agentleFS
hyh0620hyh0620/ai-hair-salon-agent/.github/skills/verify-project/SKILL.md

verify-project

Skill0 starsChanged 4 months agoMITView on GitHub

Run the release verification checklist for AI Hair Salon Agent.

  • Reads credentials

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. cm-wada-yusuke/claude-code-product-workshop-kit★ 18same name
    2. jeremymcs/skills★ 8same name
    3. kimgea/agent-kit★ 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 repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Start FastAPI and check:

    line 18
  2. Distinctive:

    when RAG is enabled, FastAPI lifespan starts and manages the configured MCP stdio child process

    line 22
  3. Distinctive:

    Verify Hermetic consultation contracts without real Provider calls:

    line 26
  4. Distinctive:

    Verify weather context behavior:

    line 30
  5. Distinctive:

    Run full evaluation only in its separately prepared environment:

    line 35
  6. Distinctive:

    Do not print API keys.

    line 47
  7. Distinctive:

    Do not commit runtime data or raw local reports.

    line 48
  8. Distinctive:

    Do not describe pytest Mock results as real integration or Provider acceptance.

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Verify Project

Pipeline

  1. Dependency check:
    python -m pip check
  2. Unit and contract tests:
    bash scripts/test_hermetic.sh
  3. Start FastAPI and check:
    • GET /health
    • home page
    • Swagger
    • when RAG is enabled, FastAPI lifespan starts and manages the configured MCP stdio child process
  4. Verify booking:
    • normal booking returns 200
    • duplicate stylist/time returns 409
  5. Verify Hermetic consultation contracts without real Provider calls:
    • LLM-not-configured mode returns a retrieval summary
    • runtime MCP failure returns 503
    • Booking remains available during MCP failure
  6. Verify weather context behavior:
    python -m pytest tests/test_weather_context_tool.py
    .env.example enables keyless Open-Meteo, but Hermetic tests use EXTERNAL_CALL_POLICY=deny. Confirm weather only follows successful conversational booking, failures never break booking, and REST or conflict booking does not call weather.
  7. Run full evaluation only in its separately prepared environment:
    python eval/run_evaluation.py --timeout 120

Output

  • Verification summary.
  • Failed command and error details, if any.

Rules

  • Do not print API keys.
  • Do not commit runtime data or raw local reports.
  • Do not describe pytest Mock results as real integration or Provider acceptance.
  • Real Qwen, Embedding, MCP and Open-Meteo acceptance is an explicit isolated flow, not CI.
  • Guest anonymous_owner_id is a browser-controlled business scope, not authentication.
  • SQLite consistency checks cover one local database, not distributed transactions.

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.