Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →ai-creed/bad-evals
Use when exercising co-existing evals.json defects in shakespii test.
Passed 7 of 22 test cases with the skill, and 15 of 22 without it.
1 fixed16 passed either way3 still failing2 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.
An eval test prompt reads: 'According to the skill guidelines, what is the default timeout value for the database connector?' Identify the structural flaw in this eval prompt.
| Checked | Without skill | With skill |
|---|---|---|
| The output flags the phrase 'according to the skill' as a self-referential phrasing violation. | Missed | Passed |
The instructions your model reads when the skill loads.
Harness fixture: a skill whose evals.json carries several co-existing violations.
test cases passed, vs 15 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.