RU

run-python-script

Runs ad hoc Python helper scripts or commands consistently across environments.

Install

mkdir -p .claude/skills/run-python-script && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16596" && unzip -o skill.zip -d .claude/skills/run-python-script && rm skill.zip

Installs to .claude/skills/run-python-script

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Use when: running an ad hoc Python script, using python -c for inspection or file transforms, editing ZIP/XLSX/XML files with Python, or choosing between python and python3 on macOS/Linux/Windows. Keywords: python script, python3, python -c, zipfile, one-off Python command, interpreter check.
293 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Beginner

Key capabilities

  • Run ad hoc Python scripts
  • Execute one-off Python commands for inspection
  • Perform file transformations using Python
  • Edit ZIP/XLSX/XML files with Python
  • Ensure `python3` is used as the interpreter
  • Handle shell quoting issues by preferring temporary files

How it works

This skill standardizes the execution of short Python helpers by consistently using `python3`, preferring temporary `.py` script files for complex tasks, and ensuring read-only operations unless explicitly requested. It avoids common shell quoting issues and provides file safety rules.

Inputs & outputs

You give it
Python script or command to execute
You get back
A concise summary of affected paths, replacement counts, or measured results

When to use run-python-script

  • Running ad hoc file transformation scripts
  • Inspecting file contents with python3
  • Executing one-off data extraction tasks
  • Verifying file content changes

About this skill

Run Python Script

This skill standardizes how to run short Python helpers safely in this workspace.

Scope

Use this skill when the task needs a one-off Python script for inspection, transformation, extraction, archive editing, or verification.

Goal

Run Python helper logic with the right interpreter, without tripping over shell quoting or assuming python exists.

Interpreter Selection

  1. On this machine, python does not exist. Always use python3 directly — do not probe with which python or command -v python first.
  2. Do not activate virtual environments for this repo unless the user explicitly asks.
  3. Use python3 consistently for the whole task.

Default Approach

  1. For short read-only inspection, python3 -c '...' is acceptable if quoting is simple.
  2. For multi-line, regex-heavy, XML/ZIP-heavy, or mutating work, prefer a temporary .py script file over a long python3 -c command.
  3. Keep scripts read-only unless the task explicitly requires writing output.
  4. For file transforms, write to a temporary output first and replace the original only after the expected change is verified.
  5. Print a concise summary such as affected paths or replacement counts.

Shell Rules

  • Use bash-compatible syntax for commands.
  • python does not exist here; always use python3.
  • Avoid inline heredocs for Python snippets in Git Bash or mixed shell environments.
  • Avoid long python3 -c commands when nested quotes, XML, JSON, or regular expressions make shell parsing fragile.

File Safety Rules

  • For ZIP-based files such as .xlsx, preserve archive entries and rewrite only the intended member files.
  • Validate expected match counts before replacing content.
  • Fail loudly with a clear error if the target pattern is absent or appears more times than expected.
  • Do not stage, commit, or push unless explicitly requested.

Preferred Patterns

Short one-liner:

python3 -c 'print("ok")'

Temporary script:

python3 path/to/temp_script.py

Expected Output

When using this skill:

  • Use python3 directly; no interpreter probing.
  • Keep side effects explicit and narrowly scoped.
  • Report what was changed or measured.

Do Not

  • Do not call python — it does not exist on this machine; use python3.
  • Do not probe for the interpreter (which python, command -v python) before running.
  • Do not use Python heredocs for inline scripts in Git Bash or cross-platform sessions.
  • Do not overwrite source files before checking expected match counts.
  • Do not leave temporary helper scripts behind unless they are intentionally useful.

When not to use it

  • When the task requires activating virtual environments without explicit user request
  • When the task involves calling `python` instead of `python3`
  • When the task requires complex inline commands that make shell parsing fragile

Limitations

  • The skill explicitly forbids using `python` as the interpreter
  • The skill does not activate virtual environments unless explicitly asked
  • The skill advises against long `python3 -c` commands for complex operations

How it compares

This skill enforces a standardized and safer way to run Python scripts by explicitly using `python3` and preferring temporary files for complex operations, unlike a generic approach that might use `python` or long inline commands prone to e

Compared to similar skills

run-python-script side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
run-python-script (this skill)01moReviewBeginner
massgen-develops-massgen16moReviewAdvanced
wox-plugin-creator12moReviewIntermediate
klingai-text-to-video11moCautionBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

massgen-develops-massgen

massgen

Guide for using MassGen to develop and improve itself. This skill should be used when agents need to run MassGen experiments programmatically (using automation mode) OR analyze terminal UI/UX quality (using visual evaluation tools). These are mutually exclusive workflows for different improvement goals.

13

wox-plugin-creator

Wox-launcher

Create and scaffold Wox plugins (nodejs, python, script-nodejs, script-python). Use when cloning official SDK templates, generating script plugin templates, or preparing plugins for publish.

13

klingai-text-to-video

jeremylongshore

Generate videos from text prompts with Kling AI. Use when creating videos from descriptions or learning prompt techniques. Trigger with phrases like 'kling ai text to video', 'klingai prompt', 'generate video from text', 'text2video kling'.

12

code-execution

mhattingpete

Execute Python code locally with marketplace API access for 90%+ token savings on bulk operations. Activates when user requests bulk operations (10+ files), complex multi-step workflows, iterative processing, or mentions efficiency/performance.

10

mcp-chaining

parcadei

Research-to-implement pipeline chaining 5 MCP tools with graceful degradation

10

windsurf-sdk-patterns

jeremylongshore

Apply production-ready Windsurf SDK patterns for TypeScript and Python. Use when implementing Windsurf integrations, refactoring SDK usage, or establishing team coding standards for Windsurf. Trigger with phrases like "windsurf SDK patterns", "windsurf best practices", "windsurf code patterns", "idiomatic windsurf".

10

Search skills

Search the agent skills registry