Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nwave-ai/nw-hexagonal-testing
5-layer agent output validation, I/O contract specification, vertical slice development, and test doubles policy with per-layer examples
Passed 20 of 22 test cases with the skill, and 13 of 22 without it.
and 4 more in the full report
7 fixed13 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
Where are output code files and automated test suites allowed to be created without special user permission?
| Checked | Without skill | With skill |
|---|---|---|
| File creation is strictly allowed only under src/** and tests/** directories. | Missed | Passed |
The instructions your model reads when the skill loads.
Validates agent OUTPUTS, not TDD testing methodology.
Validate individual software-crafter outputs.
structural_checks:
- required_elements_present: true
- format_compliance: true
- quality_standards_met: true
quality_checks:
- completeness: "All required components present"
- clarity: "Unambiguous and understandable"
- testability: "Can be validated"
test_data_quality:
real_data: "Use real API responses as golden masters"
edge_cases: "Test null, empty, malformed, boundary conditions"
assertions: "Assert expected counts, not just 'any results'"
Validate handoffs to next agent. Next agent must consume outputs without clarification.
Challenge output quality through adversarial scrutiny of generated code:
test cases passed, vs 13 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.