
Short-Form Video Clips
Generates 3-10 second MP4 video clips from a text brief via a media generation tool.
- Repository
- nexu-io/open-design
- Stars
- 105,448
- Licence
- Apache-2.0
- Files
- 2 files
What it does
Once installed, the agent plans a single short shot (product reveal, motion teaser, or ambient loop) by describing subject, camera, lighting, and motion, then sends that prompt to a video model such as Seedance 2, Kling, Veo or Sora through a unified media command. The resulting MP4 is saved into your project folder so you can play it in the file viewer. It also includes a special path for a local HTML-to-MP4 motion-design renderer, where it writes a short motion-graphics brief instead of realistic camera directions.
Great for
- Marketers who want a quick 5-10 second product reveal or social teaser
- Designers prototyping motion ideas inside an Open Design project
- Creators who want one clean looping ambient clip rather than a multi-cut story
Skip it if
- Long narrative videos or multi-scene edits, since the skill itself says to plan one shot per call and points to other skills for timelines
- Anyone needing guaranteed exact output, as text-to-video models are inconsistent and re-renders are slow and can be costly
Try asking
- “Make a 5-second product reveal of a ceramic mug rotating on a paper backdrop with warm side-light”
- “Create a 6-second motion teaser for our new app logo in 16:9”
- “Generate a seamless ambient loop of dust motes drifting through a sunbeam”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 2 original files, the Apache-2.0 licence and an attribution note.
video-shortform.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip video-shortform.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip video-shortform.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Describe one subject and one idea per request, and specify camera movement and lighting explicitly
- Keep the duration within the model's limit (for example 10s for Seedance 2 and Kling 4, 8s for Veo 3)
- If a render fails, rephrase the brief rather than retrying the same prompt, since the skill forbids silent retries
What's inside
- example.html
- SKILL.md
Redistributed unmodified from nexu-io/open-design under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.