Video Shortform

Generates 3-10 second clips using Seedance 2, Kling, Veo, or Sora. Works best for single-shot ideas like product reveals, motion teasers, or ambient loops because current text-to-video models are stronger at one focused moment than multi-cut sequences. The skill enforces project metadata for aspect ratio and length, writes a shot plan before dispatching (subject, camera, lighting, motion), then calls the unified media contract instead of raw provider APIs. Outputs one MP4 to your project folder. If your workspace already has an interactive-video skill, you're better off composing multiple short shots into a timeline rather than generating one long monolithic clip. The hyperframes-html variant is a local HTML-to-MP4 renderer, not a photoreal model, so treat those prompts as motion design cards.

skills.sh installs: 209
GitHub stars: 106.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add nexu-io/open-design --skill video-shortform --agent claude-code

Installs into .claude/skills of the current project.

Files

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).