Muse:Chain — Development skill for Claude Code
Run a sequential multi-persona chain on a question.
How to install Muse:Chain
Installs to ~/.claude/skills/doanchienthangdev-muse-muse-chain/SKILL.md
mkdir -p ~/.claude/skills/doanchienthangdev-muse-muse-chain && curl -fsSL https://raw.githubusercontent.com/doanchienthangdev/muse/HEAD/commands/muse:chain.md -o ~/.claude/skills/doanchienthangdev-muse-muse-chain/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Muse:Chain does
description: Run a sequential multi-persona chain on a question. Each persona sees the original question plus a 2-3 sentence summary of prior personas' outputs (not full raw text). Supports inline syntax (feynman→socrates→seneca) or preset name (product-decision, code-review, all). Auto-summarizes if the chain grows beyond 5 personas or 30 KB of working context. Produces a synthesis block covering agreement, divergence, and a single next action. Persists to ~/.muse/chains/-
Alternatives in Development
- Katmer Code — Claude Code inside Obsidian — academic research skills, inline diff editing, MCP support 353 ★
- Bug Health Check — Execute the bug-health-inline skill for inline orchestration 172 ★
- Paperclip Plugin Telegram — Bidirectional Telegram bot plugin for Paperclip - push notifications, bot commands, inline approve/reject butt 89 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Muse:Benchmark
Muse persona benchmark — measures distinctiveness, voice discipline, schema compliance, and mode fit across al
Muse:Debate
Run a 3-round adversarial debate between two personas on a question. Round 1 is opening statements, Round 2 is
Bullpen Name
Name your bullpen teammates. Walks through the 64 default personas in groups; user can accept-all or rename in
Synthetic Customer Discovery
A Claude skill for honest synthetic customer discovery: grounded personas, anti-collapse interview rules, and
Proceed With The Recommendation
Execute the agent's prior recommendation list under the 7 Laws — walk in order, route per item, verify, reflec
Kimchi
🌶️ A product-thinking layer for vibe coders — grills a raw idea into build-ready docs through 11 expert perso
Related Agents
Prompt Chainer
PROACTIVELY use this agent for complex multi-step tasks that require sequential prompt execution, workflow man
Council Feynman
Council member. Use standalone for first-principles debugging & explanation testing, or via /council for multi
Feynman Explainer
Decomposes a technical concept into layered explanations using the Feynman technique -- analogy first, mechani