debate

Orchestrate multi-agent AI debates with configurable roles and real-time fact-checking.

Updated Feb 21, 2026

Search Tags:#fact-checking #multi-agent #argumentation #claude code plugin #ai debate #structured debate

Ready to run

npx skills add https://github.com/colings86/ai-debate --skill debate-colings86

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: debate
Source: https://github.com/colings86/ai-debate/tree/main/plugins/ai-debate/skills/debate
Command: npx skills add https://github.com/colings86/ai-debate --skill debate-colings86

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables structured, multi-agent AI debates on any topic, complete with fact-checking and performance assessment.

Core Features & Use Cases

AI-Powered Debates: Facilitates structured arguments between specialized AI agents (Chair, Debaters, Reporter, Verifier, Audience, Assessor).
Real-time Fact-Checking: The Verifier agent cross-references cited sources during the debate.
Use Case: Set up a debate on the ethics of AI in judicial decisions, with configurable debaters and real-time source verification.

Quick Start

Initiate a debate on the topic 'Should artificial intelligence be used to make judicial decisions?'.

Frequently Asked Questions about debate

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

FAQPage Schema

How do I set up a multi-agent AI debate with real-time fact-checking?▼

To set up a multi-agent AI debate, you define a topic and configure specialized agent roles like Chair, Debaters, and Verifier. The system orchestrates turn-taking and cross-references cited sources during the debate.

Does running a structured AI debate require specific experimental features in Claude Code?▼

Running a structured AI debate requires Claude Code with the Agent Teams experimental feature enabled. You also need system access to bash, python3, and flock to manage the multi-agent orchestration.

Can I customize the personas and roles of agents participating in an AI debate?▼

You can customize the AI debate by configuring persona-driven debaters and assigning specialized roles. The system supports agents like Chair, Reporter, Verifier, Audience, and Assessor for post-debate analysis.

What is the best way to analyze and verify the arguments generated during an AI debate?▼

To analyze and verify AI debate arguments, the system uses specialized agents. The Verifier agent performs real-time fact-checking during the debate, while the Assessor agent conducts post-debate performance evaluation.

What are the limitations of using multi-agent argumentation for complex topics?▼

A limitation of multi-agent argumentation is its dependency on specific system environments. It requires bash, python3, and flock access, and relies on the Claude Code Agent Teams experimental feature to function properly.