RedTeam

This deploys 32 parallel adversarial agents to stress test your arguments, plans, or architectures. It breaks content into atomic claims, attacks from expert perspectives (engineers, architects, pentesters, even interns), then produces both a steelman version of your argument and an 8-point counter-argument designed to destroy it. Use it when you need genuine critique before a decision matters or when you're too close to your own idea to see the fatal flaw. The adversarial validation workflow pits competing approaches against each other to synthesize better solutions. It's aggressive by design, which means you'll either strengthen your position or realize you need to pivot before it's expensive.

Install to Claude Code

npx -y skills add danielmiessler/personal_ai_infrastructure --skill RedTeam --agent claude-code