Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Standardized guidelines and patterns for Frontend Ui Tailwind Standards.
.claude/skills/valec3-frontend-ui-tailwind-standards/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 78% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -34% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -40% | 0% |
typescript// Recommended order: // Layout → Display → Positioning → Box Model → Typography → Visual → Misc <div className=" flex flex-col items-center justify-between w-full max-w-md px-4 py-2 text-lg font-bold bg-white dark:bg-gray-800 rounded-lg shadow-md hover:shadow-lg transition-shadow "/>
typescript// Mobile first <div className=" text-sm md:text-base lg:text-lg xl:text-xl "/>
typescript<div className="bg-white dark:bg-gray-900"> <h1 className="text-gray-900 dark:text-white">Title</h1> </div>
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-16 | pass→pass | 11,447 | 6,079 | -47% | 1 | 1 | 0% | 1,946 | 1,425 | -27% | 0 | 0 | — |
case-04 | pass→pass | 12,079 | 8,943 | -26% | 1 | 1 | 0% | 2,316 | 2,022 | -13% | 0 | 0 | — |
case-10 | pass→pass | 7,777 | 3,561 | -54% | 1 | 1 | 0% | 1,480 | 1,054 | -29% | 0 | 0 | — |
case-01 | fail→pass | 15,493 | 11,784 | -24% | 1 | 1 | 0% | 3,532 | 2,878 | -19% | 0 | 0 | — |
case-02 | fail→pass | 8,815 | 12,694 | +44% | 1 | 1 | 0% | 1,763 | 3,139 | +78% | 0 | 0 | — |
case-03 | fail→pass | 19,529 | 13,111 | -33% | 1 | 1 | 0% | 3,448 | 3,336 | -3% | 0 | 0 | — |
case-05 | pass→pass | 12,408 | 7,430 | -40% | 1 | 1 | 0% | 2,040 | 1,746 | -14% | 0 | 0 | — |
case-06 | fail→fail | 3,717 | 4,282 | +15% | 1 | 1 | 0% | 729 | 1,037 | +42% | 0 | 0 | — |
case-07 | fail→pass | 13,947 | 5,960 | -57% | 1 | 1 | 0% | 2,219 | 1,464 | -34% | 0 | 0 | — |
case-08 | pass→pass | 10,610 | 5,851 | -45% | 1 | 1 | 0% | 2,152 | 1,052 | -51% | 0 | 0 | — |
case-09 | pass→pass | 13,475 | 8,189 | -39% | 1 | 1 | 0% | 2,310 | 1,765 | -24% | 0 | 0 | — |
case-11 | pass→pass | 2,948 | 2,993 | +2% | 1 | 1 | 0% | 502 | 842 | +68% | 0 | 0 | — |
case-12 | pass→pass | 12,377 | 8,756 | -29% | 1 | 1 | 0% | 2,156 | 1,962 | -9% | 0 | 0 | — |
case-13 | pass→pass | 8,726 | 5,781 | -34% | 1 | 1 | 0% | 1,795 | 1,364 | -24% | 0 | 0 | — |
case-14 | pass→pass | 14,574 | 12,056 | -17% | 1 | 1 | 0% | 2,631 | 2,590 | -2% | 0 | 0 | — |
case-15 | fail→pass | 9,439 | 3,571 | -62% | 1 | 1 | 0% | 1,779 | 1,065 | -40% | 0 | 0 | — |
case-17 | fail→pass | 3,758 | 3,525 | -6% | 1 | 1 | 0% | 777 | 989 | +27% | 0 | 0 | — |
case-18 | pass→pass | 3,439 | 3,527 | +3% | 1 | 1 | 0% | 642 | 769 | +20% | 0 | 0 | — |
case-19 | pass→pass | 9,504 | 4,654 | -51% | 1 | 1 | 0% | 1,863 | 1,323 | -29% | 0 | 0 | — |
case-20 | pass→pass | 11,062 | 5,517 | -50% | 1 | 1 | 0% | 2,063 | 1,409 | -32% | 0 | 0 | — |
case-21 | fail→pass | 7,157 | 5,750 | -20% | 1 | 1 | 0% | 1,626 | 1,647 | +1% | 0 | 0 | — |
case-22 | pass→pass | 12,450 | 9,763 | -22% | 1 | 1 | 0% | 2,316 | 2,251 | -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 +32 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.