ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

video-generator

AI video production workflow using Remotion. Use when creating videos, short films, commercials, or motion graphics. Triggers on requests to make promotional videos, product demos, social media videos, animated explainers, or any programmatic video content. Produces polished motion graphics, not slideshows.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/diederik24/skill-5
Or

Video Generator (Remotion)

Create professional motion graphics videos programmatically with React and Remotion.

Default Workflow (ALWAYS follow this)

  1. Scrape brand data (if featuring a product) using Firecrawl
  2. Create the project in output/<project-name>/
  3. Build all scenes with proper motion graphics
  4. Install dependencies with npm install
  5. Fix package.json scripts to use npx remotion (not bun):
    "scripts": {
      "dev": "npx remotion studio",
      "build": "npx remotion bundle"
    }
    
  6. Start Remotion Studio as a background process:
    cd output/<project-name> && npm run dev
    
    Wait for "Server ready" on port 3000.
  7. Expose via Cloudflare tunnel so user can access it:
    bash skills/cloudflare-tunnel/scripts/tunnel.sh start 3000
    
  8. Send the user the public URL (e.g. https://xxx.trycloudflare.com)

The user will preview in their browser, request changes, and you edit the source files. Remotion hot-reloads automatically.

Rendering (only when user explicitly asks to export):

cd output/<project-name>
npx remotion render CompositionName out/video.mp4

Quick Start

# Scaffold project
cd output && npx --yes create-video@latest my-video --template blank
cd my-video && npm install

# Add motion libraries
npm install lucide-react

# Fix scripts in package.json (replace any "bun" references with "npx remotion")

# Start dev server
npm run dev

# Expose publicly
bash skills/cloudflare-tunnel/scripts/tunnel.sh start 3000

Fetching Brand Data with Firecrawl

MANDATORY: When a video mentions or features any product/company, use Firecrawl to scrape the product's website for brand data, colors, screenshots, and copy BEFORE designing the video. This ensures visual accuracy and brand consistency.

API Key: Set FIRECRAWL_API_KEY in .env (see TOOLS.md).

Usage

bash scripts/firecrawl.sh "https://example.com"

Returns structured brand data: brandName, tagline, headline, description, features, logoUrl, faviconUrl, primaryColors, ctaText, socialLinks, plus screenshot URL and OG image URL.

Download Assets After Scraping

mkdir -p public/images/brand
curl -s "https://example.com/favicon.svg" -o public/images/brand/logo.svg
curl -s "${OG_IMAGE_URL}" -o public/images/brand/og-image.png
curl -sL "${SCREENSHOT_URL}" -o public/images/brand/screenshot.png

Core Architecture

Scene Management

Use scene-based architecture with proper transitions:

const SCENE_DURATIONS: Record<string, number> = {
  intro: 3000,     // 3s hook
  problem: 4000,   // 4s dramatic
  solution: 3500,  // 3.5s reveal
  features: 5000,  // 5s showcase
  cta: 3000,       // 3s close
};

Video Structure Pattern

import {
  AbsoluteFill, Sequence, useCurrentFrame,
  useVideoConfig, interpolate, spring,
  Img, staticFile, Audio,
} from "remotion";

Metadata

Stars2387
Views0
Updated2026-03-09
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-diederik24-skill-5": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.