Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use this plugin when the user wants a "Product Promo · 30s" HyperFrames motion video — Multi-scene 30-second product promo: problem-type intro, brand reveal, benefits flowchart, product surfaces, value pillars, foundation, CTA outro. Forked from Nate Herk's hyperframes-student-kit (linear-promo-30s); brand-specific copy + assets replaced with generic placeholders.
.claude/skills/nexu-io-video-template-frame-product-promo-30s/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-10 | ✗→✓ | ▲ Improved | -24% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -23% | 0% |
Multi-scene 30-second product promo: problem-type intro, brand reveal, benefits flowchart, product surfaces, value pillars, foundation, CTA outro. Forked from Nate Herk's hyperframes-student-kit (linear-promo-30s); brand-specific copy + assets replaced with generic placeholders.
A HyperFrames-ready HTML + CSS + GSAP motion composition, bundled under source/. It renders deterministically to MP4 / WEBM at 16:9, default 30s, 30fps.
Best for: 30-second product promo · B2B SaaS launch · Multi-feature reel with sound
source/index.html to understand the named layers and the animation timeline.source/; do not introduce external network assets that would break a headless render.Source: html-video templates/frame-product-promo-30s (license MIT). Forked from Nate Herk — https://github.com/nateherkai/hyperframes-student-kit/tree/main/video-projects/linear-promo-30s.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-10 | fail→pass | 10,029 | 4,969 | -50% | 1 | 1 | 0% | 1,491 | 1,128 | -24% | 0 | 0 | — |
case-20 | pass→pass | 10,988 | 4,559 | -59% | 1 | 1 | 0% | 1,664 | 1,076 | -35% | 0 | 0 | — |
case-01 | fail→fail | 46,131 | 40,090 | -13% | 1 | 1 | 0% | 8,270 | 8,592 | +4% | 0 | 0 | — |
case-02 | fail→pass | 36,247 | 37,678 | +4% | 1 | 1 | 0% | 8,247 | 8,569 | +4% | 0 | 0 | — |
case-03 | fail→fail | 33,735 | 36,912 | +9% | 1 | 1 | 0% | 7,154 | 8,580 | +20% | 0 | 0 | — |
case-04 | fail→pass | 13,672 | 11,982 | -12% | 1 | 1 | 0% | 2,331 | 2,516 | +8% | 0 | 0 | — |
case-09 | pass→pass | 10,442 | 6,684 | -36% | 1 | 1 | 0% | 1,737 | 1,400 | -19% | 0 | 0 | — |
case-05 | pass→pass | 14,340 | 7,890 | -45% | 1 | 1 | 0% | 2,401 | 1,671 | -30% | 0 | 0 | — |
case-06 | fail→pass | 13,056 | 9,664 | -26% | 1 | 1 | 0% | 2,183 | 2,083 | -5% | 0 | 0 | — |
case-07 | pass→pass | 10,955 | 2,158 | -80% | 1 | 1 | 0% | 1,993 | 691 | -65% | 0 | 0 | — |
case-08 | fail→pass | 8,414 | 4,154 | -51% | 1 | 1 | 0% | 1,282 | 985 | -23% | 0 | 0 | — |
case-11 | fail→pass | 13,870 | 5,509 | -60% | 1 | 1 | 0% | 2,357 | 1,270 | -46% | 0 | 0 | — |
case-12 | fail→pass | 17,964 | 9,715 | -46% | 1 | 1 | 0% | 2,717 | 1,829 | -33% | 0 | 0 | — |
case-13 | pass→pass | 14,283 | 15,794 | +11% | 1 | 1 | 0% | 3,018 | 3,689 | +22% | 0 | 0 | — |
case-14 | pass→pass | 10,369 | 5,278 | -49% | 1 | 1 | 0% | 1,853 | 1,290 | -30% | 0 | 0 | — |
case-19 | fail→pass | 12,167 | 2,519 | -79% | 1 | 1 | 0% | 2,058 | 746 | -64% | 0 | 0 | — |
case-15 | pass→fail | 26,590 | 37,472 | +41% | 1 | 1 | 0% | 5,699 | 8,550 | +50% | 0 | 0 | — |
case-16 | fail→pass | 12,550 | 6,394 | -49% | 1 | 1 | 0% | 1,966 | 1,357 | -31% | 0 | 0 | — |
case-17 | fail→pass | 13,349 | 5,794 | -57% | 1 | 1 | 0% | 2,119 | 1,253 | -41% | 0 | 0 | — |
case-18 | fail→pass | 8,404 | 6,628 | -21% | 1 | 1 | 0% | 1,278 | 1,287 | +1% | 0 | 0 | — |
case-21 | fail→fail | 12,711 | 9,455 | -26% | 1 | 1 | 0% | 1,817 | 1,793 | -1% | 0 | 0 | — |
case-22 | fail→pass | 14,414 | 7,530 | -48% | 1 | 1 | 0% | 2,226 | 1,591 | -29% | 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 +50 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 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.