How do I install the Python Env skill?

Run npx skillmds@latest add ni-mingcheng/python-env in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Python Env safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Python Env?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Python Env free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Python Env?

NI-MingCheng (@ni-mingcheng) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Python Env by ni-mingcheng — Agent Skill

Name: Python Env
Author: NI-MingCheng

Python Env

Run Python scripts and tests, inspect packages, and install or repair dependencies only in the conda environment named codex. Use for every Python command, test, package operation, notebook helper, or Python-based tool invocation on this machine.

NI-MingCheng Updated Sep 22, 2026

File contents

Python Environment

Run Python through conda env codex; never use system Python or conda base. Use native output for ordinary UTF-8 commands and invoke Encoding Guard only for a real encoding boundary.

Execute Python

Prefer conda run -n codex python ... for portable commands.
An absolute interpreter is acceptable only after confirming it resolves to the codex environment.
Run tests, scripts, build helpers, and package inspection in the same environment.

Manage dependencies

Inspect the project's declared requirements, lockfiles, and existing environment before changing packages.
Confirm the package or compatible version is actually missing.
Prefer the project's declared installer. If none exists, use python -m pip in env codex.
Dry-run the smallest install that satisfies the task. Do not add broad upgrade flags.
Stop if the resolver would remove, downgrade, or incompatibly upgrade existing packages.
After installation, verify the import or command and run python -m pip check.

Read dependency-management.md before installing, removing, upgrading, or repairing packages.

Frequently asked questions