Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Skeleton placeholders with a soft sweeping shimmer while content loads. Use to fill space for cards/lists/profiles that are still loading and make the wait feel shorter. Honors prefers-reduced-motion (static skeleton). Only show while real content is loading — never as decoration.
.claude/skills/nexu-io-loading-shimmer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -48% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -70% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -69% | 0% |
Skeleton placeholders with a soft sweeping highlight. Part of motion-anything; obeys MOTION-SPEC.md.
loading-shimmer.css and link it.data-skeleton to placeholder blocks (give each a width/height).prefers-reduced-motion: static skeleton, no sweep. The sweep uses transform only (GPU-safe).| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 18,653 | 14,016 | -25% | 1 | 1 | 0% | 3,301 | 3,059 | -7% | 0 | 0 | — |
case-02 | fail→fail | 20,474 | 12,698 | -38% | 1 | 1 | 0% | 3,481 | 2,404 | -31% | 0 | 0 | — |
case-03 | fail→pass | 19,516 | 10,791 | -45% | 1 | 1 | 0% | 3,684 | 2,189 | -41% | 0 | 0 | — |
case-04 | pass→pass | 11,289 | 6,437 | -43% | 1 | 1 | 0% | 1,949 | 1,290 | -34% | 0 | 0 | — |
case-05 | pass→pass | 13,313 | 6,098 | -54% | 1 | 1 | 0% | 2,078 | 1,189 | -43% | 0 | 0 | — |
case-06 | pass→pass | 9,523 | 3,430 | -64% | 1 | 1 | 0% | 1,474 | 684 | -54% | 0 | 0 | — |
case-07 | fail→pass | 13,540 | 5,177 | -62% | 1 | 1 | 0% | 1,926 | 1,000 | -48% | 0 | 0 | — |
case-08 | pass→pass | 12,448 | 6,519 | -48% | 1 | 1 | 0% | 2,209 | 1,366 | -38% | 0 | 0 | — |
case-09 | pass→pass | 8,844 | 2,229 | -75% | 1 | 1 | 0% | 1,471 | 486 | -67% | 0 | 0 | — |
case-10 | fail→pass | 7,401 | 1,400 | -81% | 1 | 1 | 0% | 1,231 | 364 | -70% | 0 | 0 | — |
case-11 | pass→pass | 3,838 | 2,552 | -34% | 1 | 1 | 0% | 639 | 561 | -12% | 0 | 0 | — |
case-12 | pass→pass | 10,790 | 2,641 | -76% | 1 | 1 | 0% | 1,697 | 554 | -67% | 0 | 0 | — |
case-13 | pass→pass | 11,925 | 2,638 | -78% | 1 | 1 | 0% | 1,806 | 537 | -70% | 0 | 0 | — |
case-14 | pass→pass | 8,186 | 1,594 | -81% | 1 | 1 | 0% | 1,388 | 389 | -72% | 0 | 0 | — |
case-15 | pass→pass | 11,161 | 6,406 | -43% | 1 | 1 | 0% | 1,884 | 1,228 | -35% | 0 | 0 | — |
case-16 | pass→pass | 11,084 | 5,418 | -51% | 1 | 1 | 0% | 1,765 | 932 | -47% | 0 | 0 | — |
case-17 | pass→pass | 13,871 | 11,777 | -15% | 1 | 1 | 0% | 2,088 | 2,068 | -1% | 0 | 0 | — |
case-18 | fail→pass | 13,717 | 3,281 | -76% | 1 | 1 | 0% | 2,387 | 732 | -69% | 0 | 0 | — |
case-19 | pass→pass | 10,409 | 3,340 | -68% | 1 | 1 | 0% | 1,639 | 674 | -59% | 0 | 0 | — |
case-20 | pass→pass | 11,966 | 5,982 | -50% | 1 | 1 | 0% | 1,828 | 1,159 | -37% | 0 | 0 | — |
case-21 | pass→pass | 5,780 | 3,735 | -35% | 1 | 1 | 0% | 962 | 777 | -19% | 0 | 0 | — |
case-22 | fail→pass | 12,154 | 8,354 | -31% | 1 | 1 | 0% | 1,824 | 1,509 | -17% | 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.