소개
Multi-Agent Brainstorming transforms single-agent designs into robust, production-ready solutions by simulating a formal peer-review process within Claude. By assigning specific, non-overlapping roles—such as the Skeptic, Constraint Guardian, and User Advocate—this skill surfaces hidden assumptions, identifies failure modes, and enforces non-functional constraints before implementation. It provides a gated, sequential workflow that prevents premature convergence and ensures high-stakes technical decisions are thoroughly stress-tested and documented.
