Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nwave-ai/nw-quality-framework
Quality gates - 11 commit readiness gates, build/test protocol, validation checkpoints, and quality metrics
Passed 21 of 22 test cases with the skill, and 9 of 22 without it.
and 16 more in the full report
12 fixed9 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
During our local development loop, we completed an atomic TDD cycle but the test suite failed during step 2 execution. What command should we run to handle this failure while preserving green test discipline?
| Checked | Without skill | With skill |
|---|---|---|
| The response specifies executing git reset --hard HEAD^ to maintain green discipline upon test failure | Missed | Passed |
The instructions your model reads when the skill loads.
All pass before committing:
Note: Reviewer approval (formerly Gate 12) and Testing Theater detection (formerly Gate 13) enforced at deliver-level Phase 4 (Adversarial Review via /nw-review), not per step.
Definition: Acceptance tests pass because test fixtures create the expected end-state directly, rather than exercising production code through the driving port. Tests verify the correct outcome from the WRONG source.
Detection: After GREEN phase, run git diff --name-only. If files_to_modify
from the roadmap step have NO changes but tests flipped from RED to GREEN, this is
Fixture Theater. The test fixtures are implementing the feature, not production code.
Litmus test: Delete the new production code (or revert production files to pre-GREEN state). If tests still pass, it's Fixture Theater.
test cases passed, vs 9 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.