Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Review WooCommerce code changes for coding standards compliance. Use when reviewing code locally, performing automated PR reviews, or checking code quality.
.claude/skills/microck-woocommerce-code-review/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 90% | 0% |
Review code changes against WooCommerce coding standards and conventions.
Consult the woocommerce-backend-dev skill for detailed standards. Using these standards as guidance, flag these violations and other similar ones:
Architecture & Structure:
new for DI-managed classes - Classes in src/ must use $container->get() (dependency-injection.md)src/Internal/ - Default location unless explicitly public (file-entities.md)Naming & Conventions:
Documentation:
@since annotations - Required for public/protected methods and hooks (code-entities.md)Data Integrity:
Testing:
$instance in tests - Must use $sut variable name (unit-tests.md)@testdox - Required in test method docblocks (unit-tests.md)includes/ vs src/ (unit-tests.md)Consult the woocommerce-copy-guidelines skill. Flag:
For each violation found:
text❌ [Issue Type]: [Specific problem] Location: [File path and line number] Standard: [Link to relevant skill file] Fix: [Brief explanation or example]
woocommerce-backend-dev, woocommerce-dev-cycle, and woocommerce-copy-guidelines skills| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-08 | fail→pass | 7,808 | 4,436 | -43% | 1 | 1 | 0% | 1,296 | 1,616 | +25% | 0 | 0 | — |
case-01 | fail→fail | 8,185 | 4,473 | -45% | 1 | 1 | 0% | 1,438 | 1,625 | +13% | 0 | 0 | — |
case-02 | pass→pass | 7,305 | 6,285 | -14% | 1 | 1 | 0% | 1,141 | 1,850 | +62% | 0 | 0 | — |
case-03 | fail→pass | 9,830 | 3,921 | -60% | 1 | 1 | 0% | 1,691 | 1,424 | -16% | 0 | 0 | — |
case-04 | fail→pass | 8,738 | 4,353 | -50% | 1 | 1 | 0% | 1,335 | 1,655 | +24% | 0 | 0 | — |
case-05 | fail→pass | 6,830 | 3,194 | -53% | 1 | 1 | 0% | 1,037 | 1,259 | +21% | 0 | 0 | — |
case-06 | fail→pass | 4,483 | 4,296 | -4% | 1 | 1 | 0% | 789 | 1,502 | +90% | 0 | 0 | — |
case-07 | pass→pass | 4,497 | 3,202 | -29% | 1 | 1 | 0% | 663 | 1,298 | +96% | 0 | 0 | — |
case-09 | pass→pass | 9,951 | 7,069 | -29% | 1 | 1 | 0% | 1,614 | 2,097 | +30% | 0 | 0 | — |
case-10 | pass→pass | 6,739 | 3,545 | -47% | 1 | 1 | 0% | 1,146 | 1,435 | +25% | 0 | 0 | — |
case-11 | fail→pass | 6,979 | 3,619 | -48% | 1 | 1 | 0% | 1,074 | 1,433 | +33% | 0 | 0 | — |
case-12 | pass→pass | 16,069 | 4,306 | -73% | 1 | 1 | 0% | 2,728 | 1,597 | -41% | 0 | 0 | — |
case-13 | pass→pass | 7,849 | 3,509 | -55% | 1 | 1 | 0% | 1,140 | 1,391 | +22% | 0 | 0 | — |
case-14 | pass→pass | 6,844 | 4,252 | -38% | 1 | 1 | 0% | 1,046 | 1,491 | +43% | 0 | 0 | — |
case-15 | pass→pass | 4,488 | 4,882 | +9% | 1 | 1 | 0% | 613 | 1,504 | +145% | 0 | 0 | — |
case-16 | pass→pass | 7,988 | 4,791 | -40% | 1 | 1 | 0% | 1,443 | 1,622 | +12% | 0 | 0 | — |
case-17 | pass→pass | 6,487 | 3,532 | -46% | 1 | 1 | 0% | 1,090 | 1,368 | +26% | 0 | 0 | — |
case-18 | pass→pass | 5,384 | 2,883 | -46% | 1 | 1 | 0% | 871 | 1,327 | +52% | 0 | 0 | — |
case-19 | fail→pass | 7,359 | 7,283 | -1% | 1 | 1 | 0% | 1,273 | 2,097 | +65% | 0 | 0 | — |
case-20 | pass→pass | 15,721 | 12,244 | -22% | 1 | 1 | 0% | 2,859 | 3,076 | +8% | 0 | 0 | — |
case-21 | pass→pass | 14,715 | 12,918 | -12% | 1 | 1 | 0% | 2,702 | 3,322 | +23% | 0 | 0 | — |
case-22 | pass→pass | 12,180 | 11,189 | -8% | 1 | 1 | 0% | 2,160 | 3,048 | +41% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +32 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.