate" agent to challenge findings, ensuring only robust issues are reported.
  • Multi-Agent Collaboration: Utilizes specialist agents (Staff Engineer, QA, Security, Architect) for comprehensive analysis.
  • Use Case: Before merging a critical feature update, run this Skill to get a thorough, multi-faceted review that rigorously vets the code against project standards and potential pitfalls.

Quick Start

Run the review-team skill on the provided pull request URL to initiate an adversarial code review.

Frequently Asked Questions about review-team

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

FAQPage Schema
How does adversarial code review work for pull requests?

Automated PR review employs specialist agents for Staff Engineering, QA, Security, and Architecture to analyze code diffs. A Devil's Advocate agent then challenges these findings to filter out false positives and produce confidence-rated reports.

How do I automate multi-agent PR analysis against project conventions?

To automate multi-agent PR analysis, provide a pull request URL to the review process. It automatically detects tickets and analyzes code diffs against project conventions and ticket acceptance criteria to generate confidence-rated findings.

What is the best way to perform security and architecture checks before merging?

The best way to perform security and architecture checks before merging is using a multi-agent review process. It deploys specialist Security and Architect agents to rigorously vet code changes against project standards and potential pitfalls.

Can I configure the verbosity of automated code review findings?

Yes, automated code review findings support configurable verbosity. You can adjust the output detail level of confidence-rated findings generated by the specialist agents and the Devil's Advocate filtering process.

When do I need an automated Devil's Advocate review for my code diffs?

You need an automated Devil's Advocate review for code diffs when merging critical feature updates. It rigorously vets code against project standards by challenging initial findings, reducing the risk of introducing bugs or architectural flaws.