Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when reviewing stylesheets, component styles, and responsive behavior related to Use consistent CSS naming conventions. Check the rendered layout across breakpoints and interaction states before proposing a fix.
.claude/skills/thedaviddias-naming-conventions/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 72% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 2% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 154% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 15% | 0% |
Without a naming convention, class names become a guessing game — does .active mean the nav item is active, the button is pressed, or a form field has focus? With BEM or a similar methodology, .button--active is unambiguous. This reduces the time spent searching for existing styles and prevents accidental style conflicts.
Audit the class names in this CSS file. Are they consistently named? Do they follow a clear convention? Are there any ambiguous names that could conflict?
Rename classes to follow BEM methodology: Block, Block__Element, Block--Modifier pattern.
Explain BEM naming convention, why naming conventions matter, and how to apply BEM to a real component.
Review stylesheets, component styles, and responsive states related to Use consistent CSS naming conventions. Flag exact selectors, declarations, or breakpoints that violate the rule in the rendered UI.
For full implementation details, code examples, and framework-specific guidance, see references/rule.md.
Rule page: https://frontendchecklist.io/en/rules/css/naming-conventions
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 2,590 | 2,727 | +5% | 1 | 1 | 0% | 467 | 803 | +72% | 0 | 0 | — |
case-02 | pass→pass | 4,488 | 2,897 | -35% | 1 | 1 | 0% | 776 | 794 | +2% | 0 | 0 | — |
case-03 | pass→pass | 1,963 | 2,999 | +53% | 1 | 1 | 0% | 347 | 882 | +154% | 0 | 0 | — |
case-04 | pass→pass | 3,862 | 3,202 | -17% | 1 | 1 | 0% | 711 | 821 | +15% | 0 | 0 | — |
case-05 | pass→pass | 4,412 | 3,967 | -10% | 1 | 1 | 0% | 788 | 953 | +21% | 0 | 0 | — |
case-06 | pass→pass | 2,984 | 2,195 | -26% | 1 | 1 | 0% | 552 | 646 | +17% | 0 | 0 | — |
case-07 | pass→pass | 5,570 | 4,066 | -27% | 1 | 1 | 0% | 1,017 | 1,069 | +5% | 0 | 0 | — |
case-08 | pass→pass | 3,457 | 1,709 | -51% | 1 | 1 | 0% | 524 | 609 | +16% | 0 | 0 | — |
case-09 | fail→pass | 5,404 | 2,756 | -49% | 1 | 1 | 0% | 985 | 793 | -19% | 0 | 0 | — |
case-15 | pass→pass | 3,455 | 3,102 | -10% | 1 | 1 | 0% | 673 | 896 | +33% | 0 | 0 | — |
case-10 | pass→pass | 3,236 | 2,685 | -17% | 1 | 1 | 0% | 492 | 802 | +63% | 0 | 0 | — |
case-11 | pass→pass | 3,493 | 3,530 | +1% | 1 | 1 | 0% | 690 | 940 | +36% | 0 | 0 | — |
case-12 | fail→fail | 5,381 | 1,424 | -74% | 1 | 1 | 0% | 1,004 | 545 | -46% | 0 | 0 | — |
case-13 | pass→pass | 2,846 | 2,652 | -7% | 1 | 1 | 0% | 443 | 726 | +64% | 0 | 0 | — |
case-14 | pass→pass | 2,965 | 2,425 | -18% | 1 | 1 | 0% | 486 | 689 | +42% | 0 | 0 | — |
case-16 | pass→pass | 4,048 | 2,453 | -39% | 1 | 1 | 0% | 691 | 713 | +3% | 0 | 0 | — |
case-17 | pass→pass | 2,447 | 1,705 | -30% | 1 | 1 | 0% | 374 | 580 | +55% | 0 | 0 | — |
case-18 | pass→pass | 2,876 | 2,131 | -26% | 1 | 1 | 0% | 489 | 653 | +34% | 0 | 0 | — |
case-19 | pass→pass | 3,551 | 2,249 | -37% | 1 | 1 | 0% | 605 | 696 | +15% | 0 | 0 | — |
case-20 | fail→fail | 7,442 | 6,669 | -10% | 1 | 1 | 0% | 1,672 | 1,907 | +14% | 0 | 0 | — |
case-21 | pass→pass | 3,463 | 4,047 | +17% | 1 | 1 | 0% | 682 | 988 | +45% | 0 | 0 | — |
case-22 | pass→pass | 2,012 | 2,822 | +40% | 1 | 1 | 0% | 441 | 914 | +107% | 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 +5 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.