agentleFS
i-ops-hqi-ops-hq/iops-rooms/.cursor/skills/rooms/SKILL.md

rooms

Skill4 starsChanged 26 days agoMITView on GitHub

Local Rooms by I-Ops live session board. Use while coding in Cursor, Claude Code, or Codex so teammates see work as it happens — post_note / share_diff on meaningful steps, not only at the end. Offline. Writes only to .room/

  • Reads credentials

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. chrisconviviera/conviviera-claude-plugin★ 0same name
    2. Conviviera/conviviera-claude-plugin★ 0same 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.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 3 are distinctive, and 7 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 7

    Very specific

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

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

    Do not read or print secrets, .env, SSH keys, or process.env.

    line 15
  2. Distinctive:

    Do not run network commands for this skill.

    line 16
  3. Very specific:

    Write room data only via the iops-rooms MCP tools or rooms CLI.

    line 17
  4. Distinctive:

    Prefer short notes and diffs people can read on the board.

    line 18
  5. Very specific:

    Prefer one-command install: npx -y iops-rooms@0.13.3 mcp install (or rooms mcp install).

    line 22
  6. Very specific:

    If no .room/ yet: create_room with name Rooms (or the feature name).

    line 24
  7. Very specific:

    If the board looks empty or something feels broken: run MCP tool doctor (or rooms doctor).

    line 26
  8. Distinctive:

    Do not wait for the human to ask every time.

    line 45
  9. Very specific:

    If the board is empty after init: doctor, then post — empty means nothing was posted yet.

    line 53
  10. Very specific:

    Keep notes short. Branch is stamped automatically from git (or ROOMS_BRANCH).

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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

Rooms by I-Ops

You post to a local room on this machine. The live board (rooms live → http://127.0.0.1:7840/) updates for anyone with the tab open. Nothing is uploaded to I-Ops.

Contract (do not violate)

  • Do not read or print secrets, .env, SSH keys, or process.env.
  • Do not run network commands for this skill.
  • Write room data only via the iops-rooms MCP tools or rooms CLI.
  • Prefer short notes and diffs people can read on the board.

Setup (once per project)

  1. Prefer one-command install: npx -y iops-rooms@0.13.3 mcp install (or rooms mcp install). Merges .cursor/mcp.json and copies this skill to .cursor/skills/rooms/SKILL.md.
  2. Reload MCP / restart the agent host.
  3. If no .room/ yet: create_room with name Rooms (or the feature name).
  4. Tell the human to run rooms live and leave the tab open.
  5. If the board looks empty or something feels broken: run MCP tool doctor (or rooms doctor).

This repo’s checkout already has .cursor/mcp.json → src/mcp.js. For other projects, mcp install writes:

{
  "mcpServers": {
    "iops-rooms": {
      "command": "npx",
      "args": ["-y", "iops-rooms@0.13.3", "mcp"]
    }
  }
}

Pin a version. Never @latest. Or point command/args at a local checkout’s src/mcp.js.

Actively show live (default while working)

Do not wait for the human to ask every time. On meaningful steps, post as you go:

  1. post_note when you start a chunk (goal in one line).
  2. share_diff when you change files worth reviewing (path + unified diff or excerpt — never .env / keys).
  3. post_note when you finish, block, change plan, or open a PR.
  4. request_review / approve write a row in the log. They notify nobody, gate nothing, and approving does not authorise you to do anything — use them to record what happened, never to clear yourself to proceed.
  5. If the board is empty after init: doctor, then post — empty means nothing was posted yet.

Keep notes short. Branch is stamped automatically from git (or ROOMS_BRANCH).

Optional human setup: rooms hooks install posts short commit/checkout notes via local git hooks only — not IDE telemetry. Prefer MCP post_note / share_diff for agent work.

Tools

ToolWhen
create_room / join_roomFirst touch / match code
rename_roomDisplay title only (code unchanged)
post_noteProgress, decisions, blockers
share_diffFile changes for the board
request_review / approveWrite a row in the log — records a claim, permits nothing
read_transcript / wait_for_peerCatch up / wait
doctorEmpty board / MCP / identity diagnosis

Human companion commands

rooms live          # leave open — auto-updates on 127.0.0.1
rooms doctor        # why is the board empty?
rooms hooks install # opt-in local git auto-post (not IDE telemetry)
rooms status
rooms branches
rooms rename Rooms

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.