brainstorm

Generates ranked design alternatives via adversarial debate among three specialized agents.

Updated May 7, 2026
One-click install
npx skills add https://github.com/tmalcolm-0607/mad-council-claw --skill brainstorm-tmalcolm-0607
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: brainstorm
Source: https://github.com/tmalcolm-0607/mad-council-claw/tree/main/.claude/skills/brainstorm
Command: npx skills add https://github.com/tmalcolm-0607/mad-council-claw --skill brainstorm-tmalcolm-0607

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Single-perspective brainstorming often misses critical risks, hidden assumptions, and alternative approaches. This Skill brings together three adversarial agents—an Advocate, a Skeptic, and an Architect—to surface diverse perspectives and strengthen ideas before committing to them.

Core Features & Use Cases

  • Adversarial Debate: Three persistent agents challenge ideas from different angles, exposing blind spots and failure modes.
  • Structured Synthesis: The orchestrator ranks angles by feasibility, lift, and blast radius, then presents ranked options to the user.
  • Use Case: When evaluating whether to migrate from REST to GraphQL, the Skill explores trade-offs, identifies risks, and recommends a direction with confidence levels.

Quick Start

Use the brainstorm skill to explore multiple perspectives on migrating your API from REST to GraphQL.

Frequently Asked Questions about brainstorm

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

FAQPage Schema
What is adversarial brainstorming for architecture decisions?

Adversarial brainstorming for architecture decisions is a structured debate method where specialized agents challenge ideas from different angles to surface blind spots, identify risks, and strengthen technical direction before committing.

How do I evaluate whether to migrate my API from REST to GraphQL?

To evaluate an API migration from REST to GraphQL, use a multi-perspective brainstorming skill to explore trade-offs through adversarial debate, identify failure modes, and recommend a direction with ranked confidence levels.

Do I need a specific environment to run multi-agent brainstorming?

Yes, multi-agent brainstorming requires a Claude Code environment with experimental agent teams enabled and access to subagent spawning tools to generate ranked design alternatives through structured adversarial debate.

What's the best way to explore multiple valid approaches for strategic direction setting?

The best way to explore strategic direction is to deploy an orchestrator that ranks design alternatives by feasibility, lift, and blast radius, synthesizing inputs from persistent adversarial agents like an Advocate, Skeptic, and Architect.

Why does single-perspective brainstorming miss critical risks in problem exploration?

Single-perspective brainstorming misses critical risks because it lacks adversarial challenge, often hiding assumptions and failure modes that structured synthesis and multi-agent debate would otherwise expose.