agentleFS
hyh0620hyh0620/ai-hair-salon-agent/.github/skills/run-demo/SKILL.md

run-demo

Skill0 starsChanged 4 months agoMITView on GitHub

Run the verified five-minute AI Hair Salon Agent interview demo using live candidates returned by the configured demo environment.

  • Reads credentials
  • Sends data out

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. NVIDIA/xr-ai★ 104same name
    2. spantail/spantail★ 4same 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 repository5 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, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    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:

    Use a controlled demo database and ensure MCP Knowledge Service has already ingested salon_knowledge.

    line 10
  2. Distinctive:

    Keep MCP failure injection and authentication replay demonstrations as optional Runbook flows, not part of the default five-minute demo.

    line 30
  3. Distinctive:

    If consultation returns 503, check MCP environment variables and collection ingestion.

    line 42
  4. Distinctive:

    If no future candidate is returned, query another future period or rebuild the controlled demo database.

    line 43
  5. Distinctive:

    If the weather context is unavailable, the booking should still succeed and simply omit the weather reminder.

    line 44

≈ “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

Run Demo

Pipeline

  1. Use a controlled demo database and ensure MCP Knowledge Service has already ingested salon_knowledge.
  2. Configure the MCP interpreter, module, working directory and Collection, then start FastAPI. Its lifespan starts and manages the MCP stdio child process:
    python -m uvicorn app:app --host 127.0.0.1 --port 8000 --no-proxy-headers
  3. Check health:
    curl http://127.0.0.1:8000/health
  4. In the chat, enter 明天下午找擅长冷棕色的老师 and use the actual future candidates returned by the system. Do not assume a fixed date or stylist ID.
  5. Select one returned option, confirm the summary, and verify that the response includes a real appointment_id. No database write should occur before final confirmation.
  6. For an optional conflict demonstration, reuse the just-created stylist and time from the returned result with another test owner. Expect a conflict; do not edit the database to create it.
  7. Query consultation:
    curl -X POST http://127.0.0.1:8000/api/consultation/query \
      -H "Content-Type: application/json" \
      -d '{"question":"染发前后有什么注意事项?"}'
  8. Confirm the response contains Citations and explain that MCP is the tool protocol while RAG is the retrieval pipeline.
  9. .env.example already enables keyless Open-Meteo for Shanghai. Confirm weather appears only after the conversational booking commit; do not toggle it off after the demo. Hermetic verification blocks real weather calls.
  10. Keep MCP failure injection and authentication replay demonstrations as optional Runbook flows, not part of the default five-minute demo.

Output

  • Health JSON.
  • Dynamically selected appointment confirmation with a real ID.
  • Optional conflict result based on the same returned candidate.
  • Consultation answer with sources.
  • Post-commit weather reminder when the optional service is available.

Failure Handling

  • If consultation returns 503, check MCP environment variables and collection ingestion; FastAPI normally owns the stdio child process.
  • If no future candidate is returned, query another future period or rebuild the controlled demo database. Do not hard-code a replacement date or stylist.
  • If the weather context is unavailable, the booking should still succeed and simply omit the weather reminder.
  • See docs/DEMO_RUNBOOK.md for setup, failure injection and deep authentication validation.

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.