Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when reviewing rendered HTML, layout components, or design-system patterns that may depend on presentation for meaning. Check the DOM order, semantic structure, form relationships, and whether CSS generated content carries essential information.
.claude/skills/thedaviddias-content-without-css/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 40% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 46% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 139% | 0% |
| case-03 | ✓→✗ | ▼ Worse | 70% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 20% | 0% |
Users can browse with custom styles, high contrast modes, reader tools, or failed stylesheets. If the page only makes sense visually, content order, instructions, and task flow break as soon as presentation changes.
Find pages or components that rely on CSS for meaning. Verify the page still has a logical reading order, visible labels, instructions, error text, and operable primary actions when author styles are disabled or replaced by user styles.
Use semantic HTML and DOM order to preserve headings, lists, labels, field groups, helper text, and error messaging without relying on CSS positioning, pseudo-elements, or visual-only cues.
Explain why semantic HTML and meaningful DOM order let content remain understandable when CSS fails to load or users apply their own styles.
Review templates, rendered HTML, and component markup related to Ensure content remains usable without CSS. Flag where meaning, reading order, labels, instructions, or task flow depend on CSS rather than semantics, and note how to verify the fix with styles disabled.
For full implementation details, code examples, and framework-specific guidance, see references/rule.md.
Rule page: https://frontendchecklist.io/en/rules/accessibility/content-without-css
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | pass→pass | 5,758 | 4,807 | -17% | 1 | 1 | 0% | 1,129 | 1,350 | +20% | 0 | 0 | — |
case-01 | fail→pass | 7,617 | 8,999 | +18% | 1 | 1 | 0% | 1,386 | 1,947 | +40% | 0 | 0 | — |
case-03 | pass→fail | 4,847 | 6,300 | +30% | 1 | 1 | 0% | 885 | 1,502 | +70% | 0 | 0 | — |
case-04 | pass→pass | 8,176 | 7,990 | -2% | 1 | 1 | 0% | 1,615 | 2,089 | +29% | 0 | 0 | — |
case-05 | pass→pass | 9,340 | 7,828 | -16% | 1 | 1 | 0% | 1,665 | 1,699 | +2% | 0 | 0 | — |
case-06 | pass→pass | 6,894 | 7,128 | +3% | 1 | 1 | 0% | 1,392 | 1,760 | +26% | 0 | 0 | — |
case-07 | pass→pass | 5,904 | 4,337 | -27% | 1 | 1 | 0% | 1,116 | 1,245 | +12% | 0 | 0 | — |
case-08 | pass→pass | 4,700 | 4,922 | +5% | 1 | 1 | 0% | 1,001 | 1,235 | +23% | 0 | 0 | — |
case-09 | pass→pass | 7,636 | 6,790 | -11% | 1 | 1 | 0% | 1,752 | 1,612 | -8% | 0 | 0 | — |
case-10 | pass→pass | 8,908 | 8,306 | -7% | 1 | 1 | 0% | 1,876 | 1,796 | -4% | 0 | 0 | — |
case-11 | pass→pass | 6,279 | 6,898 | +10% | 1 | 1 | 0% | 1,429 | 1,653 | +16% | 0 | 0 | — |
case-12 | pass→pass | 10,854 | 8,361 | -23% | 1 | 1 | 0% | 2,248 | 1,975 | -12% | 0 | 0 | — |
case-13 | pass→pass | 8,964 | 6,549 | -27% | 1 | 1 | 0% | 1,827 | 1,625 | -11% | 0 | 0 | — |
case-14 | fail→pass | 5,505 | 6,378 | +16% | 1 | 1 | 0% | 1,149 | 1,672 | +46% | 0 | 0 | — |
case-15 | pass→pass | 4,741 | 5,653 | +19% | 1 | 1 | 0% | 1,084 | 1,323 | +22% | 0 | 0 | — |
case-16 | pass→pass | 4,956 | 8,161 | +65% | 1 | 1 | 0% | 1,086 | 1,866 | +72% | 0 | 0 | — |
case-17 | fail→pass | 3,397 | 5,684 | +67% | 1 | 1 | 0% | 592 | 1,413 | +139% | 0 | 0 | — |
case-18 | pass→pass | 6,543 | 5,718 | -13% | 1 | 1 | 0% | 1,346 | 1,451 | +8% | 0 | 0 | — |
case-19 | pass→pass | 2,885 | 3,148 | +9% | 1 | 1 | 0% | 625 | 899 | +44% | 0 | 0 | — |
case-20 | pass→pass | 4,120 | 4,117 | -0% | 1 | 1 | 0% | 674 | 1,128 | +67% | 0 | 0 | — |
case-21 | pass→pass | 5,196 | 4,322 | -17% | 1 | 1 | 0% | 1,181 | 1,273 | +8% | 0 | 0 | — |
case-22 | pass→pass | 8,719 | 8,504 | -2% | 1 | 1 | 0% | 1,780 | 1,992 | +12% | 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 +9 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
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.