From mumo
Multi-model deliberation via mumo's MCP server. Best for contested architecture/product decisions, design reviews, pressure-testing a pre-launch spec, resolving tradeoffs with multiple defensible framings, or explicit user requests for a mumo panel. Requires the mumo MCP server to be connected.
How this skill is triggered — by the user, by Claude, or both
Slash command
/mumo:mumoThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
mumo runs deliberations across multiple AI models. Use it when independent perspectives are useful.
mumo runs deliberations across multiple AI models. Use it when independent perspectives are useful.
The plugin prompts for a mumo API key at install time. If the key is missing or tools return auth errors, direct the user to https://mumo.chat/settings/api-keys to create one (keys start with mmo_live_).
Use mumo for:
Skip for factual questions, syntax help, routine code edits, or tasks where the user has already specified exactly what to build.
create_deliberation with the user's problem. Set application: "Claude Code".wait_for_round with the returned session_id and round_id.append_round if another round would help. Otherwise stop.Snippets are moderator attention. They mark what mattered in the prior round and optionally explain why.
| Type | Reaction |
|---|---|
| KEEP | this seems worth preserving |
| EXPLORE | there's something here |
| CHALLENGE | I'm not convinced |
| CORE | this feels central |
| SHIFT | this changed the frame |
A snippet comment can be reflective, evaluative, clarifying, skeptical, or directive. "This feels like the crux" and "I'm least convinced by this" are valid comments. You do not need an action verb or next-step directive. The quality bar is: is this a genuine, situated reaction to what the model said?
Use the round prompt for broad comments that don't attach to a specific quote. Use snippets for quote-grounded attention.
Avoid huge quote dumps, generic praise repeated across many snippets, or comments that shift participants away from the problem into platform meta. More guidance: reference/snippets.md.
Use this test:
Does this note help participants think about the user's problem, or does it mainly report on the platform, session, or process?
Append another round when:
Stop when:
The panel does not need to converge. Sometimes the right output is a clear map of why the decision remains contested.
| Need | Tool |
|---|---|
| Start a session | create_deliberation |
| Wait for model responses | wait_for_round |
| Add a follow-up round | append_round |
| Recover/read full state | get_session |
| Find prior sessions | list_sessions |
| Confirm model IDs | list_models |
| Check wallet balance | get_credit |
If the user names specific models, call list_models first. Otherwise omit models and let mumo select the panel. More on model selection: reference/model-selection.md.
Pass moderator_name on create_deliberation set to your own model identity (e.g., "Claude Opus 4.6"). The audit trail should reflect who's steering. Don't use the user's name; their identity is already on the session.
Load at most one playbook when it clearly fits:
| Playbook | When |
|---|---|
contested-decision | choosing between options with real tradeoffs |
design-review | reviewing a proposed system, API, plan, or code shape |
uncertainty-expansion | exploring unknowns, stress-testing assumptions |
red-team | finding failure modes, abuse cases, or launch risks |
If none clearly fits, use this kernel only.
These are defaults. If the user prefers more autonomy (e.g., "don't ask before appending" or "always use GPT-5.5 and Gemini"), follow their preferences over this guidance.
Share your panel read with the user, and align on whether to append a round.
More at reference/synthesis.md.
If responses include claim_confidence or snippets[].comment_confidence, these are self-reported and not calibrated across models. Surface the confidence_disclaimer string if displaying scores.
reference/claim-maps.mdreference/snippets.mdreference/model-selection.mdreference/synthesis.mdreference/operating-notes.mdProvides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
npx claudepluginhub mumo-chat/mumo-mcp --plugin mumo