autoconference:debate
CommunityPressure-test ideas in an adversarial debate.
Education & Research#multi-agent#debate#adversarial reasoning#pro-con#argument evaluation#judge scoring#literature thinking
Authorwjgoarxiv
Version1.0.0
Installs0
System Documentation
What problem does it solve?
It helps you evaluate competing viewpoints by running a structured pro/con debate with an impartial judge, turning disagreement into scored, actionable critique.
Core Features & Use Cases
- Adversarial 2-researcher debate: Runs two independent agents arguing opposite positions with strict role separation.
- Round-based challenge + rebuttal: Forces precise attacks on the opponent’s weakest claim each round, then requires targeted rebuttals.
- Judge-scored outcomes: Produces per-round scores, winner/tie, convergence detection, and a final verdict with unresolved disputes and follow-up recommendations.
- Use Case: Decide which policy, strategy, or technical claim is more convincing by having one side argue for the proposition and the other side argue against it under adjustable evidence strictness.
Quick Start
Tell the AI: "Run an autoconference:debate for the question 'X' with 3 rounds and strict judging, and save the report as debate-report.md."
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 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: autoconference:debate Download link: https://github.com/wjgoarxiv/autoconference-skill/archive/main.zip#autoconference-debate Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.