Muse:Debate — Development skill for Claude Code
Run a 3-round adversarial debate between two personas on a question.
How to install Muse:Debate
Installs to ~/.claude/skills/doanchienthangdev-muse-muse-debate/SKILL.md
mkdir -p ~/.claude/skills/doanchienthangdev-muse-muse-debate && curl -fsSL https://raw.githubusercontent.com/doanchienthangdev/muse/HEAD/commands/muse:debate.md -o ~/.claude/skills/doanchienthangdev-muse-muse-debate/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Muse:Debate does
description: Run a 3-round adversarial debate between two personas on a question. Round 1 is opening statements, Round 2 is cross-examination, Round 3 is a framework-voice synthesis noting agreement + disagreement + the question for the user. Requires both personas to have ## Debate positions sections (gracefully degrades if one is missing, with asymmetry flagged in Round 3). Rejects self-debate. Persists to ~/.muse/debates/--vs--.md. allowed-tools: Read, Glob, Bash,
Alternatives in Development
- SuperClaude Framework — A configuration framework that enhances Claude Code with specialized commands, cognitive personas, and develop 22k ★
- Value Prop Statements — Generate value prop statements for marketing, sales, and onboarding 7.8k ★
- Persona Gen — Generate detailed user personas for your product 86 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Claude Council Of Five
Claude Code skill: five personas (Chair, Devil's Advocate, Principles Purist, Outsider, Executor) debate your
Decision Council
Claude skill: a council of independent perspectives (blind round, debate, and a synthesis that takes a stance)
Muse:Chain
Run a sequential multi-persona chain on a question. Each persona sees the original question plus a 2-3 sentenc
Jidoka Debate
Run an adversarial debate (prosecutor/defender/judge) on an analytical or decision question
Muse:Benchmark
Muse persona benchmark — measures distinctiveness, voice discipline, schema compliance, and mode fit across al
Claude Personas
Persistent persona modes for Claude Code: command-controlled personas (solo/parallel), a guided persona creato
Related Agents
Debate Orchestrator
Orchestrate multi-round debates between AI tools. Manages proposer/challenger rounds, builds cross-tool prompt
Proof Auditor
Independent rubric-verdict producer for reasoning deliverables. Runs alongside the incumbent judge; produces a
Consensus Synthesizer
Reads all validator reports, applies consensus-synthesis voting rules, handles disagreements via consensus-dis