Install any skill in seconds. Free to start, no credit card required.
Get Started Free →arabelatso/assertion-synthesizer
Generate test assertions from existing code implementation.
Passed 9 of 23 test cases with the skill, and 14 of 23 without it.
1 fixed16 passed either way3 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
A developer wrote the following pytest function for `filter_in_stock_products(products)`: ```python def test_filter(): result = filter_in_stock_products(sample_products) assert result ``` Refine this test to provide thorough assertions for collection contents, list length, and product attributes.
| Checked | Without skill | With skill |
|---|---|---|
| Output includes an explicit length assertion using len(result). | Passed | Passed |
| Output includes assertions verifying attributes of individual returned items. | Passed | Passed |
| Output checks condition filtering across returned items using an all() call. | Missed | Passed |
The instructions your model reads when the skill loads.
Generate comprehensive test assertions by analyzing code implementation, behavior, and expected outputs.
Read and understand the implementation to identify testable behavior:
Extract scenarios that need assertions:
Create appropriate assertions for each scenario:
Assertion Types:
assert result == expected, assertEquals(expected, actual)assert is_valid, assertTrue(condition)assert item in list, assertContains(list, item)pytest.raises(Exception), assertThrows(Exception)assert obj.status == "active", assertEquals("active", obj.getStatus())Organize assertions into well-structured test functions:
test cases passed, vs 14 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.