Multi Agent Brainstorming

Use this skill when a design or idea requires higher confidence, risk reduction, or formal review. This skill orchestrates a structured, sequential multi-agent design review where each agent has a strict, non-overlapping role. It prevents blind spots, false confidence, and premature convergence.

514 stars 146 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI --skill multi-agent-brainstorming
Manual install
git clone --depth 1 https://github.com/Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI.git /tmp/Agent-Skills-4-Vibe-Coding-CLI
mkdir -p ~/.claude/skills
cp -r /tmp/Agent-Skills-4-Vibe-Coding-CLI/.agent/skills/multi-agent-brainstorming ~/.claude/skills/multi-agent-brainstorming

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Multi-Agent Brainstorming (Structured Design Review)

## Purpose

Transform a single-agent design into a **robust, review-validated design**
by simulating a formal peer-review process using multiple constrained agents.

This skill exists to:
- surface hidden assumptions
- identify failure modes early
- validate non-functional constraints
- stress-test designs before implementation
- prevent idea swarm chaos

This is **not parallel brainstorming**.
It is **sequential design review with enforced roles**.

---

## Operating Model

- One agent designs.
- Other agents review.
- No agent may exceed its mandate.
- Creativity is centralized; critique is distributed.
- Decisions are explicit and logged.

The process is **gated** and **terminates by design**.

---

## Agent Roles (Non-Negotiable)

Each agent operates under a **hard scope limit**.

## 🧠 Knowledge Modules (Fractal Skills)

### 1. [1️⃣ Primary Designer (Lead Agent)](./sub-skills/1-primary-designer-lead-agent.md)
### 2. [2️⃣ Skeptic / Challenger Agent](./sub-skills/2-skeptic-challenger-agent.md)
### 3. [3️⃣ Constraint Guardian Agent](./sub-skills/3-constraint-guardian-agent.md)
### 4. [4️⃣ User Advocate Agent](./sub-skills/4-user-advocate-agent.md)
### 5. [5️⃣ Integrator / Arbiter Agent](./sub-skills/5-integrator-arbiter-agent.md)
### 6. [Phase 1 — Single-Agent Design](./sub-skills/phase-1-single-agent-design.md)
### 7. [Phase 2 — Structured Review Loop](./sub-skills/phase-2-structured-review-loop.md)
Read the full skill on GitHub

Details

Skill name
multi-agent-brainstorming
Path
.agent/skills/multi-agent-brainstorming/SKILL.md
Repo updated
11 June 2026

FAQ

What does the Multi Agent Brainstorming skill do?

Use this skill when a design or idea requires higher confidence, risk reduction, or formal review. This skill orchestrates a structured, sequential multi-agent design review where each agent has a strict, non-overlapping role. It prevents blind spots, false confidence, and premature convergence.

How do I install the Multi Agent Brainstorming skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI --skill multi-agent-brainstorming. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Multi Agent Brainstorming popular?

It lives in Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI, which has 514 GitHub stars and 146 forks.

Related skills

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.