Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →ai-creed/corpus-good
Use when verifying that one broken skill does not abort the corpus run.
Passed 16 of 20 test cases with the skill, and 12 of 20 without it.
and 3 more in the full report
6 fixed12 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
An automated regression test passes the corpus directory path to the linter. If the good fixture evaluates successfully, what output list is generated?
| Checked | Without skill | With skill |
|---|---|---|
| produces an empty list of findings | Missed | Passed |
The instructions your model reads when the skill loads.
Serves as the healthy neighbor of a deliberately broken fixture skill.
The corpus root path handed over by the broken-skill test.
The broken fixture tree is checked out unchanged.
An empty findings list for the good fixture.
Given the input good, the expected output is good-lint-clean.
Fixing the broken neighbor; it is broken by design.
test cases passed, vs 12 / 20 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.