agentleFS
Sign inStart free
hyh0620hyh0620/ai-hair-salon-agent/.github/skills/setup-environment/SKILL.md

setup-environment

Skill0 starsChanged 4 months agoMITView on GitHub

Prepare a local AI Hair Salon Agent checkout for development and verification. Use when setting up dependencies or checking MCP configuration.

  • Reads credentials
  • Installs packages

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 4

    Distinctive

    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. Distinctive:

    Create or reuse virtual environment:

    line 21
  2. Distinctive:

    Create local config if missing:

    line 31
  3. Very specific:

    Verify required MCP variables are present in .env before enabling RAG:

    line 35
  4. Distinctive:

    Do not print API keys.

    line 53
  5. Very specific:

    If MCP path variables are missing, leave RAG_MCP_ENABLED=false until configured.

    line 54
  6. Distinctive:

    Do not install the main project and MCP Knowledge Service into the same virtual environment.

    line 55

“Common” is measured: kept by at least 6 in 10 of the 6 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

Setup Environment

Inputs

  • Project root: current repository.
  • Main project Python: python3.12.
  • MCP Knowledge Service: independent virtual environment; its project metadata supports Python 3.11+.
  • Optional MCP Knowledge Service path supplied through .env.

Pipeline

  1. Check Python:
    python3.12 --version
  2. Create or reuse virtual environment:
    python3.12 -m venv .venv
source .venv/bin/activate
  3. Install dependencies:
    python -m pip install --upgrade pip
python -m pip install -c constraints-py312.txt -r requirements-dev.txt
  4. Create local config if missing:
    test -f .env || cp .env.example .env
  5. Verify required MCP variables are present in .env before enabling RAG:
    • RAG_MCP_SERVER_PYTHON
    • RAG_MCP_SERVER_MODULE
    • RAG_MCP_SERVER_CWD
    • RAG_MCP_COLLECTION
  6. Run dependency check:
    python -m pip check

Output

  • Local .venv.
  • Local .env with placeholders.
  • Next command: start FastAPI. When RAG is enabled and configured, FastAPI lifespan starts and manages the MCP stdio child process.

Failure Handling

  • Do not print API keys.
  • If MCP path variables are missing, leave RAG_MCP_ENABLED=false until configured.
  • Do not install the main project and MCP Knowledge Service into the same virtual environment.
  • Manual MCP server startup is only for standalone stdio protocol validation, not normal application integration.

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