How does this differ from standard AI brainstorming?

While standard brainstorming is generative and open-ended, this skill is a structured, sequential review process that uses constrained agent roles to intentionally critique and stress-test a design.

When is the best time to invoke this skill?

Use this skill during the design phase of a project, specifically when a proposal requires higher confidence, risk reduction, or formal validation before implementation starts.

What agents are involved in the review process?

The process involves a Primary Designer, a Skeptic to identify failures, a Constraint Guardian for technical limits, a User Advocate for usability, and an Arbiter to finalize decisions.

What is the Purpose of the Decision Log?

The Decision Log is a mandatory artifact that tracks all rejected alternatives, raised objections, and final rationales to ensure the design process is transparent and well-reasoned.

Multi-Agent Brainstorming

Name: Multi-Agent Brainstorming
Author: claudiodearaujo

byclaudiodearaujo

Collaboration Tools

Orchestrates a structured, sequential multi-agent design review to surface risks and validate architectures before implementation.

About

This skill transforms single-agent ideas into robust, review-validated designs by simulating a formal peer-review process. It orchestrates a sequential workflow where specialized agents—including a Skeptic, Constraint Guardian, and User Advocate—critique the design under strict, non-overlapping mandates. By enforcing a mandatory Decision Log and explicit arbitration, it prevents blind spots, reduces architectural risk, and ensures high-confidence outcomes for complex technical decisions.

Key Features

Mandatory Decision Log for auditing and rationale
0 GitHub stars
Sequential role-based review orchestration
Arbiter agent for conflict resolution and final approval
Dedicated Skeptic agent for risk identification
Constraint Guardian for performance and security validation

Use Cases

Validating complex system architectures before coding begins
Conducting non-functional requirement reviews for performance and security
Stress-testing high-risk features for hidden assumptions and failure modes

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add claudiodearaujo/izacenter multi-agent-brainstorming

For use in Claude.ai and ChatGPT

Download Skill

GitHub