Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →视频转场与动画增强工具，提取 Remotion 的动画理念，提供高级视频转场效果和 Framer Motion 交互式动画。可与 ppt-generator、nanobanana-ppt-visualizer、ppt-roadshow-generator Skill 协同工作。
.claude/skills/anbeime-remotion-video-enhancer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 37% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 103% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 48% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 101% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 126% | 0% |
moviepy>=1.0.3 pillow>=9.0.0
bash # Ubuntu/Debian sudo apt-get install ffmpeg
# macOS brew install ffmpeg
根据协同模式，接收不同输入：
scripts/animation_planner.py：bash python scripts/animation_planner.py \ --input ./input_data \ --style dynamic \ --output ./animation_plan.json
scripts/video_transitions.py：bash python scripts/video_transitions.py \ --input ./video.mp4 \ --transitions ./animation_plan.json \ --output ./enhanced_video.mp4
scripts/html_animations.py：bash python scripts/html_animations.py \ --input ./ppt_data.json \ --template enhanced_viewer.html \ --output ./animated_viewer.html
enhanced_video.mp4animated_viewer.htmlanimation_plan.json用户请求："生成一个带高级转场的 PPT 视频"
┌─────────────────────────────────────────────────────────┐
│ ppt-generator Skill │
├─────────────────────────────────────────────────────────┤
│ 7 角色协作生成 JSON 数据 │
│ 输出：ppt_data.json │
└─────────────────────────────────────────────────────────┘
│
▼ JSON 数据
┌─────────────────────────────────────────────────────────┐
│ remotion-video-enhancer Skill │
├─────────────────────────────────────────────────────────┤
│ 1. 动画规划（animation_planner.py） │
│ 2. HTML 动画增强（html_animations.py） │
│ 3. 输出：animated_viewer.html │
└─────────────────────────────────────────────────────────┘用户请求："为生成的播放器添加 Framer Motion 动画"
┌─────────────────────────────────────────────────────────┐
│ nanobanana-ppt-visualizer Skill │
├─────────────────────────────────────────────────────────┤
│ 生成 HTML 播放器 + 图片 │
│ 输出：viewer.html, slide-*.png │
└─────────────────────────────────────────────────────────┘
│
▼ HTML 文件
┌─────────────────────────────────────────────────────────┐
│ remotion-video-enhancer Skill │
├─────────────────────────────────────────────────────────┤
│ 1. 使用 Framer Motion 增强 viewer.html │
│ 2. 添加页面过渡、元素入场、交互效果 │
│ 3. 输出：animated_viewer.html │
└─────────────────────────────────────────────────────────┘用户请求："为路演视频添加高级转场效果"
┌─────────────────────────────────────────────────────────┐
│ ppt-roadshow-generator Skill │
├─────────────────────────────────────────────────────────┤
│ 10 角色协作生成路演视频 │
│ 输出：roadshow_video.mp4 │
└─────────────────────────────────────────────────────────┘
│
▼ 视频文件
┌─────────────────────────────────────────────────────────┐
│ remotion-video-enhancer Skill │
├─────────────────────────────────────────────────────────┤
│ 1. 动画规划（animation_planner.py） │
│ 2. 视频转场增强（video_transitions.py） │
│ 3. 应用 Remotion 风格转场 │
│ 4. 输出：enhanced_roadshow_video.mp4 │
└─────────────────────────────────────────────────────────┘bashpython scripts/animation_planner.py \ --input ./ppt_data.json \ --style dynamic \ --output ./animation_plan.json
bashpython scripts/video_transitions.py \ --input ./video.mp4 \ --transitions ./animation_plan.json \ --output ./enhanced_video.mp4
bashpython scripts/html_animations.py \ --input ./ppt_data.json \ --template enhanced_viewer.html \ --output ./animated_viewer.html
json { "transitions": [ {"type": "slide", "direction": "right", "duration": 1.5}, {"type": "zoom", "scale": 1.2, "duration": 1.0} ] }
bash python scripts/video_transitions.py \ --input-dir ./videos/ \ --transitions ./animation_plan.json \ --output-dir ./enhanced_videos/
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 14,025 | 6,818 | -51% | 1 | 1 | 0% | 2,948 | 4,036 | +37% | 0 | 0 | — |
case-02 | fail→fail | 27,455 | 27,506 | +0% | 1 | 1 | 0% | 6,203 | 8,784 | +42% | 0 | 0 | — |
case-03 | fail→pass | 12,382 | 14,572 | +18% | 1 | 1 | 0% | 2,696 | 5,475 | +103% | 0 | 0 | — |
case-04 | pass→pass | 8,749 | 2,597 | -70% | 1 | 1 | 0% | 1,451 | 3,043 | +110% | 0 | 0 | — |
case-05 | pass→pass | 7,357 | 3,660 | -50% | 1 | 1 | 0% | 1,305 | 3,081 | +136% | 0 | 0 | — |
case-10 | fail→pass | 10,580 | 3,470 | -67% | 1 | 1 | 0% | 2,183 | 3,233 | +48% | 0 | 0 | — |
case-06 | fail→pass | 9,477 | 2,784 | -71% | 1 | 1 | 0% | 1,555 | 3,127 | +101% | 0 | 0 | — |
case-07 | fail→pass | 7,500 | 3,183 | -58% | 1 | 1 | 0% | 1,408 | 3,186 | +126% | 0 | 0 | — |
case-08 | fail→pass | 8,245 | 3,661 | -56% | 1 | 1 | 0% | 1,486 | 3,201 | +115% | 0 | 0 | — |
case-09 | fail→fail | 29,783 | 4,705 | -84% | 1 | 1 | 0% | 2,487 | 3,621 | +46% | 0 | 0 | — |
case-11 | fail→pass | 24,289 | 6,299 | -74% | 1 | 1 | 0% | 1,161 | 3,559 | +207% | 0 | 0 | — |
case-12 | pass→pass | 10,456 | 3,256 | -69% | 1 | 1 | 0% | 1,811 | 3,300 | +82% | 0 | 0 | — |
case-13 | fail→pass | 8,461 | 3,670 | -57% | 1 | 1 | 0% | 1,320 | 3,291 | +149% | 0 | 0 | — |
case-14 | pass→pass | 7,215 | 2,392 | -67% | 1 | 1 | 0% | 1,266 | 2,929 | +131% | 0 | 0 | — |
case-15 | fail→pass | 12,045 | 5,218 | -57% | 1 | 1 | 0% | 2,557 | 3,435 | +34% | 0 | 0 | — |
case-16 | pass→pass | 24,965 | 7,015 | -72% | 1 | 1 | 0% | 1,821 | 3,973 | +118% | 0 | 0 | — |
case-17 | fail→pass | 9,686 | 3,440 | -64% | 1 | 1 | 0% | 1,645 | 3,211 | +95% | 0 | 0 | — |
case-18 | fail→pass | 15,701 | 7,657 | -51% | 1 | 1 | 0% | 2,279 | 3,934 | +73% | 0 | 0 | — |
case-19 | fail→pass | 9,034 | 1,294 | -86% | 1 | 1 | 0% | 1,603 | 2,767 | +73% | 0 | 0 | — |
case-20 | fail→pass | 10,204 | 3,506 | -66% | 1 | 1 | 0% | 1,977 | 3,263 | +65% | 0 | 0 | — |
case-21 | fail→fail | 14,608 | 12,607 | -14% | 1 | 1 | 0% | 2,511 | 5,198 | +107% | 0 | 0 | — |
case-22 | fail→fail | 18,289 | 11,748 | -36% | 1 | 1 | 0% | 2,493 | 4,626 | +86% | 0 | 0 | — |
case-23 | fail→fail | 29,133 | 32,621 | +12% | 1 | 1 | 0% | 6,187 | 8,768 | +42% | 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 22 counted toward the lift figure. The other 1 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 +57 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.