Multi Agent Brainstorming

If you've ever had a design fall apart in production because nobody asked the hard questions early, this formalizes that missing step. It runs a gated peer review process where one agent designs and four specialized agents (skeptic, constraint guardian, user advocate, arbiter) review in sequence with hard scope limits. No parallel brainstorming chaos, no feature creep during review. Each objection gets logged and resolved explicitly before you can exit. It's heavyweight by design, so save it for architecturally significant decisions where the cost of being wrong is high. The mandatory decision log alone makes it worth considering for anything you'll need to defend later.

Install to Claude Code

npx -y skills add sickn33/antigravity-awesome-skills --skill multi-agent-brainstorming --agent claude-code