video-shortform
Short-form video generation skill — 3-10 second clips for product reveals, motion teasers, ambient loops. Defaults to Seedance 2 but works the same with Kling 3 / 4, Veo 3 or Sora 2. Output is one MP4 saved to the project folder. When the workspace also ships an interactive-video / hyperframes skill, prefer composing several short shots into a single timeline rather than one long monolithic clip.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 1.1k
- Forks
- 104
01 前言 Front Matter
- od
- { "mode": "video", "preview": { "type": "html", "entry": "example.html" }, "surface": "video", "scenario": "marketing", "design_system": { "requires": false }, "example_prompt": "5-second product reveal — ceramic coffee mug rotating on a soft\npaper backdrop, warm side-light from camera-left, micro dust motes\ndrifting through the beam. Cinematic, 16:9, slow drift on the camera." }
- name
- video-shortform
- triggers
- [ "video", "clip", "shortform", "reel", "短视频", "动效" ]
- description
- Short-form video generation skill — 3-10 second clips for product reveals, motion teasers, ambient loops. Defaults to Seedance 2 but works the same with Kling 3 / 4, Veo 3 or Sora 2. Output is one MP4 saved to the project folder. When the workspace also ships an interactive-video / hyperframes skill, prefer composing several short shots into a single timeline rather than one long monolithic clip.
03 SKILL.md 正文
Video Shortform Skill
Short-form (≤ 10s) is the sweet spot for current text-to-video models — they're great at one shot with one idea, weaker at multi-cut narratives. Plan one shot per call.
Special case: hyperframes-html is not a photoreal text-to-video
model. It's a local HTML-to-MP4 renderer. For that model, do not roleplay
cinematography or "real-world" camera physics. Treat the brief as a motion
design card / title-frame / product interstitial, ask at most one
clarifying question, then dispatch immediately.
Resource map
video-shortform/
├── SKILL.md
└── example.html
Workflow
Step 0 — Read the project metadata
videoModel, videoLength (seconds), videoAspect. These are
hard-locks — clamp the prompt to whatever the chosen model supports
(Seedance 2 caps at 10s; Kling 4 supports up to 10s + image-to-video;
Veo 3 supports 8s with audio).
Step 1 — Plan the shot
Write the shotlist BEFORE calling the model:
| Slot | Content |
|---|---|
| Subject | What's in frame? |
| Camera | Static / pan / push-in / orbit? |
| Lighting | Key direction + temperature |
| Motion | What moves, at what pace? Subject motion vs camera motion. |
| Sound | Ambient bed? (only if the model supports audio) |
Normally, show this to the user as a one-sentence plan before dispatching — they can redirect cheaply.
For hyperframes-html, skip the extra pre-dispatch narration once the
user has answered the discovery form. Collapse the plan into the actual
generation prompt and dispatch immediately.
Step 2 — Compose the prompt
Use the format the upstream model prefers (Seedance: motion + camera +
mood; Kling: subject + camera + style; Veo: subject + cinematography +
sound). Bind the project's videoAspect and videoLength directly to
the API parameters; never put them in prose.
For hyperframes-html, write a concise motion-design brief instead of a
camera-realism prompt. Focus on subject, layout, palette, motion
character, and overall tone. Do not spend turns narrating environment
checks, missing side files, or "I am about to dispatch" status updates.
Step 3 — Dispatch via the media contract
Use the unified dispatcher — do not call provider APIs by hand:
"$OD_NODE_BIN" "$OD_BIN" media generate \
--project "$OD_PROJECT_ID" \
--surface video \
--model "<videoModel from metadata>" \
--aspect "<videoAspect from metadata>" \
--length <videoLength seconds> \
--output "<short-slug>-<seconds>s.mp4" \
--prompt "<assembled shot prompt from Step 2>"
The command prints one line of JSON: {"file": {"name": "...", ...}}.
The bytes land in the project; the FileViewer plays it automatically.
Step 4 — Hand off
Reply with: shot summary, the filename returned by the dispatcher, and one sentence on what to try if the user wants a variation.
For hyperframes-html, keep the reply especially short: what was
rendered, the filename, and one concrete variation idea.
Hard rules
- One shot per turn. Multi-shot timelines belong in a hyperframes / interactive-video skill, not here.
- Match
videoAspectexactly — re-renders are slow. - Never ship a video without saving the file — the user expects something to play in the file viewer.
- When the underlying model fails (NSFW filter, content policy,
timeout), keep the raw provider error in the tool trace and give the
user the media contract's
nextStepsentence for that outcome. Never paste upstream error text into the reply. Don't silently retry. - Do not claim a render has been "sent", "started", or "is running"
unless you have already called
"$OD_NODE_BIN" "$OD_BIN" media generate.
04 同仓库更多 Skills
youtube-clipper
YouTube clip generation and editing with automated workflows — pull source video, slice highlights, add captions, and export.
writing-guidelines
Review docs/prose for Writing Guidelines compliance. Use when asked to "review my docs", "check writing style", "audit prose", "review docs voice and tone", or "check this page against the writing handbook".
wpds
WordPress Design System. Apply WordPress's official design tokens, typography, and component patterns to themes and sites.
weread-year-in-review-video-template
WeRead-inspired HyperFrames video template for vertical annual reading reports, personal reading dashboards, book-note recaps, and shareable year-in-review stories. Use when users want a 9:16 HTML-to-MP4 reading report with warm paper texture, editorial Chinese typography, book-page metaphors, data highlights, and deterministic motion.
web-design-guidelines
Review UI code for Web Interface Guidelines compliance by the Vercel engineering team. Covers layout, typography, color, motion, and accessibility for product UI.
web-clone
网站复刻 / 克隆方法论。USE WHEN 用户说 复刻网站、克隆网站、clone website、抄个站、仿站、 照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、 复刻某个交互/WebGL/Canvas/Three.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树,覆盖静态站 / React-Vue-Next 内容站 / WebGL-Canvas 重前端站三大分支,并强制核对任何 AI 二手分析里的可执行代码。