hyperframes

Create HTML-based video compositions with GSAP animations and render deterministic MP4 outputs.

1|Updated Apr 24, 2026
One-click install
npx skills add https://github.com/automatedigital/spark --skill hyperframes-automatedigital
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hyperframes
Source: https://github.com/automatedigital/spark/tree/main/skills/creative/hyperframes
Command: npx skills add https://github.com/automatedigital/spark --skill hyperframes-automatedigital

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @hyperframes/producer, sharp, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Creating polished video content typically requires expensive software, complex timelines, and manual rendering workflows that are hard to iterate on. This Skill brings video production directly into the AI agent's toolkit using HTML as the source of truth, making it fast to prototype, deterministic to render, and easy to version control.

Core Features & Use Cases

  • Composition Authoring: Build title cards, overlays, captions, and full multi-scene videos using HTML with data attributes for timing and GSAP for animation.
  • Audio-Reactive Visuals: Generate beat-synced animations, glow effects, and pulse-driven motion from pre-extracted audio frequency data.
  • Text Highlighting & Captions: Add marker sweeps, hand-drawn circles, burst lines, scribble effects, and karaoke-style captions synced to audio or transcript timestamps.
  • Scene Transitions: Apply crossfades, wipes, reveals, and shader transitions between scenes with choreographed entrance and exit animations.
  • Design System Integration: Respect brand colors, fonts, and spacing from a design.md file, or choose from 8 named visual styles and 9 curated palettes.

Quick Start

Use the hyperframes skill to create a 30-second product launch video with animated title cards, stats, and scene transitions, then render it to an MP4 file.

Frequently Asked Questions about hyperframes

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

FAQPage Schema
How do I automate HTML-driven video compositions and animations for AI workflows?

HTML-driven video compositions are automated by defining scenes with HTML and data attributes, applying GSAP timelines for animation, and rendering deterministic MP4 outputs through the render pipeline. It eliminates manual rendering workflows by using HTML as the source of truth.

Can I create audio-reactive visuals and beat-synced animations using HTML?

Audio-reactive visuals are generated from pre-extracted audio frequency data to drive beat-synced animations, glow effects, and pulse-driven motion. HTML elements serve as the visual targets, animated precisely using GSAP timelines synced to the provided audio data.

How do I add karaoke-style captions and text highlighting synced to a transcript?

Karaoke-style captions and text highlighting are added by applying marker sweeps, hand-drawn circles, burst lines, and scribble effects to text elements. The animations are synced to audio or transcript timestamps using HTML data attributes and GSAP timelines.

Does HyperFrames support scene transitions and multi-scene video composition?

Multi-scene video composition is fully supported with crossfades, wipes, reveals, and shader transitions between scenes. Entrance and exit animations are choreographed using GSAP timelines and CSS styling to maintain deterministic MP4 output.

Do I need a design system file to render video compositions?

A design system context is required via a design.md file to define brand colors, fonts, and spacing. If absent, the composition can fall back to eight named visual styles and nine curated palettes to ensure deterministic MP4 rendering.

What is the best way to build version-controlled motion graphics without traditional video software?

Building version-controlled motion graphics without traditional software is achieved by using HTML as the source of truth for video production. This approach makes compositions fast to prototype, deterministic to render, and easy to version control in automated workflows.