Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Art-direct and implement distinctive, motion-rich marketing, editorial, portfolio, and landing websites with original reference-inspired imagery, standout heroes, GSAP choreography, one smooth-scroll engine, optional Three.js shaders, honest icon and logo sourcing, photo avatars, accessibility, and performance safeguards. Use when a user asks for an Awwwards-quality, premium, cinematic, interactive, high-concept, or motion-led website, or explicitly requests this visual and motion system.
.claude/skills/mengto-build-awwwards-quality-sites/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-10 | ✗→✓ | ▲ Improved | 68% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 55% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 33% | 0% |
| case-22 | ✗→✓ | ▲ Improved | 25% | 0% |
Build a cohesive, memorable site whose visual idea, media, typography, and motion tell the same story. Treat “Awwwards quality” as an acceptance bar, never as an award or recognition claim.
prefers-reduced-motion: reduce. Render final states immediately instead of merely shortening animations.prefers-reduced-motion behavior.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | pass→pass | 14,205 | 16,725 | +18% | 1 | 1 | 0% | 3,014 | 4,933 | +64% | 0 | 0 | — |
case-01 | fail→fail | 28,415 | 30,055 | +6% | 1 | 1 | 0% | 6,228 | 7,544 | +21% | 0 | 0 | — |
case-02 | fail→fail | 36,405 | 10,043 | -72% | 1 | 1 | 0% | 6,223 | 2,430 | -61% | 0 | 0 | — |
case-03 | fail→fail | 28,704 | 32,204 | +12% | 1 | 1 | 0% | 6,227 | 7,543 | +21% | 0 | 0 | — |
case-04 | pass→pass | 13,435 | 8,414 | -37% | 1 | 1 | 0% | 2,637 | 3,129 | +19% | 0 | 0 | — |
case-06 | pass→pass | 8,287 | 21,354 | +158% | 1 | 1 | 0% | 1,890 | 6,263 | +231% | 0 | 0 | — |
case-07 | fail→fail | 27,326 | 24,810 | -9% | 1 | 1 | 0% | 6,215 | 7,531 | +21% | 0 | 0 | — |
case-08 | pass→fail | 26,211 | 28,451 | +9% | 1 | 1 | 0% | 5,778 | 7,516 | +30% | 0 | 0 | — |
case-09 | pass→fail | 15,723 | 33,701 | +114% | 1 | 1 | 0% | 3,137 | 7,491 | +139% | 0 | 0 | — |
case-10 | fail→pass | 20,378 | 27,098 | +33% | 1 | 1 | 0% | 4,244 | 7,118 | +68% | 0 | 0 | — |
case-11 | fail→pass | 25,293 | 25,014 | -1% | 1 | 1 | 0% | 6,085 | 7,521 | +24% | 0 | 0 | — |
case-12 | fail→fail | 26,270 | 11,283 | -57% | 1 | 1 | 0% | 6,170 | 2,042 | -67% | 0 | 0 | — |
case-13 | pass→fail | 21,299 | 12,138 | -43% | 1 | 1 | 0% | 4,655 | 2,240 | -52% | 0 | 0 | — |
case-14 | fail→fail | 26,230 | 8,054 | -69% | 1 | 1 | 0% | 6,177 | 1,643 | -73% | 0 | 0 | — |
case-15 | fail→fail | 21,672 | 11,542 | -47% | 1 | 1 | 0% | 4,957 | 1,953 | -61% | 0 | 0 | — |
case-16 | fail→fail | 22,038 | 11,498 | -48% | 1 | 1 | 0% | 5,055 | 3,021 | -40% | 0 | 0 | — |
case-17 | pass→pass | 20,180 | 27,144 | +35% | 1 | 1 | 0% | 4,227 | 7,494 | +77% | 0 | 0 | — |
case-18 | fail→pass | 16,934 | 20,398 | +20% | 1 | 1 | 0% | 3,454 | 5,350 | +55% | 0 | 0 | — |
case-19 | pass→pass | 24,744 | 27,908 | +13% | 1 | 1 | 0% | 5,202 | 7,493 | +44% | 0 | 0 | — |
case-20 | fail→pass | 15,920 | 12,014 | -25% | 1 | 1 | 0% | 2,374 | 3,164 | +33% | 0 | 0 | — |
case-21 | pass→pass | 27,554 | 35,928 | +30% | 1 | 1 | 0% | 5,689 | 7,507 | +32% | 0 | 0 | — |
case-22 | fail→pass | 16,337 | 13,214 | -19% | 1 | 1 | 0% | 2,854 | 3,554 | +25% | 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, and 18 counted toward the lift figure. The other 4 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +9 percentage points is the difference between those two pass rates over the 18 comparable cases. 6 cases got worse with the skill loaded, and they are included in that figure.
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.