Multi Agent Brainstorming
sickn33/antigravity-awesome-skillsA team of AI agents works together to check a design before it is built. Each agent has a special job. One agent is the designer. Another agent looks for problems. One agent checks limits like speed and cost. Another speaks for the user. A final agent decides when the design is good enough.
This process finds hidden assumptions and failure modes early. It stops bad ideas from growing into big mistakes. The review happens step by step. No agent can go beyond its role. This keeps the review fair and focused.
Anyone who plans a new feature or system can use this skill. It turns a single design into a tested and validated plan. Teams save time by catching issues before coding starts.
Add Multi Agent Brainstorming skill to your workflow
Global
mkdir -p ~/.claude/skills/multi-agent-brainstormingProject
mkdir -p .claude/skills/multi-agent-brainstormingSource Repository
More Code Review & Quality Claude Code Skills
Improve Codebase Architecturemattpocock/skills
Scan your codebase for architecture improvements with visual reports and pick one to refactor
Web Design Guidelinesvercel-labs/agent-skills
Review your UI code for compliance with web interface guidelines
Caveman Reviewjuliusbrussee/caveman
Ultra-compressed one-line code review comments that cut noise
Zoom Outmattpocock/skills
Get a big picture view of your code with a simple map of modules and callers
Codebase Designmattpocock/skills
Create deep modules with tiny interfaces and lots of hidden logic for testability
Requesting Code Reviewobra/superpowers
Catch code issues early with focused automated reviews before every merge
Request Refactor Planmattpocock/skills
Plan safe code refactors with tiny commits and clear GitHub issues
Receiving Code Reviewobra/superpowers
Think first, then code. Verify feedback before making changes. Stay objective