Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/ac-criteria-validator
Validate acceptance criteria and feature completion.
Passed 17 of 22 test cases with the skill, and 14 of 22 without it.
and 4 more in the full report
6 fixed11 passed either way2 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
Show the feature tracking state JSON structure for feature `auth-001` after validation finishes successfully. Should the status field be `done` or `completed`?
| Checked | Without skill | With skill |
|---|---|---|
| Sets pass flag to true upon successful criteria verification | Missed | Passed |
| Sets progress status to completed after passing all checks | Passed | Passed |
The instructions your model reads when the skill loads.
Validate acceptance criteria and determine feature completion.
Validates that implemented features meet their acceptance criteria, determining when passes can transition from false to true.
from scripts.criteria_validator import CriteriaValidator
validator = CriteriaValidator(project_dir)
result = await validator.validate_feature("auth-001")
print(result.passes) # True/False
print(result.criteria_results)
{
"feature_id": "auth-001",
"passes": true,
"criteria_results": [
{
"criterion": "Valid registration creates user",
"passed": true,
"evidence": "test_valid_registration passed",
"method": "test_execution"
},
{
"criterion": "Invalid email shows error",
"passed": true,
"evidence": "test_invalid_email passed",
"method": "test_execution"
}
],
"test_summary": {
test cases passed, vs 14 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.