Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →archive228/coverage-gaps
Find the untested code paths that actually matter, not just the coverage percentage. Use after adding tests.
Passed 20 of 22 test cases with the skill, and 18 of 22 without it.
2 fixed18 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
In an e-commerce checkout microservice, we discovered three untested paths: 1) Getter method on TaxCalculator returns correct default rate, 2) DB connection failure during order finalization throws 500, 3) Coupon code string trimming when user inputs trailing spaces. How should we order these by risk?
| Checked | Without skill | With skill |
|---|---|---|
| Ranks DB connection failure during finalization highest in blast radius risk | Passed | Passed |
| Ranks the getter method test lowest in priority | Missed | Passed |
The instructions your model reads when the skill loads.
Coverage % is a vanity metric. Hunt the gaps that bite:
if/else and catch exercised, not just the happy line.test cases passed, vs 18 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.