debate

Coordinate adversarial debate rounds and synthesize a final recommendation.

1|Updated Mar 30, 2026
One-click install
npx skills add https://github.com/lleontor705/cortex-ia --skill debate-lleontor705
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: debate
Source: https://github.com/lleontor705/cortex-ia/tree/main/internal/assets/skills/debate
Command: npx skills add https://github.com/lleontor705/cortex-ia --skill debate-lleontor705

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Adversarial debate moderator orchestrates competing positions to surface the strongest solution through structured argumentation.

Core Features & Use Cases

  • Define 2-4 competing positions with clear theses and evaluation criteria.
  • Spawn defender agents for each position and manage three debate rounds: Opening Argument, Rebuttal, Final Defense.
  • Synthesize surviving points into a final recommendation and preserve dissenting perspectives for transparency.
  • Persist debate results for traceability and audit.

Quick Start

Initiate a 2-4 position debate and run all three rounds (Opening Argument, Rebuttal, Final Defense) to produce a synthesis and recommendation.

Frequently Asked Questions about debate

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

FAQPage Schema
How do I use adversarial analysis to evaluate competing architecture decisions?

Adversarial analysis evaluates competing architecture decisions by spawning dedicated defender agents for each position, running structured rounds of opening arguments, rebuttals, and final defenses to synthesize a final recommendation.

What is structured argumentation for codebase decision-making?

Structured argumentation for codebase decision-making is a process where 2-4 competing positions are defined with clear theses and evaluation criteria, then debated across multiple rounds to synthesize a final recommendation.

How do I set up a multi-agent debate for software engineering solutions?

To set up a multi-agent debate, define a topic, establish 2-4 competing positions, and provide tooling for p2p messaging and persistence so dedicated defender agents can manage rounds and synthesize results.

Does adversarial debate preserve dissenting perspectives after synthesis?

Yes, adversarial debate preserves dissenting perspectives after synthesis. It synthesizes surviving points into a final recommendation while explicitly retaining dissenting viewpoints for transparency and audit.

Can I run an adversarial debate without dedicated defender agents for each position?

No, dedicated defender agents for each position are required. The adversarial debate mechanism relies on these agents to independently manage opening arguments, rebuttals, and final defenses before synthesis.