agentleFS
Sign inStart free
OrYaminOrYamin/room/skill/SKILL.md

room

Skill0 starsChanged 7 months agoMITView on GitHub

Start a multi-agent discussion room where several Claude agents with different expert personas collaborate, debate, and plan together. Use when the user wants multiple perspectives on a decision, wants to explore trade-offs from different viewpoints, or wants a simulated planning meeting / design review. Triggers include phrases like "get multiple opinions", "discuss with a team", "simulate a planning meeting", "have experts debate", "what would different stakeholders think", or any /room invocation.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. Rudywizz/rudywizz-motion★ 4same name
    2. slonana-labs/agichan★ 4same name
    3. MarkDonish/round-table-workspace★ 2same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Do NOT cd before invoking.

    line 44
  2. Distinctive:

    If the bundle errors out, surface the stderr to the user — do not retry silently.

    line 52

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Room skill

You have been invoked as /room. A compiled Node.js bundle does all the actual multi-agent orchestration. Your job is just to translate the user's natural language arguments into one JSON config line and exec the bundle via Bash.

Step 1 — parse $ARGUMENTS

Build a single-line JSON object with these fields (omit any field the user did not specify so defaults apply):

  • goal (string, required) — the discussion topic. Take everything that isn't a flag. If the user typed only flags, ask them for the goal first.
  • method ("round-robin" | "popcorn" | "orchestrator", default round-robin). Accept synonyms: rr→round-robin, pop→popcorn, orch/boss→orchestrator.
  • agents (integer, default 3) — number of persona agents.
  • maxTurns (integer, default 12).
  • threshold (float 0..1, default 0.85) — consensus confidence required to stop early.
  • model (string, optional) — override the heavy model for persona turns.
  • personas (array of {name, description}, optional) — if omitted, the bundle auto-generates personas tailored to the goal.

Step 2 — run the bundle

Execute via the Bash tool, passing the JSON as a single argv arg. Use single quotes around the JSON and escape any inner single quotes:

node ~/.claude/skills/room/room.js '<json-config>'

The bundle streams persona turns, router/orchestrator/decision events, and a final synthesis to stdout. Relay the output back to the user verbatim — do not paraphrase the discussion.

Step 3 — working directory

Do NOT cd before invoking. The bundle reads process.cwd() at startup and injects it into each persona's prompt so they can ground their points in the user's current repo via Read/Glob/Grep.

Notes

  • Persona agents have read-only tools only (Read, Glob, Grep, WebSearch, WebFetch). They cannot modify files.
  • If the bundle errors out, surface the stderr to the user — do not retry silently.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free