Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when reviewing rendered HTML, interactive components, or design-system patterns related to Wrap definition items in a definition list. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.
.claude/skills/thedaviddias-dlitem/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✓→✗ | ▼ Worse | -20% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 0% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 18% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 25% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 36% | 0% |
Standalone <dt> or <dd> elements lose their semantic meaning and fail to provide the context needed for assistive technologies to link terms with definitions.
Locate any <dt> or <dd> elements that are not children of a <dl> element.
Wrap orphaned <dt> and <dd> elements in a parent <dl> container.
Explain why <dt> and <dd> must be contained within a <dl> for correct semantic association.
Review the rendered markup and interactive states that affect Wrap definition items in a definition list. Flag exact elements, roles, labels, focus behavior, or keyboard interactions that violate the rule, and note how to verify the fix with browser accessibility tooling or assistive tech.
For full implementation details, code examples, and framework-specific guidance, see references/rule.md.
Rule page: https://frontendchecklist.io/en/rules/accessibility/dlitem
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 7,783 | 6,391 | -18% | 1 | 1 | 0% | 1,545 | 1,540 | -0% | 0 | 0 | — |
case-02 | pass→pass | 72,578 | 11,754 | -84% | 1 | 1 | 0% | 2,267 | 2,664 | +18% | 0 | 0 | — |
case-03 | pass→pass | 4,747 | 4,717 | -1% | 1 | 1 | 0% | 930 | 1,166 | +25% | 0 | 0 | — |
case-04 | pass→pass | 4,761 | 5,233 | +10% | 1 | 1 | 0% | 918 | 1,251 | +36% | 0 | 0 | — |
case-17 | pass→pass | 4,046 | 1,524 | -62% | 1 | 1 | 0% | 692 | 553 | -20% | 0 | 0 | — |
case-05 | pass→pass | 4,019 | 4,138 | +3% | 1 | 1 | 0% | 752 | 1,052 | +40% | 0 | 0 | — |
case-06 | pass→pass | 7,845 | 5,500 | -30% | 1 | 1 | 0% | 1,506 | 1,363 | -9% | 0 | 0 | — |
case-07 | pass→pass | 7,196 | 6,942 | -4% | 1 | 1 | 0% | 1,541 | 1,733 | +12% | 0 | 0 | — |
case-08 | pass→pass | 4,178 | 4,304 | +3% | 1 | 1 | 0% | 718 | 1,078 | +50% | 0 | 0 | — |
case-09 | pass→pass | 3,088 | 3,146 | +2% | 1 | 1 | 0% | 549 | 841 | +53% | 0 | 0 | — |
case-10 | pass→pass | 5,974 | 6,565 | +10% | 1 | 1 | 0% | 1,086 | 1,646 | +52% | 0 | 0 | — |
case-11 | pass→fail | 10,636 | 7,284 | -32% | 1 | 1 | 0% | 2,027 | 1,631 | -20% | 0 | 0 | — |
case-12 | pass→pass | 6,853 | 4,956 | -28% | 1 | 1 | 0% | 1,414 | 1,273 | -10% | 0 | 0 | — |
case-13 | pass→pass | 4,136 | 4,957 | +20% | 1 | 1 | 0% | 794 | 1,169 | +47% | 0 | 0 | — |
case-14 | pass→pass | 12,694 | 5,041 | -60% | 1 | 1 | 0% | 2,152 | 1,220 | -43% | 0 | 0 | — |
case-15 | pass→pass | 12,469 | 7,350 | -41% | 1 | 1 | 0% | 2,319 | 1,595 | -31% | 0 | 0 | — |
case-16 | pass→pass | 5,737 | 7,047 | +23% | 1 | 1 | 0% | 1,044 | 1,436 | +38% | 0 | 0 | — |
case-18 | pass→pass | 9,049 | 6,112 | -32% | 1 | 1 | 0% | 1,599 | 1,329 | -17% | 0 | 0 | — |
case-19 | pass→pass | 7,124 | 2,896 | -59% | 1 | 1 | 0% | 1,329 | 803 | -40% | 0 | 0 | — |
case-20 | pass→pass | 5,854 | 5,884 | +1% | 1 | 1 | 0% | 1,091 | 1,321 | +21% | 0 | 0 | — |
case-21 | pass→pass | 6,980 | 5,602 | -20% | 1 | 1 | 0% | 1,351 | 1,411 | +4% | 0 | 0 | — |
case-22 | pass→pass | 8,378 | 6,009 | -28% | 1 | 1 | 0% | 1,425 | 1,462 | +3% | 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 -100 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.
Other measured skills in the registry, with their headline benchmark lift.