agentleFS
Sign inStart free
fritzprixfritzprix/libr-agent/.agents/skills/setup-wizard/SKILL.md

setup-wizard

Skill11 starsChanged 18 days agoMITView on GitHub

Use when the user needs to diagnose and install runtime environment dependencies (Python, Node.js, uv) for running LibrAgent or MCP servers. Use on first run or a new machine ("I just installed LibrAgent, what do I need to set up?"), MCP "command not found" or spawn errors, or missing Python/Node runtime failures. Triggers: 처음 깔았는데 뭐 설정해야 돼, 초기 설정, 환경 설정, command not found, node 없음, python 없음. LibrAgent 실행에 필요한 Python, Node.js 등의 환경을 자동으로 진단하고 설치하도록 안내하는 마법사입니다.

  • Installs packages

3 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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Prefer scripts when the user wants hands-off install:

    line 44
  2. Distinctive:

    After setup, re-run the verification script before retrying failed MCP servers.

    line 77

≈ “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

System Setup for MCP Servers

Automated installation and verification of MCP runtime dependencies.

Path conventions

Paths in this skill are relative to this skill's Base Directory. Replace <skill-base-dir> with its absolute path in commands.

Workflow

  1. Detect OS — identify platform via terminal
  2. Check installations — run verification commands below
  3. Install missing components — use platform scripts or installation-guide.md
  4. Verify — run verify_setup script or manual checks; confirm Python 3.11+, Node 18+, uv available

Quick Verification

Windows (PowerShell):

Get-Command python -ErrorAction SilentlyContinue
Get-Command node -ErrorAction SilentlyContinue
Get-Command uv -ErrorAction SilentlyContinue

Linux/macOS:

which python3 && python3 --version
which node && node --version
which uv && uv --version

Report what is missing, then load only the relevant section from the installation guide.

Automated Scripts

Prefer scripts when the user wants hands-off install:

# Windows examples
& "<skill-base-dir>/scripts/verify_setup.ps1"
& "<skill-base-dir>/scripts/install_python.ps1"
& "<skill-base-dir>/scripts/install_node.ps1"
& "<skill-base-dir>/scripts/install_uv.ps1"
# Linux/macOS examples (install_node.sh is Linux-only; on macOS use brew install node)
bash "<skill-base-dir>/scripts/verify_setup.sh"
bash "<skill-base-dir>/scripts/install_python.sh"
bash "<skill-base-dir>/scripts/install_node.sh"   # Linux only; no-op if node exists, add --force to reinstall
bash "<skill-base-dir>/scripts/install_uv.sh"

Advanced Topics

  • PATH configuration: PATH_CONFIG.md
  • Virtual environments: VENV_GUIDE.md
  • Offline installation: OFFLINE_INSTALL.md
  • OS-specific commands: installation-guide.md

Integration with LibrAgent

LibrAgent MCP servers require:

  • Python 3.11+ for Python-based MCP servers
  • Node.js 18+ for TypeScript-based MCP servers
  • uv for fast Python dependency management

After setup, re-run the verification script before retrying failed MCP servers.

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