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 Include a print stylesheet. Check the rendered layout across breakpoints and interaction states before proposing a fix.
.claude/skills/thedaviddias-css-print/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -49% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 39% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -20% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 15% | 0% |
Print stylesheets ensure content is readable when printed—removing digital clutter and optimizing for paper saves ink and improves accessibility.
Verify that a print stylesheet is provided and properly optimized for printed pages with appropriate typography, layout, and hidden elements.
Create a print stylesheet that removes unnecessary elements, optimizes typography for print, and ensures content is readable when printed.
Explain how print stylesheets improve user experience for printed pages by optimizing layout, removing digital-only elements, and ensuring readability.
Review stylesheets, component styles, and responsive states related to Include a print stylesheet. 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/css-print
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | fail→pass | 11,508 | 4,459 | -61% | 1 | 1 | 0% | 2,096 | 1,076 | -49% | 0 | 0 | — |
case-01 | pass→pass | 13,640 | 9,099 | -33% | 1 | 1 | 0% | 2,894 | 2,251 | -22% | 0 | 0 | — |
case-02 | pass→pass | 5,550 | 5,148 | -7% | 1 | 1 | 0% | 1,136 | 1,229 | +8% | 0 | 0 | — |
case-03 | pass→pass | 8,673 | 5,412 | -38% | 1 | 1 | 0% | 1,708 | 1,291 | -24% | 0 | 0 | — |
case-05 | pass→pass | 2,426 | 3,291 | +36% | 1 | 1 | 0% | 435 | 844 | +94% | 0 | 0 | — |
case-06 | pass→pass | 5,654 | 3,981 | -30% | 1 | 1 | 0% | 1,138 | 1,039 | -9% | 0 | 0 | — |
case-07 | fail→pass | 5,577 | 6,284 | +13% | 1 | 1 | 0% | 1,069 | 1,481 | +39% | 0 | 0 | — |
case-08 | fail→fail | 8,342 | 5,477 | -34% | 1 | 1 | 0% | 1,637 | 1,372 | -16% | 0 | 0 | — |
case-17 | pass→pass | 6,516 | 3,400 | -48% | 1 | 1 | 0% | 1,204 | 965 | -20% | 0 | 0 | — |
case-09 | pass→pass | 8,128 | 5,691 | -30% | 1 | 1 | 0% | 1,755 | 1,480 | -16% | 0 | 0 | — |
case-10 | pass→pass | 10,619 | 6,627 | -38% | 1 | 1 | 0% | 1,963 | 1,487 | -24% | 0 | 0 | — |
case-11 | pass→pass | 10,330 | 11,707 | +13% | 1 | 1 | 0% | 2,424 | 2,963 | +22% | 0 | 0 | — |
case-12 | pass→pass | 7,921 | 7,053 | -11% | 1 | 1 | 0% | 1,713 | 1,632 | -5% | 0 | 0 | — |
case-13 | pass→pass | 4,289 | 2,675 | -38% | 1 | 1 | 0% | 818 | 718 | -12% | 0 | 0 | — |
case-14 | fail→pass | 16,196 | 10,651 | -34% | 1 | 1 | 0% | 3,425 | 2,699 | -21% | 0 | 0 | — |
case-15 | pass→pass | 5,598 | 6,829 | +22% | 1 | 1 | 0% | 1,071 | 1,615 | +51% | 0 | 0 | — |
case-16 | fail→pass | 11,980 | 6,647 | -45% | 1 | 1 | 0% | 2,448 | 1,951 | -20% | 0 | 0 | — |
case-18 | fail→pass | 8,094 | 8,408 | +4% | 1 | 1 | 0% | 1,781 | 2,047 | +15% | 0 | 0 | — |
case-19 | fail→pass | 8,441 | 6,434 | -24% | 1 | 1 | 0% | 1,789 | 1,665 | -7% | 0 | 0 | — |
case-20 | fail→fail | 5,492 | 7,532 | +37% | 1 | 1 | 0% | 1,199 | 1,919 | +60% | 0 | 0 | — |
case-21 | pass→pass | 2,854 | 3,946 | +38% | 1 | 1 | 0% | 611 | 1,068 | +75% | 0 | 0 | — |
case-22 | pass→pass | 3,980 | 5,120 | +29% | 1 | 1 | 0% | 967 | 1,274 | +32% | 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 +27 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.