Unit tests
Curated open Agent-Skill format skills for MyLLM (the on-device iOS AI agent). Install with /skill add teamdzx/myllm-skills.
npx -y skills add TeamDzX/myllm-skills --skill unit-testsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Write unit tests for a function or module. Use when the user shares code and wants tests for it.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
1.0 KB, as published. Nobody here has run it
Unit tests
Write focused unit tests for the code the user provides.
- Identify the language and test framework. If it's not obvious, pick the idiomatic default (e.g. pytest for Python, Jest for JS/TS, XCTest for Swift, JUnit for Java) and say which you used.
- Cover, at minimum:
- the happy path,
- edge cases (empty/zero/boundary/large inputs),
- error/invalid-input behaviour.
- Output the tests in one runnable code block.
Rules:
- Use Arrange–Act–Assert and descriptive test names that state the expectation.
- Test observable behaviour and the public interface — not private implementation details.
- One logical assertion focus per test; avoid coupling tests to each other.
- Don't hit the network, clock, or filesystem — stub/mock those and note it.
- If a likely bug surfaces while writing tests, add a failing test for it and flag it briefly.