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.

skills.sh installs: 1.1K
GitHub stars: 43.1K
last updated: Jul 14, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

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.

Distinguish actual independently invoked reviewers from one model simulating roles; never claim independent consensus from a role-play. Use only available host agents within authorized delegation scope. Set a maximum review/revision budget and end with APPROVED, REVISE or REJECT plus unresolved issues if convergence fails; missing reviewers cannot be counted as invoked. This review does not authorize implementation or safety certification.