Prompt Library coding intermediate

ChatGPT Prompts for Python Scripts: Automation and Data Processing

ChatGPT prompts for Python scripts. Automation, data processing, API integrations, and CLI tools — production-quality Python with error handling and type hints.

Tested on: GPT-4oClaude 4Gemini 2.5

The Prompt

Act as a senior Python engineer who writes clean, well-documented scripts for production automation and data processing.
Write a Python script for:
Task: {describe what the script should do in plain English}
Input: {what data or files the script takes as input}
Output: {what the script should produce}
Python version: {3.10 / 3.11 / 3.12}
Dependencies allowed: {standard library only / list permitted third-party packages}
Error handling level: {basic / comprehensive — with logging}
CLI interface: {yes / no — if yes, describe expected arguments}

Output:
1. Complete script (fully runnable — includes shebang, imports, type hints, docstrings)
2. Requirements.txt snippet (for any third-party packages)
3. Usage examples (command-line examples for 3 different input scenarios)
4. Error cases handled (list of specific errors the script handles and how)
5. Performance notes (time complexity for key operations — relevant if processing large data)
6. Suggested tests (3 pytest test cases for the core logic)

Code standards:
- Type hints on all function signatures
- Docstrings in Google style format
- Logging instead of print statements (except for intentional CLI output)
- No bare except clauses — catch specific exceptions
- Configuration via environment variables or argparse — no hardcoded values
- Main guard: if __name__ == '__main__'

Variables to fill in

  • {task} What the script should do — plain English
  • {input} What data or files the script accepts
  • {output} What the script produces
  • {dependencies} Standard library only or permitted third-party packages
  • {error handling} Basic or comprehensive with logging

How to use this prompt

  1. Describe the task in plain English before specifying implementation details
  2. List allowed dependencies explicitly — prevents the AI from suggesting packages you can't install
  3. Use the usage examples to verify the script handles your actual use cases
  4. Add the suggested tests to your CI pipeline before running the script in production
Python script running in terminal with clean output on dark background
Photo by Chris Ried on Unsplash

Type hints are documentation that runs

Python’s type hint system, combined with mypy or pyright, catches a significant percentage of runtime errors at development time. More importantly, type-hinted code is self-documenting — a function signature def process_orders(orders: list[Order]) -> dict[str, float] tells you everything you need to know without reading the body.

Logging beats print statements for every non-trivial script

Print statements disappear in production, can’t be filtered by level, and don’t include timestamps. Python’s logging module gives you DEBUG/INFO/WARNING/ERROR levels, automatic timestamps, and the ability to redirect output to files without changing code. The prompt enforces logging from the start — not after the script is already in production.

argparse removes the ‘where do I configure this’ problem

Hardcoded configuration values are the most common reason a working script breaks when someone else runs it. Using argparse (or environment variables for sensitive values like API keys) makes scripts portable — they work in any environment without code changes. The prompt’s constraint prevents hardcoded values from appearing in the output.