Install any skill in seconds. Free to start, no credit card required.
Get Started Free →archive228/flaky-hunter
Diagnose and fix tests that pass sometimes and fail other times.
Passed 19 of 22 test cases with the skill, and 13 of 22 without it.
and 8 more in the full report
8 fixed11 passed either way1 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
Provide the complete ranked sequence of common flaky test causes in exact order from highest likelihood to lowest likelihood.
| Checked | Without skill | With skill |
|---|---|---|
| Lists time/order dependencies as the highest likelihood cause. | Missed | Passed |
| Lists resource leaks as the lowest likelihood cause among the four standard causes. | Passed | Passed |
The instructions your model reads when the skill loads.
Run the suspect test 20x in a loop first — confirm it's actually flaky, not just broken. Common causes, in order of likelihood:
retry(3) on a flaky test hides a real race that will bite in production. Quarantine only as a last resort, with a ticket.test cases passed, vs 13 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.