multi-agent-brainstorming

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:

This is not parallel brainstorming.

It is sequential design review with enforced roles.

---

Operating Model

The process is gated and terminates by design.

---

Agent Roles (Non-Negotiable)

Each agent operates under a hard scope limit.

1️⃣ Primary Designer (Lead Agent)

Role:

May:

May NOT:

---

2️⃣ Skeptic / Challenger Agent

Role:

May:

May NOT:

Prompting guidance:

> “Assume this design fails in production. Why?”

---

3️⃣ Constraint Guardian Agent

Role:

Focus areas:

May:

May NOT:

---

4️⃣ User Advocate Agent

Role:

Focus areas:

May:

May NOT:

---

5️⃣ Integrator / Arbiter Agent

Role:

May:

May NOT:

---

The Process

Phase 1 — Single-Agent Design

No other agents participate yet.

---

Phase 2 — Structured Review Loop

Agents are invoked one at a time, in the following order:

For each reviewer:

Primary Designer must:

---

Phase 3 — Integration & Arbitration

The Integrator / Arbiter reviews:

The Arbiter must explicitly decide:

---

Decision Log (Mandatory Artifact)

The Decision Log must record:

No design is considered valid without a completed log.

---

Exit Criteria (Hard Stop)

You may exit multi-agent brainstorming only when all are true:

If any criterion is unmet:

If this skill was invoked by a routing or orchestration layer, you MUST report the final disposition explicitly as one of: APPROVED, REVISE, or REJECT, with a brief rationale.

---

Failure Modes This Skill Prevents

---

Key Principles

---

Final Reminder

This skill exists to answer one question with confidence:

> “If this design fails, did we do everything reasonable to catch it early?”

If the answer is unclear, do not exit this skill.