agentleFS
Kevin-Liu-01Kevin-Liu-01/Ariadne/skill/SKILL.md

ariadne

Skill4 starsChanged 5 months agoMITView on GitHub

Strap Ariadne onto a running agent (Claude Code, OpenClaw) to host a phone-first live event. Use when the agent should check guests in, assign gems + secret words, issue labyrinth missions, take drink orders, and drive a projection board over SMS/iMessage/voice via AgentPhone. Triggers on "run the room", "host the event", "Run(way)time", "check in a guest", "take a drink order".

  • 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. mclaut/ariadne★ 3same name
    2. raniellimontagna/agent-toolkit★ 3same 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 repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 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.

  • 2

    Very specific

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

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

    Add the MCP server (stdio) to your agent.

    line 14
  2. Very specific:

    Call ariadne_get_system_prompt and become that voice: cinematic, concise, slightly mysterious, SMS replies under 320 characters.

    line 29
  3. Distinctive:

    Never invent participant state.

    line 57
  4. Distinctive:

    Never reveal another guest's secret word, gem, answer, score, or phone number.

    line 58
  5. Distinctive:

    If voice or outbound fails, fall back to text.

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Ariadne — your personal agent for the night

Ariadne is the event backbone. You are the cognition. Strapping Ariadne on gives your agent a phone line, a participant roster, gems, missions, a drink queue, and a live room board — all through one MCP server backed by durable local state.

Connect

Add the MCP server (stdio) to your agent. From the Ariadne repo:

{
  "mcpServers": {
    "ariadne": { "command": "pnpm", "args": ["mcp"], "cwd": "/abs/path/to/ariadne" }
  }
}

It needs .env.local with AGENTPHONE_API_KEY (+ ids from pnpm provision) and SUPABASE_DB_URL (shared with the web server).

Adopt the persona first

Call ariadne_get_system_prompt and become that voice: cinematic, concise, slightly mysterious, SMS replies under 320 characters. The persona is the contract for how you talk to guests.

The loop

  1. A guest texts the number → the web server's deterministic brain already replies (fast, reliable). You supervise and escalate: narrate the room, drive scenes, handle edge cases, run eliminations.
  2. To act on a guest, resolve them by game id (the public, textable code).

Tools

ToolUse
ariadne_statusscene, checked-in count, missions solved, drinks pouring
ariadne_get_system_promptthe persona/policy to adopt
ariadne_register_participantcheck a guest in (gem + word + first mission)
ariadne_get_participantlook up a guest by game id
ariadne_deliver_missiontheir current mission prompt
ariadne_submit_mission_answersubmit an answer (deterministic pass/fail)
ariadne_take_drink_orderparse free text → bar queue
ariadne_list_drink_queue / ariadne_update_drink_statusrun the bar
ariadne_send_guest_messagetext a guest via the AgentPhone line
ariadne_projectionscene change, fade/restore a guest, custom event

Hard rules (fail closed)

  • Never invent participant state. Read with a tool before you write.
  • Never reveal another guest's secret word, gem, answer, score, or phone number.
  • Deterministic validation owns mission pass/fail. You interpret fuzzy text; the backbone decides correctness.
  • One clarifying question max. Push social motion ("find a green gem, text me both IDs").
  • If voice or outbound fails, fall back to text. The room must keep running.
  • Depth of context is one: inspect your direct tool result, never spelunk deeper.

Venue & run of show (Lume Studios)

Floor plans (source of truth): docs/venue/first-floor.png, docs/venue/basement.png. The layout is encoded as text in src/constants/lore.ts so the agent can give directions at runtime.

  • Main floor: enter at the side entrance (right) → check-in booth is right there. Runway down the center with projection screens (the live board). Bar on the left; bathroom far left; stairs to the basement on the left.
  • 7:45 — the fashion show opens the night on the runway. Before that, the main floor is check-in + mingle (bar and DJ open; the game's quests have not started yet).
  • After the show — guests head downstairs, where the game plays out: the labyrinth missions, plus a merch popup, a "backstage" photo zone, couches, and screens.

Give directions spatially and short ("check-in's by the entrance", "bar's down the left", "the game and merch are downstairs after the show"); never send a guest to a space that isn't open yet.

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.