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 Include a skip navigation link. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.
.claude/skills/thedaviddias-skip-navigation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-21 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | -10% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | -21% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 33% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 3% | 0% |
Skip links save keyboard and screen reader users from tabbing through 50+ navigation items on every page visit—turning a frustrating experience into an efficient one.
Verify that a 'Skip to main content' link is present and functional at the beginning of the page.
Add a visually hidden skip link that becomes visible on focus and links to the main content area.
Explain how skip links improve efficiency for keyboard users by allowing them to bypass repeated navigation elements.
Review the rendered markup and interactive states that affect Include a skip navigation link. 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/skip-navigation
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 8,975 | 6,452 | -28% | 1 | 1 | 0% | 1,689 | 1,523 | -10% | 0 | 0 | — |
case-02 | pass→pass | 5,794 | 2,900 | -50% | 1 | 1 | 0% | 991 | 783 | -21% | 0 | 0 | — |
case-03 | pass→pass | 3,253 | 2,868 | -12% | 1 | 1 | 0% | 546 | 728 | +33% | 0 | 0 | — |
case-04 | pass→pass | 11,104 | 9,684 | -13% | 1 | 1 | 0% | 2,174 | 2,239 | +3% | 0 | 0 | — |
case-05 | pass→pass | 7,864 | 4,115 | -48% | 1 | 1 | 0% | 1,366 | 1,020 | -25% | 0 | 0 | — |
case-06 | pass→pass | 6,355 | 5,239 | -18% | 1 | 1 | 0% | 1,124 | 1,131 | +1% | 0 | 0 | — |
case-19 | pass→pass | 7,822 | 5,364 | -31% | 1 | 1 | 0% | 1,431 | 1,188 | -17% | 0 | 0 | — |
case-07 | pass→pass | 9,947 | 4,653 | -53% | 1 | 1 | 0% | 1,643 | 1,049 | -36% | 0 | 0 | — |
case-08 | pass→pass | 7,829 | 5,432 | -31% | 1 | 1 | 0% | 1,365 | 1,268 | -7% | 0 | 0 | — |
case-09 | pass→pass | 3,393 | 3,316 | -2% | 1 | 1 | 0% | 561 | 808 | +44% | 0 | 0 | — |
case-10 | pass→pass | 3,461 | 3,275 | -5% | 1 | 1 | 0% | 582 | 755 | +30% | 0 | 0 | — |
case-11 | pass→pass | 9,272 | 6,991 | -25% | 1 | 1 | 0% | 1,723 | 1,495 | -13% | 0 | 0 | — |
case-12 | pass→pass | 8,938 | 6,525 | -27% | 1 | 1 | 0% | 1,439 | 1,356 | -6% | 0 | 0 | — |
case-13 | pass→pass | 3,496 | 3,134 | -10% | 1 | 1 | 0% | 592 | 789 | +33% | 0 | 0 | — |
case-14 | pass→pass | 13,344 | 8,279 | -38% | 1 | 1 | 0% | 2,332 | 1,748 | -25% | 0 | 0 | — |
case-15 | pass→pass | 11,400 | 8,034 | -30% | 1 | 1 | 0% | 1,934 | 1,589 | -18% | 0 | 0 | — |
case-16 | pass→pass | 4,285 | 4,025 | -6% | 1 | 1 | 0% | 772 | 992 | +28% | 0 | 0 | — |
case-17 | pass→pass | 10,209 | 7,232 | -29% | 1 | 1 | 0% | 1,840 | 1,584 | -14% | 0 | 0 | — |
case-18 | pass→pass | 11,196 | 10,312 | -8% | 1 | 1 | 0% | 1,792 | 1,921 | +7% | 0 | 0 | — |
case-20 | pass→pass | 10,775 | 11,961 | +11% | 1 | 1 | 0% | 2,070 | 2,671 | +29% | 0 | 0 | — |
case-21 | fail→pass | 13,562 | 12,023 | -11% | 1 | 1 | 0% | 2,388 | 2,390 | +0% | 0 | 0 | — |
case-22 | pass→pass | 9,642 | 7,421 | -23% | 1 | 1 | 0% | 1,954 | 1,683 | -14% | 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.