Loading
Write failing tests first, surface the edge cases you'd miss, and turn requirements into a real test suite.
Tests are how you know a change works — and LLMs are good at generating them if you frame the task well. These prompts write failing tests first from a spec, surface edge cases you'd miss, and turn loose requirements into a concrete suite. They emphasise meaningful assertions over coverage theatre. Run them on any model with your own key.
Paste a stack trace plus the relevant code and get the most likely root cause, how to confirm it, and the fix. Ranked by probability.
Translates an 'it's broken' message into a triage-ready ticket: steps to reproduce, expected vs actual, severity, and the first place to look in the code.
Give a function signature and what it should do; get a focused test suite covering the happy path, edges, and error cases — written to fail until you implement it.