Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when creating UI designs to avoid generic "AI slop" aesthetics. Enforces distinctive typography, cohesive color systems, purposeful motion, and atmospheric backgrounds. Critical for landing pages, dashboards, and branded interfaces.
.claude/skills/aiskillstore-frontend-aesthetics/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 4% | 0% |
You tend to converge toward generic, "on distribution" outputs. In frontend design,this creates what users call the "AI slop" aesthetic. Avoid this: make creative,distinctive frontends that surprise and delight.
Focus on:
Avoid generic AI-generated aesthetics:
Interpret creatively and make unexpected choices that feel genuinely designed for the context. Vary between light and dark themes, different fonts, different aesthetics. You still tend to converge on common choices (Space Grotesk, for example) across generations. Avoid this: it is critical that you think outside the box!
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 42,790 | 41,961 | -2% | 1 | 1 | 0% | 8,251 | 8,594 | +4% | 0 | 0 | — |
case-02 | fail→pass | 36,795 | 38,869 | +6% | 1 | 1 | 0% | 8,244 | 8,587 | +4% | 0 | 0 | — |
case-03 | pass→pass | 38,538 | 37,879 | -2% | 1 | 1 | 0% | 8,237 | 8,580 | +4% | 0 | 0 | — |
case-04 | pass→pass | 39,773 | 36,931 | -7% | 1 | 1 | 0% | 8,235 | 8,578 | +4% | 0 | 0 | — |
case-05 | pass→pass | 40,692 | 39,064 | -4% | 1 | 1 | 0% | 8,236 | 8,579 | +4% | 0 | 0 | — |
case-06 | pass→pass | 37,823 | 40,022 | +6% | 1 | 1 | 0% | 8,235 | 8,578 | +4% | 0 | 0 | — |
case-07 | pass→pass | 43,496 | 40,981 | -6% | 1 | 1 | 0% | 8,224 | 8,567 | +4% | 0 | 0 | — |
case-08 | pass→pass | 39,222 | 42,633 | +9% | 1 | 1 | 0% | 8,228 | 8,571 | +4% | 0 | 0 | — |
case-09 | pass→pass | 39,742 | 57,819 | +45% | 1 | 1 | 0% | 7,342 | 8,576 | +17% | 0 | 0 | — |
case-10 | fail→pass | 40,807 | 42,866 | +5% | 1 | 1 | 0% | 8,226 | 8,569 | +4% | 0 | 0 | — |
case-11 | pass→pass | 75,474 | 51,646 | -32% | 1 | 1 | 0% | 8,227 | 8,570 | +4% | 0 | 0 | — |
case-12 | pass→pass | 42,570 | 41,487 | -3% | 1 | 1 | 0% | 8,229 | 8,572 | +4% | 0 | 0 | — |
case-13 | pass→pass | 41,534 | 52,287 | +26% | 1 | 1 | 0% | 8,219 | 8,562 | +4% | 0 | 0 | — |
case-14 | fail→pass | 59,614 | 59,412 | -0% | 1 | 1 | 0% | 8,223 | 8,566 | +4% | 0 | 0 | — |
case-15 | pass→pass | 45,894 | 45,334 | -1% | 1 | 1 | 0% | 8,232 | 8,575 | +4% | 0 | 0 | — |
case-16 | pass→pass | 53,969 | 104,882 | +94% | 1 | 1 | 0% | 8,225 | 8,568 | +4% | 0 | 0 | — |
case-17 | pass→pass | 41,529 | 60,910 | +47% | 1 | 1 | 0% | 8,221 | 8,564 | +4% | 0 | 0 | — |
case-18 | pass→pass | 56,004 | 59,915 | +7% | 1 | 1 | 0% | 7,400 | 8,572 | +16% | 0 | 0 | — |
case-19 | pass→pass | 49,954 | 66,937 | +34% | 1 | 1 | 0% | 8,227 | 8,570 | +4% | 0 | 0 | — |
case-20 | pass→pass | 9,774 | 17,604 | +80% | 1 | 1 | 0% | 904 | 3,023 | +234% | 0 | 0 | — |
case-21 | pass→pass | 20,398 | 36,010 | +77% | 1 | 1 | 0% | 3,249 | 8,565 | +164% | 0 | 0 | — |
case-22 | fail→fail | 21,794 | 49,620 | +128% | 1 | 1 | 0% | 3,604 | 8,566 | +138% | 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 +18 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.