skills.rest
sumrae412
sumrae412COMMUNITY
Explore all skills by this author →
GitHub

debate-team

Orchestrate multi-agent adversarial reviews of implementation plans and code diffs.

2|Updated Feb 17, 2026
Search Tags:#testing#quality assurance#code review#llm#ai agents#adversarial review
One-click install
npx skills add https://github.com/sumrae412/claude-skills --skill debate-team
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: debate-team
Source: https://github.com/sumrae412/claude-skills/tree/main/debate-team
Command: npx skills add https://github.com/sumrae412/claude-skills --skill debate-team

SYSTEM DOCUMENTATION & REQUIREMENTS

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

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.

Frequently Asked Questions about debate-team

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

FAQPage Schema
What is cross-model adversarial review for code diffs and implementation plans?▼

Adversarial review dispatches specialized AI agents to critique software artifacts from security, architecture, and style perspectives, synthesizing findings into a comprehensive changelog for higher quality assurance.

How do I automate multi-agent code review for a pull request?▼

Submit your PR diff to trigger automated assessment of artifact complexity, parallel dispatch of AI critics, synthesis of findings, and changelog creation for comprehensive quality assurance.

Can I use AI agents to find security bugs in an implementation plan?▼

Yes, the DeepSeek Bug-Hunter AI agent specifically critiques implementation plans and code diffs to identify security flaws and bugs during the adversarial review process.

What is the best way to catch architectural issues in a feature diff?▼

Leveraging the GPT-4o Architecture critic during an adversarial review identifies structural flaws in feature diffs from a dedicated architectural perspective before merging.

Does adversarial code review work for UI and style inconsistencies?▼

Yes, the Haiku Style AI agent evaluates artifacts during the adversarial review process to catch UI and style inconsistencies alongside security and architectural flaws.

Related Skills

Explore More Software Engineering Skills→
jcolanojcolano
1

sparc-methodology

Coordinate multi-agent software development across the 17 SPARC modes.

Community
Advanced
brsblbrsbl
14

review

Analyze code changes to identify bugs and quality issues.

Community
Advanced
DevelopersGlobalDevelopersGlobal
65

ci-cd-pipelines

Automate CI/CD pipelines with quality gates and deployment processes.

Official
Advanced
beyonaibeyonai
45

cross-modal-review

Orchestrate a secondary AI model review to validate code changes.

Community
Advanced