Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mkurman/test
Generate or run tests. Auto-detects test framework, generates comprehensive tests for source files, or runs existing test suites with failure analysis.
Passed 13 of 18 test cases with the skill, and 7 of 18 without it.
and 6 more in the full report
7 fixed9 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
When presenting test recommendations for an un-tested file `src/utils/logger.ts`, what slash command examples should be included at the bottom of the output so the user knows how to generate tests or run the suite?
| Checked | Without skill | With skill |
|---|---|---|
| The response includes /test src/utils/logger.ts or /test <file path> as an example command. | Missed | Passed |
| The response includes /test run as an example command. | Missed | Passed |
The instructions your model reads when the skill loads.
Accepts optional arguments:
run: run the existing test suite and analyze results<quick_start>
<step_1_detect_framework>
Detect the test framework and conventions before doing anything else.
Check these sources in order:
package.json (Node/JS/TS projects):
scripts.test for the test commanddevDependencies for jest, vitest, mocha, ava, tap, node:test, playwright, cypressjest or vitest config keysConfig files:
jest.config.*, vitest.config.*, .mocharc.*, ava.config.*pytest.ini, pyproject.toml (look for [tool.pytest]), setup.cfggo.mod (Go projects use go test by default)Cargo.toml (Rust projects use cargo test)Existing test files:
*.test.*, *.spec.*, *_test.*, test_*.* files__tests__/ vs tests/ vs test/)Record your findings:
test cases passed, vs 7 / 18 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.