Python Script
Developmentpython-scriptPython Script is an Agent Skill for development published in the Dicklesworthstone/pi_agent_rust repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Create robust Python automation with full logging and safety checks. Use when tasks need complex data processing, authenticated API work, conditional file operations, or error handling beyond simple shell commands.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/Dicklesworthstone/pi_agent_rust/blob/HEAD/tests/ext_conformance/artifacts/npm/vaayne-agent-kit/skills/python-script/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/python-script, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Python Scripter
Overview
Design and run Python scripts with clear requirements, safety checks, and reproducible logging.
Workflow
- Confirm inputs, outputs, constraints, and preferred libraries.
- Identify risky operations and secure explicit approval.
- Scaffold a script with PEP 723 metadata and structured logging.
- Lint with
uvx ruff check --fix .agents/scripts/{script_name}.py. - Run with
uv run --script .agents/scripts/{script_name}.pyand monitor logs. - Report results, risks encountered, and any follow-up steps.
Logging requirements
- Log to
.agents/logs/{script_name}.logand stream to console - Capture start/end timestamps, parameters, file operations, and errors
- Add
RotatingFileHandlerif logs may grow large
Template
Read references/script-template.md for the full script template.
Safety practices
- Provide dry-run or rollback paths
- Validate external inputs and API responses
- Use temporary directories for intermediates
- Never run destructive steps without confirmation