How does this differ from standard AI brainstorming?

Unlike parallel brainstorming which can lead to chaos, this skill uses a sequential process with constrained roles (like Skeptic and Arbiter) to simulate a professional peer-review environment.

Why is a Decision Log mandatory?

The Decision Log provides a formal audit trail of why specific choices were made, what alternatives were rejected, and how risks identified by the Skeptic were mitigated.

Can this skill help with security and performance?

Yes, the Constraint Guardian agent specifically focuses on non-functional requirements such as security, performance, scalability, and operational costs.

What is the role of the Arbiter in this skill?

The Arbiter acts as the final decision-maker, resolving conflicts between agents, ensuring all objections are addressed, and declaring the design complete based on strict exit criteria.

Multi-Agent Brainstorming

Name: Multi-Agent Brainstorming
Author: claudiodearaujo

byclaudiodearaujo

•

コラボレーションツール

Orchestrates a structured, multi-role design review process to validate architectures and identify potential failure modes.

The Multi-Agent Brainstorming skill transforms single-agent ideas into robust, review-validated designs by simulating a formal peer-review process. It orchestrates a sequential workflow involving specialized agents—a Primary Designer, Skeptic, Constraint Guardian, User Advocate, and Arbiter—each with strict, non-overlapping mandates. This approach prevents blind spots, reduces implementation risk, and ensures that non-functional requirements like security and scalability are stress-tested before a single line of code is written.

主な機能

01Gated exit criteria to ensure all objections are formally resolved

02Rigorous 'Skeptic' role to identify edge cases and YAGNI violations

031 GitHub stars

04Structured sequential review loops with specialized agent roles

05Constraint enforcement for performance, security, and maintainability

06Mandatory Decision Log for tracking trade-offs and rationales

ユースケース

01Conducting formal design reviews for user-facing experience flows

02Validating complex system architectures before implementation

03Stress-testing high-risk design decisions for hidden assumptions

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add claudiodearaujo/sistema-de-narra-o-de-livro multi-agent-brainstorming

For use in Claude.ai and ChatGPT

Download Skill