Skip to main content
skill CX Codex

video-shortform — Claude Code skill: what it does, how to install

video-shortform produces 3–10 second video clips — product reveals, motion teasers, ambient loops — and saves a single MP4 into the project folder.

Apache-2.0 210 installs ★ 108,855 updated 2026-10-25

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add nexu-io/open-design --skill video-shortform -a claude-code
Open on GitHub

What video-shortform does

The skill plans one shot per call: it drafts a shotlist covering subject, camera, lighting and motion, then assembles a prompt matching whichever model is in use. Seedance 2 is the default, with Kling 3/4, Veo 3 and Sora 2 also supported. Generation runs through a shared dispatcher command rather than hitting any provider API directly, and the project's aspect ratio and length settings are bound straight to that call. Seedance 2 tops out at 10 seconds, Kling 4 goes up to 10 seconds and adds image-to-video, Veo 3 runs 8 seconds with audio.

The hyperframes-html model gets separate treatment: it's a local HTML renderer, not a photoreal generator, so the skill swaps the camera-language prompt for a motion-design brief — subject, layout, palette, pacing — and fires off the render without extra status chatter.

When a project also has an interactive-video or hyperframes skill installed, the guidance is to chain several short shots into one timeline instead of producing a single long clip.

What it helps with

  • build a 3-10 second product teaser clip
  • generate video through Seedance 2, Kling, Veo 3 or Sora 2 without calling provider APIs by hand
  • render a motion-design frame via hyperframes-html
  • draft a shotlist before dispatching a video generation call
  • chain several short shots into one timeline

Example prompts for the agent

  • Generate a 5-second reveal: a ceramic mug spinning on a paper backdrop, warm side light, slow camera drift
  • Render a motion-design card through hyperframes-html for the product title frame
  • Create an 8-second ambient loop with Veo 3 including sound

How to install video-shortform

1Skills CLI (Vercel)

npx skills add nexu-io/open-design --skill video-shortform -a claude-code

2Manually: put the files in place

~/.claude/skills/video-shortform/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/video-shortform/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about video-shortform

How do I install video-shortform in Claude Code?

Run npx skills add nexu-io/open-design --skill video-shortform -a claude-code; the skill file lands at ~/.claude/skills/video-shortform/SKILL.md.

What does video-shortform do?

It generates 3-10 second video clips — product reveals, motion teasers, ambient loops — and writes the result as a single MP4 file into the project folder.

Which models does video-shortform support?

Seedance 2 is the default, alongside Kling 3/4, Veo 3 and Sora 2; the hyperframes-html option works differently, rendering HTML into video locally instead of generating camera-realistic footage.

Source text

SKILL.md · Apache-2.0
---
name: video-shortform
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.
triggers:
  - "video"
  - "clip"
  - "shortform"
  - "reel"
  - "短视频"
  - "动效"
od:
  mode: video
  surface: video
  scenario: marketing
  preview:
    type: html
    entry: example.html
  design_system:
    requires: false
  example_prompt: |
    5-second product reveal — ceramic coffee mug rotating on a soft
    paper backdrop, warm side-light from camera-left, micro dust motes
    drifting through the beam. Cinematic, 16:9, slow drift on the camera.
---

# 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:

```bash
"$OD_NODE_BIN" "$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 `videoAspect` exactly — 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 `nextStep` sentence 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`.

© nexu-io · Apache-2.0 · nexu-io/open-design

Similar skills

All skills for AI and ML →

From the same set140

The whole set →
eng-runbook eng-runbook generates a single-page HTML operations runbook with alerts, incident checklists, and terminal commands. Useful for on-call engineers and SRE teams. CX Codex +1 231installs image-poster image-poster builds structured prompts for posters and cover art, then runs a local CLI dispatcher. Saves finished PNG files directly to your project folder. CX Codex +1 229installs team-okrs Generates a single-screen desktop HTML prototype for tracking team OKRs. It comes in handy when you need a quarterly goal dashboard with progress bars and status badges. CX Codex +1 229installs audio-jingle audio-jingle generates jingles, voiceover, and sound effects. Routes music to Suno V5, Udio, or Lyria; speech to MiniMax TTS or ElevenLabs V3; SFX to ElevenLabs SFX or AudioCraft. CX Codex +1 211installs replit-deck replit-deck converts PRDs, roadmaps, and RFCs into single-file interactive HTML slide decks across eight dedicated design themes. CX Codex +1 209installs html-ppt-pitch-deck html-ppt-pitch-deck builds an HTML pitch deck for a demo day: hook, traction, moat and the raise. Aimed at accelerator partners and angels. CX Codex +1 190installs html-ppt-weekly-report html-ppt-weekly-report is a Claude Code skill that builds an HTML deck for OpenDesign’s weekly growth review. It covers stars, installs, and activation, with drivers and a recommended decision. CX Codex +1 186installs html-ppt-course-module html-ppt-course-module builds an HTML training deck for a new hospitality hire's first 30 days, based on the course-module template of the html-ppt master skill. CX Codex +1 186installs

Project sponsors

Companies that keep this analytics open