Coding · Free prompt
AI prompt to write unit tests
Ask an AI for tests and you often get one test for the happy path. This prompt makes it cover what actually matters: edge cases, invalid input, and the failures that break things in production.
Copy this prompt
You are a developer who writes thorough, readable unit tests and thinks hard about edge cases. Write unit tests for the code below. LANGUAGE: [e.g. TypeScript, Python] TEST FRAMEWORK: [e.g. Jest, Vitest, pytest] WHAT THIS CODE SHOULD DO: [ONE OR TWO SENTENCES] CODE TO TEST: ``` [PASTE YOUR CODE HERE] ``` Cover these cases: - The normal, expected case. - Edge cases: empty input, zero, very large values, boundaries. - Invalid input and error handling. - Any tricky behavior specific to this code. Rules: - Give each test a clear name that says what it checks. - Keep tests simple and independent of each other. - Do not test the framework or the language itself, only this code. - If the code has a bug that makes a sensible test fail, point it out. Return the test file, ready to run.
Paste it into ChatGPT, Claude, or Gemini and replace the text in [SQUARE BRACKETS] with your own details.
Why this prompt works
- 01
Listing edge cases explicitly is what gets the model past the single happy-path test it defaults to.
- 02
Telling it what the code "should do" lets it write tests for intended behavior, not just current behavior.
- 03
Asking it to flag bugs that break sensible tests turns test-writing into a free code review.
How to adapt it
- -Name your test framework. Test syntax differs a lot between Jest, pytest, and others.
- -Test one function at a time for clear, focused test files.
- -If it writes a test that fails, check whether the test is wrong or the code is. Sometimes it found a real bug.
Frequently asked questions
Why does this write tests prompt work better than a basic one?
Listing edge cases explicitly is what gets the model past the single happy-path test it defaults to.
How do I adapt this prompt for my own situation?
Name your test framework. Test syntax differs a lot between Jest, pytest, and others.
Is this prompt free, and does it work with Claude and Gemini as well as ChatGPT?
Yes on both. The prompt is completely free to copy, and it is model-agnostic - it produces strong results in ChatGPT, Claude, and Gemini. Paste it into any of them.
Want this tuned to your exact situation?
A template gets you started. Deepclario takes your version of a prompt, scores it, asks what is missing, and rewrites it for your specific task. Free, no account needed.
Improve my prompt freeMore coding prompts