multi-agent-brainstorming

Installation
Summary

Structured peer-review process using constrained agents to validate designs and surface hidden assumptions before implementation.

  • Five specialized agent roles with hard scope limits: Primary Designer, Skeptic/Challenger, Constraint Guardian, User Advocate, and Integrator/Arbiter, each with explicit permissions and restrictions
  • Sequential review workflow where the designer proposes, then three reviewer agents provide feedback in order, with mandatory Decision Log recording all objections and resolutions
  • Exit criteria enforce completion: Understanding Lock, all reviewers invoked, objections resolved or rejected, and Arbiter approval required before proceeding
  • Prevents idea swarm chaos, hallucinated consensus, and overconfident designs by centralizing creativity while distributing constrained critique
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.


Related skills
Installs
836
GitHub Stars
37.3K
First Seen
Jan 25, 2026