Prompts that restructure code safely.
24votes
2answers
2.8kviews

Output contract that makes the model write code future-me won't hate

My gripe isn't that AI code is wrong, it's that it is unmaintainable: 80-line functions, clever one-liners, no seams for testing, magic numbers everywhere. It passes review by looking confident. I sto
17votes
1answers
2.4kviews

Safely refactoring a 600-line god-function CLI without changing its behavior

Inherited a single def run() that was 600 lines: arg parsing, file IO, business logic, and printing all tangled together. Management wanted features added but touching it was Russian roulette. Asking
13votes
0answers
3.1kviews

Prompt for reviewing a diff with severity levels instead of vague nitpicks

Our AI code reviews were noise: a wall of "consider renaming this" and "you could add a comment" mixed in with the occasional actual security bug, all weighted the same. People started ignoring the bo
10votes
2answers
2.2kviews

Prompt that adds characterization tests before it touches legacy code

I inherited a 12-year-old billing module with zero tests and a maze of nested conditionals. Every time I asked Claude to "refactor this to be cleaner" it happily rewrote the control flow and silently
9votes
2answers
1.8kviews

Prompt to convert a messy research notebook into a reproducible, parameterized script

My analysis lived in a 400-cell notebook with out-of-order execution, hardcoded paths from my laptop, and df reused for six different frames. It ran on my machine and nowhere else. I needed a clean CL
5votes
0answers
968views

Splitting a 600-line god function into pure units without behavior drift

The worst function in our codebase does input parsing, three network calls, retry logic, formatting, and logging in one 600-line block. I wanted GPT to carve it into small pure functions plus a thin o