website-to-video

Capture a website and produce a HyperFrames video from its brand assets.

1|Updated Aug 28, 2026
One-click install
npx skills add https://github.com/mooch10/mochiptos --skill website-to-video-mooch10
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: website-to-video
Source: https://github.com/mooch10/mochiptos/tree/main/frontend/.agents/website-to-video
Command: npx skills add https://github.com/mooch10/mochiptos --skill website-to-video-mooch10

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Turning an existing website into a polished video (site tour, showcase, or social clip) normally requires manual screenshots, brand extraction, storyboarding, voiceover recording, and motion design. This Skill automates that entire pipeline, from headless-Chrome capture of the site's visuals to a validated, linted HyperFrames composition. ## Core Features & Use Cases - Automated Site Capture: Runs npx hyperframes capture to download screenshots, SVGs, fonts, colors, and computed design tokens from any URL. - Brand Identity Extraction: Generates a DESIGN.md cheat sheet with exact color palettes, font files, component CSS values, and WCAG contrast checks. - Storyboard, Script & Voiceover: Guides collaborative storyboard and narration-script approval, then generates TTS audio (HeyGen, ElevenLabs, or Kokoro) with word-level caption timing. - Deterministic Video Build: Builds GSAP-based beat compositions with linting, snapshot verification, and a final Studio preview URL. - Use Case: Ask it to turn your landing page into a 15-second Instagram clip — it captures the site, extracts your brand, drafts a storyboard for approval, generates narration, and delivers a ready-to-render video project. ## Quick Start Ask the agent to turn https://your-site.com into a 30-second showcase video and follow the step-by-step gates from capture through validation.

Frequently Asked Questions about website-to-video

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I turn a website into a video automatically?▼

Run the website-to-video workflow with a target URL. It captures the site with headless Chrome, extracts brand colors and fonts, drafts a storyboard and narration script for your approval, then builds and validates a HyperFrames video composition.

What video formats and durations does website-to-video support?▼

It supports landscape 1920x1080, portrait 1080x1920, and square 1080x1080 outputs. Typical durations range from 10-15 second social ads to 30-60 second product demos, with beat counts derived from the storyboard rather than fixed templates.

Which TTS providers can generate the narration voiceover?▼

The workflow supports HeyGen TTS, ElevenLabs, and the local Kokoro engine. You choose the provider at Step 4, after which audio is generated, transcribed, and word-level timestamps are mapped to storyboard beats.

When should I not use website-to-video?▼

Do not use it for product or SaaS launch promos (use product-launch-video), topic explainers with no source site, GitHub PR videos, or re-editing existing video files. It is scoped to general site showcases built from the site's own captured visuals.

Does the capture step require an API key?▼

The base capture works without keys, but setting a Gemini API key enables AI-generated descriptions of captured images, improving asset selection for each scene. Without it, descriptions rely on DOM context like position and alt text.