agentleFS
danielrosehilldanielrosehill/Claude-Israel-Agent-Skills-Plugin/skills/environment-check/SKILL.md

environment-check

Skill2 starsChanged 24 days agoMITView on GitHub

Use when another skill in this plugin reports a missing dependency (Python module, Playwright browser, CLI tool), or when the user wants to verify or set up the runtime environment for Israel-Agent-Skills. Checks for required tools and offers to install them. Trigger phrases - "set up environment for X skill", "playwright not installed", "install dependencies for israel skills", "fix missing module", "ModuleNotFoundError: playwright".

  • Installs packages

2 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

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Detect the runtime: Run python3 -c "import sys.

    line 21
  2. Distinctive:

    Does not install system packages (apt, brew, dnf) — surface those instructions to the user instead.

    line 42
  3. Very specific:

    Does not modify shell rc files.

    line 43
  4. Very specific:

    Does not manage virtualenvs for the user — the plugin's scripts use whatever python3 is on PATH.

    line 44

≈ “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

Environment Check & Install

Shared dependency manager for Israel-Agent-Skills. Other skills delegate here when they detect a missing tool, instead of bundling install logic each.

Supported toolchains

ToolUsed byInstall command (Linux/macOS)
playwright (Python) + Chromiumnsc-travel-threat, ben-gurion-flight-board, any browser-driven skillpipx install playwright && pipx runpip playwright install playwright && playwright install chromium — or pip install --user playwright && python3 -m playwright install chromium
requestsfiber-availability-check, RSS skillspip install --user requests
pyyamlskills reading user prefspip install --user pyyaml
feedparserisrael-news-rsspip install --user feedparser

Procedure

  1. Detect the runtime. Run python3 -c "import sys; print(sys.executable, sys.version_info[:2])" — that interpreter is the one the plugin's scripts will use (they all use #!/usr/bin/env python3).
  2. Probe for the missing dependency. For Python modules:
    python3 -c "import <module>" 2>&1
    For Playwright's browser binary specifically (the module-import check is not enough — the Chromium binary is separate):
    python3 -c "from playwright.sync_api import sync_playwright; p=sync_playwright().start(); b=p.chromium.launch(headless=True); b.close(); p.stop(); print('ok')"
  3. If pipx already has the tool but the system python3 doesn't see it (common with playwright), prefer fixing the import path rather than reinstalling. Either install into user-site as well (pip install --user <pkg>), or point PYTHONPATH at the pipx venv site-packages for that one invocation.
  4. Confirm with the user before installing anything. Show: what's missing, what command will run, whether it touches user-site (--user) or a system location. Never run sudo pip install.
  5. For Playwright browser binaries, respect any existing PLAYWRIGHT_BROWSERS_PATH env var. If the user has one set (check env | grep PLAYWRIGHT_BROWSERS_PATH), use it; otherwise let Playwright use its default (~/.cache/ms-playwright).
  6. Verify by re-running the probe after install. Report success or paste the new error.

What this skill does NOT do

  • Does not install system packages (apt, brew, dnf) — surface those instructions to the user instead.
  • Does not modify shell rc files. If a PATH change is needed, print the line for the user to add.
  • Does not manage virtualenvs for the user — the plugin's scripts use whatever python3 is on PATH.

Reporting back to the calling skill

Once the dependency is satisfied, tell the user "you can re-run the [skill] command now" and let the original conversation resume there. Do not chain into the original skill yourself.

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.