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 Provide alternative text for objects. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.
.claude/skills/thedaviddias-object-alt/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✓→✓ | ＝ Same ✓ | -2% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | -3% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 34% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | -12% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 8% | 0% |
If an object fails to load or the user's browser doesn't support the format, alternative text ensures that the information is still accessible.
<object> elementCheck all <object> elements in the HTML to ensure they contain descriptive fallback content.
Add alternative text or a semantic fallback inside the <object> tags.
Explain how fallback content in <object> tags helps users who cannot load or view the primary object content.
Review the rendered markup and interactive states that affect Provide alternative text for objects. 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/object-alt
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 14,565 | 11,524 | -21% | 1 | 1 | 0% | 2,502 | 2,455 | -2% | 0 | 0 | — |
case-07 | pass→pass | 15,580 | 13,348 | -14% | 1 | 1 | 0% | 2,677 | 2,620 | -2% | 0 | 0 | — |
case-02 | pass→pass | 6,580 | 5,288 | -20% | 1 | 1 | 0% | 1,301 | 1,264 | -3% | 0 | 0 | — |
case-03 | pass→pass | 8,081 | 9,519 | +18% | 1 | 1 | 0% | 1,438 | 1,930 | +34% | 0 | 0 | — |
case-04 | pass→pass | 14,822 | 11,402 | -23% | 1 | 1 | 0% | 2,624 | 2,311 | -12% | 0 | 0 | — |
case-05 | pass→pass | 9,634 | 10,146 | +5% | 1 | 1 | 0% | 1,799 | 1,948 | +8% | 0 | 0 | — |
case-06 | pass→pass | 8,345 | 7,440 | -11% | 1 | 1 | 0% | 1,831 | 1,733 | -5% | 0 | 0 | — |
case-08 | pass→pass | 11,693 | 7,239 | -38% | 1 | 1 | 0% | 2,257 | 1,584 | -30% | 0 | 0 | — |
case-09 | pass→pass | 13,558 | 10,262 | -24% | 1 | 1 | 0% | 2,382 | 2,033 | -15% | 0 | 0 | — |
case-10 | pass→pass | 12,932 | 11,416 | -12% | 1 | 1 | 0% | 2,409 | 2,280 | -5% | 0 | 0 | — |
case-11 | pass→pass | 7,441 | 6,187 | -17% | 1 | 1 | 0% | 1,348 | 1,335 | -1% | 0 | 0 | — |
case-12 | pass→pass | 13,233 | 8,730 | -34% | 1 | 1 | 0% | 2,329 | 1,866 | -20% | 0 | 0 | — |
case-13 | pass→pass | 3,874 | 5,590 | +44% | 1 | 1 | 0% | 863 | 1,255 | +45% | 0 | 0 | — |
case-14 | pass→pass | 10,506 | 9,835 | -6% | 1 | 1 | 0% | 1,911 | 1,903 | -0% | 0 | 0 | — |
case-15 | pass→pass | 12,129 | 10,941 | -10% | 1 | 1 | 0% | 2,142 | 2,252 | +5% | 0 | 0 | — |
case-16 | pass→pass | 8,981 | 10,546 | +17% | 1 | 1 | 0% | 1,565 | 2,092 | +34% | 0 | 0 | — |
case-17 | pass→pass | 11,415 | 10,784 | -6% | 1 | 1 | 0% | 2,153 | 2,382 | +11% | 0 | 0 | — |
case-18 | pass→pass | 5,584 | 6,978 | +25% | 1 | 1 | 0% | 1,074 | 1,523 | +42% | 0 | 0 | — |
case-19 | pass→pass | 12,821 | 10,229 | -20% | 1 | 1 | 0% | 2,264 | 2,022 | -11% | 0 | 0 | — |
case-20 | pass→pass | 4,207 | 4,679 | +11% | 1 | 1 | 0% | 717 | 1,018 | +42% | 0 | 0 | — |
case-21 | pass→pass | 3,198 | 3,547 | +11% | 1 | 1 | 0% | 565 | 860 | +52% | 0 | 0 | — |
case-22 | pass→pass | 10,820 | 9,184 | -15% | 1 | 1 | 0% | 2,086 | 1,976 | -5% | 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 0 percentage points is the difference between those two pass rates over the 22 comparable cases.
Other measured skills in the registry, with their headline benchmark lift.