Skills
.Work. You
Rest

debate-team

Community

Cross-model adversarial review for plans & PRs.

Software Engineering#testing#quality assurance#code review#llm#ai agents#adversarial review
Authorsumrae412
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill automates a rigorous, multi-model adversarial review process for implementation plans and code changes, ensuring higher quality artifacts by leveraging diverse AI perspectives.

Core Features & Use Cases

  • Tri-Model Debate: Engages DeepSeek Bug-Hunter, GPT-4o Architecture, and Haiku Style critics to identify flaws from different angles.
  • Automated Review: Assesses complexity, generates proposals, dispatches critics in parallel, synthesizes findings, and presents a changelog.
  • Use Case: Before merging a complex feature PR, submit the diff to the debate-team skill. It will simulate a team of specialized AI reviewers to catch bugs, architectural issues, and UI inconsistencies that a single reviewer might miss.

Quick Start

Use the debate-team skill to review the attached implementation plan for the new user authentication module.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: debate-team
Download link: https://github.com/sumrae412/claude-skills/archive/main.zip#debate-team

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.