Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Turn a reference video into a super detailed recreation or inspiration prompt. Use when the user provides, mentions, uploads, links, or points to a video and asks to analyze the design, UI, animations, transitions, scroll interactions, typography, colors, assets, WebGL/Three.js, storytelling, section-by-section behavior, or to create a prompt/article that recreates the page, app, interaction, or motion system.
.claude/skills/mengto-video-to-superprompt/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | 178% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 56% | 0% |
| case-04 | ✓→✗ | ▼ Worse | 75% | 0% |
| case-19 | ✓→✗ | ▼ Worse | 16% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 168% | 0% |
Convert any usable reference video into a builder-ready prompt that captures what the video shows, how it moves, how it should be rebuilt, and what assets or generated media are needed. The default output is one paste-ready prompt unless the user asks for an article, asset pack, or implementation.
ffprobe for duration, dimensions, frame rate, codec, and size.ffmpeg, favoring timeline beats over uniform thumbnails.bash ffprobe -v error -show_entries format=duration,size:stream=width,height,r_frame_rate -of json "$VIDEO" mkdir -p /tmp/video-frames ffmpeg -y -i "$VIDEO" -vf fps=1 /tmp/video-frames/frame-%03d.jpg
text block for the paste-ready prompt unless the user asks for another format.content.md plus local frame/video evidence, manifest, and prompts. Follow the current repo article conventions.video.currentTime, parallax layer, opacity reveal, transform, mask, shader, particle field, hover state, or carousel physics.references/superprompt-template.md when writing the final prompt from scratch or when the user asks for the “full detailed prompt.”| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 12,152 | 4,835 | -60% | 1 | 1 | 0% | 2,004 | 1,477 | -26% | 0 | 0 | — |
case-02 | fail→fail | 18,293 | 28,027 | +53% | 1 | 1 | 0% | 3,310 | 5,978 | +81% | 0 | 0 | — |
case-03 | fail→fail | 14,951 | 4,745 | -68% | 1 | 1 | 0% | 2,565 | 1,331 | -48% | 0 | 0 | — |
case-04 | pass→fail | 4,964 | 3,697 | -26% | 1 | 1 | 0% | 1,061 | 1,860 | +75% | 0 | 0 | — |
case-05 | pass→pass | 4,055 | 3,612 | -11% | 1 | 1 | 0% | 664 | 1,782 | +168% | 0 | 0 | — |
case-06 | pass→pass | 3,439 | 3,441 | +0% | 1 | 1 | 0% | 664 | 1,718 | +159% | 0 | 0 | — |
case-07 | pass→pass | 9,250 | 6,383 | -31% | 1 | 1 | 0% | 1,780 | 2,472 | +39% | 0 | 0 | — |
case-08 | pass→pass | 15,882 | 18,936 | +19% | 1 | 1 | 0% | 2,938 | 4,843 | +65% | 0 | 0 | — |
case-09 | fail→fail | 8,522 | 14,896 | +75% | 1 | 1 | 0% | 1,569 | 3,353 | +114% | 0 | 0 | — |
case-10 | fail→fail | 8,690 | 4,662 | -46% | 1 | 1 | 0% | 746 | 1,389 | +86% | 0 | 0 | — |
case-11 | fail→pass | 9,204 | 18,359 | +99% | 1 | 1 | 0% | 1,637 | 4,553 | +178% | 0 | 0 | — |
case-12 | fail→fail | 18,637 | 4,476 | -76% | 1 | 1 | 0% | 3,622 | 1,439 | -60% | 0 | 0 | — |
case-13 | pass→pass | 26,808 | 28,219 | +5% | 1 | 1 | 0% | 5,331 | 6,401 | +20% | 0 | 0 | — |
case-14 | fail→fail | 16,933 | 4,680 | -72% | 1 | 1 | 0% | 1,882 | 1,405 | -25% | 0 | 0 | — |
case-15 | pass→pass | 16,117 | 23,327 | +45% | 1 | 1 | 0% | 2,770 | 4,736 | +71% | 0 | 0 | — |
case-16 | fail→pass | 11,194 | 10,855 | -3% | 1 | 1 | 0% | 1,984 | 3,093 | +56% | 0 | 0 | — |
case-17 | pass→pass | 11,753 | 9,907 | -16% | 1 | 1 | 0% | 2,139 | 2,871 | +34% | 0 | 0 | — |
case-18 | pass→pass | 10,906 | 6,174 | -43% | 1 | 1 | 0% | 1,881 | 2,051 | +9% | 0 | 0 | — |
case-19 | pass→fail | 7,844 | 7,448 | -5% | 1 | 1 | 0% | 1,430 | 1,659 | +16% | 0 | 0 | — |
case-20 | pass→pass | 13,823 | 10,745 | -22% | 1 | 1 | 0% | 2,619 | 2,919 | +11% | 0 | 0 | — |
case-21 | pass→pass | 11,787 | 15,291 | +30% | 1 | 1 | 0% | 1,976 | 3,876 | +96% | 0 | 0 | — |
case-22 | fail→fail | 9,652 | 5,148 | -47% | 1 | 1 | 0% | 1,737 | 2,133 | +23% | 0 | 0 | — |
case-23 | pass→pass | 9,454 | 2,997 | -68% | 1 | 1 | 0% | 1,645 | 1,722 | +5% | 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. 23 cases were attempted, and 18 counted toward the lift figure. The other 5 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 0 percentage points is the difference between those two pass rates over the 18 comparable cases. 3 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.