Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nwave-ai/nw-ad-critique-dimensions
Review dimensions for acceptance test quality - happy path bias, GWT compliance, business language purity, coverage completeness, walking skeleton user-centricity, priority validation, observable behavior assertions, traceability coverage, and walking skeleton boundary proof
Passed 21 of 22 test cases with the skill, and 8 of 22 without it.
and 21 more in the full report
13 fixed8 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
When grepping scenario files under Strategy B, we found the `@in-memory` tag on two walking skeleton scenarios. What rule applies?
| Checked | Without skill | With skill |
|---|---|---|
| Detects strategy drift where walking skeleton claims real adapters but uses in-memory tags | Passed | Passed |
| Assigns a high severity rating to the strategy drift finding | Missed | Passed |
The instructions your model reads when the skill loads.
Load when performing peer review of acceptance tests (during *handoff-develop).
Pattern: Only successful scenarios, error paths missing.
Detection: Count success vs error scenarios. Error should be at least 40%. Missing coverage examples: login success but no invalid password | Payment processed but no decline/timeout | Search results but no empty/error cases.
Severity: blocker (production error handling untested).
Pattern: Scenarios violate Given-When-Then structure.
Violations: Missing Given context | Multiple When actions (split into separate scenarios) | Then with technical assertions instead of business outcomes. Each scenario: Given (context), When (single action), Then (observable outcome).
Severity: high (tests not behavior-driven).
Pattern: Technical terms leak into acceptance tests.
Flag: database, API, HTTP, REST, JSON, classes, methods, services, controllers, status codes (500, 404), infrastructure (Redis, Kafka, Lambda).
Business alternatives: "Customer data is stored" not "Database persists record" | "Order is confirmed" not "API returns 200 OK" | "Payment fails" not "Gateway throws exception"
Severity: high (tests coupled to implementation).
Pattern: User stories lack acceptance test coverage.
Validation: Map each story to scenarios | Verify all AC have corresponding tests | Confirm edge cases and boundaries tested.
Severity: blocker (unverified requirements).
test cases passed, vs 8 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.