website-to-video

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

61.3k|7.8k|Updated Mar 29, 2026
One-click install
npx skills add https://github.com/calesthio/OpenMontage --skill website-to-video-calesthio
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: website-to-video
Source: https://github.com/calesthio/OpenMontage/tree/main/.agents/skills/website-to-video
Command: npx skills add https://github.com/calesthio/OpenMontage --skill website-to-video-calesthio

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Turning a live website into a polished video normally requires manual screenshots, brand asset hunting, storyboarding, and frame-by-frame animation work. This Skill automates that pipeline: it captures a URL with headless Chrome, extracts the brand's colors, fonts, and assets, then guides a gated 7-step workflow from brand analysis through storyboard, narration, composition building, and validation to a finished HyperFrames video. ## Core Features & Use Cases - Automated site capture: Downloads screenshots, SVGs, fonts, and computed design tokens from any URL, with optional Gemini-powered image descriptions. - Brand-faithful video production: Generates DESIGN.md, STORYBOARD.md, and SCRIPT.md artifacts, then builds GSAP-driven HTML compositions per beat using the site's real assets. - Full audio pipeline: Supports HeyGen TTS, ElevenLabs, or local Kokoro narration with transcription, beat timing, and captions. - Use Case: Paste a landing page URL and ask for a 15-second Instagram clip — the Skill captures the site, locks messaging with you, builds animated beats in the brand's visual identity, and delivers a Studio preview URL. ## Quick Start Ask the agent to turn https://your-site.com into a 30-second site tour video and follow the gated workflow prompts.

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?▼

Run the capture command with the target URL, then follow the 7-step workflow: brand analysis, DESIGN.md creation, storyboard and script approval, narration generation, composition building, and validation. The output is a HyperFrames Studio project you can preview or render to MP4.

What video formats and durations does website capture support?▼

Outputs include landscape 1920x1080, portrait 1080x1920 for Stories and TikTok, and square 1080x1080 for feeds. Typical durations range from 10-15 second social ads to 30-60 second product demos, driven by script length rather than fixed templates.

Which TTS providers can generate the narration voiceover?▼

Three providers are supported: HeyGen TTS, ElevenLabs, and local Kokoro TTS with 54 bundled voices across 9 languages. Kokoro runs locally with no API key, while HeyGen requires signing in via the hyperframes auth command.

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 site, GitHub PR videos, adding captions to existing footage, or re-cutting existing video files. The Skill is scoped to general site showcases built from captured visuals.

Does the capture work without a Gemini API key?▼

Yes, the base capture requires no API keys and downloads screenshots, assets, fonts, and design tokens. Without a Gemini key, image descriptions come from DOM context like position and alt text instead of AI vision descriptions.