multi-mind

Community

Multi-Agent debates to validate PRD and code.

Authorelsolal
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill enables structured, multi-agent debates to challenge PRDs and code decisions, surfacing diverse perspectives and reducing blind spots before implementation.

Core Features & Use Cases

  • Six-Agent Debate Engine: Orchestrates six AI agents (Claude, GPT, Gemini, DeepSeek, GLM, Kimi) to analyze PRDs and code reviews from multiple viewpoints.
  • Five-Round Process: Conducts Critique, Frictions, Targeted Debate, Convergence, and Consensus to produce a comprehensive assessment.
  • Automated Documentation: Generates a final Markdown report and saves it to docs/debates with a structured audit trail, including divergences.
  • Safe & Reproducible: Enforces rules to prevent premature consensus, logs all critiques, and documents trade-offs.

Quick Start

To run Multi-Mind on a target document, provide the file path and mode (prd or review). Example:

  • prd /path/to/PRD.md
  • review /path/to/Review.md

Dependency Matrix

Required Modules

None required

Components

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: multi-mind
Download link: https://github.com/elsolal/Skillz-Claude/archive/main.zip#multi-mind

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.