Council

danielmiessler/personal_ai_infrastructure

When you need multiple expert perspectives actually responding to each other rather than just collecting independent opinions, this orchestrates structured debates where specialized agents challenge and build on each other's points across three rounds. Unlike RedTeam which purely attacks an idea, Council is collaborative adversarial, meaning agents debate to find the best path forward while you see the full transcript of who said what. It's genuinely fast because agents run in parallel within each round. Use the full Debate workflow for architectural decisions or security reviews, Quick workflow for sanity checks. The real value is in watching how positions evolve when experts have to respond to each other's actual arguments instead of talking past each other.

skills.sh installs: 131
GitHub stars: 14.6K
last updated: Jun 3, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Council

Runs a multi-agent debate. Topic-briefed members discuss a topic over rounds, respond to each other's actual points, and surface insights through real intellectual friction. You get a visible round-by-round transcript plus a synthesis. DEBATE runs three rounds; QUICK runs one for a fast perspective check.

One model gives one frame and one set of blind spots, and "pros and cons" gives a flat list with no one pushing back; distinct experts who disagree on the merits expose the weak parts of an idea before you commit.