agentleFS
Sign inStart free
thoitiettxl-cyberthoitiettxl-cyber/Claw-II/skills/python-env-manager/SKILL.md

python-env-manager

Skill2 starsChanged 7 months agoMITView on GitHub

Manage Python environment in OpenClaw-Module; handle ModuleNotFoundError, install package via pip wrapper, and standardize to current glibc-runner runtime.

  • Installs packages

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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. Distinctive:

    If you need a compiler:

    line 34
  2. Very specific:

    Don't call pip naked; prioritize python -m pip via wrapper.

    line 48
  3. Very specific:

    Do not export LD_LIBRARY_PATH global to run Python.

    line 49
  4. Very specific:

    When you need to install/upgrade prebuilt Python runtime: follow skill glibc-prebuilt-bundle (artifact policy + backup + smoke + rollback).

    line 50
  5. Distinctive:

    Check results, state validation, and next steps.

    line 72
  6. Distinctive:

    If input/permissions are missing: state what is missing and clearly ask for it.

    line 75
  7. Distinctive:

    If there is a runtime/tool error: return a brief error + possible cause + proposed fix.

    line 76
  8. Distinctive:

    If there is policy/safety risk: stop and escalate according to the approval checkpoint.

    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

Python Environment Manager

This skill standardizes Python operation according to OpenClaw-Module's glibc-runner runtime.

Indexed Reference Map

  • @[SKILL.md#L1-L77] Frontmatter + compatibility.
  • @[SKILL.md#L10-L77] Python error handling process + rules.
  • @[../glibc-prebuilt-bundle/SKILL.md#L1-L63] Canonical flow when needing to install/upgrade prebuilt Python.
  • @[scripts/list_packages.sh#L1-L3] Script lists installed packages.

Handle ModuleNotFoundError

  1. Identify missing modules
    • Get the module name from the error line: ModuleNotFoundError: No module named '...'.
  2. Install the correct runtime using wrapper
    • Always use:
    /data/adb/openclaw/node/bin/python -m pip install <package-name>
    • Or if PATH is correct: python -m pip install <package-name>.
  3. Native build (when the package needs to be compiled)
    • If you need a compiler:
    CC=clang CXX=clang++ /data/adb/openclaw/node/bin/python -m pip install <package-name>
  4. Verify site-packages correct current path
    ls /data/adb/openclaw/python/lib/python3.12/site-packages/
  5. Re-test the original task
    • Rerun the previous script/job to confirm the actual fix.

Rules

  • Don't call pip naked; prioritize python -m pip via wrapper.
  • Do not export LD_LIBRARY_PATH global to run Python.
  • When you need to install/upgrade prebuilt Python runtime: follow skill glibc-prebuilt-bundle (artifact policy + backup + smoke + rollback).

Available scripts

  • scripts/list_packages.sh: list packages in the current Python runtime.

Trigger Rules

  • Positive: Activate when the user request matches python-env-manager according to the description: Manage Python environment in OpenClaw-Module; handle ModuleNotFoundError, install packages via pip wrapper, and standardize to the current glibc-runner runtime.
  • Negative: Do not activate for requests outside scope or that do not need this skill's workflow/expertise.
  • Escalation: If there is external action/network write or a sensitive operation, add an approval checkpoint before execution.

Output Contract

  • Deliverable: results aligned with the goal of python-env-manager; clearly state artifacts/paths/steps performed (if any).
  • Validation: report PASS/FAIL status together with the main checks run.
  • Failure mode: when there is an error, state the root cause + proposed fix.

Scope

  • In-scope: tasks matching the skill description: Manage Python environment in OpenClaw-Module; handle ModuleNotFoundError, install packages via pip wrapper, and standardize to the current glibc-runner runtime.
  • Out-of-scope: requests outside the domain or against system policy.

SOP

  1. Determine whether the request is within the skill's scope.
  2. Execute the skill's main workflow/instructions in a safe order.
  3. Check results, state validation, and next steps.

Error Handling

  • If input/permissions are missing: state what is missing and clearly ask for it.
  • If there is a runtime/tool error: return a brief error + possible cause + proposed fix.
  • If there is policy/safety risk: stop and escalate according to the approval checkpoint.

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