Remotion To Hyperframes

OrganizationPopular

heygen-com

remotion-to-hyperframes

Bring existing video code or footage into HyperFrames and verify it frame by frame against the original - Remotion first, also Motion Canvas, Lottie, Three.js, p5.js, canvas or plain HTML/CSS animation, or renders from Manim, After Effects or Blender. Use to port, convert, migrate or reuse work made with another tool.

Overview

Publisher	heygen-com
Repository	`hyperframes`
Skill name	`remotion-to-hyperframes`
Stars	73.3K
Forks	6.6K
Bundled files	65
License	Apache-2.0
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
65 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by heygen-com on GitHub. Read the source before you install it.

Installation

Install the Remotion To Hyperframes AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/heygen-com/hyperframes/tree/main/skills/remotion-to-hyperframes
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/heygen-com/hyperframes.git /tmp/hyperframes
mkdir -p .claude/skills
cp -r /tmp/hyperframes/skills/remotion-to-hyperframes .claude/skills/remotion-to-hyperframes

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Remotion To Hyperframes in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Remotion To Hyperframes on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Remotion To Hyperframes is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Plugin installs: Before setup or freshness commands, follow plugin execution rules when this skill is inside a HyperFrames plugin.

Import into HyperFrames

HyperFrames is the container: its tracks, sub-compositions and variables are editable in Studio whatever runs inside a clip. Bring each part in at the highest level it supports and record which level you used.

Level	For	How	Editable in Studio afterwards
Native	code that can become HTML + GSAP: most Remotion, HTML/CSS/GSAP animation, simple Motion Canvas	translate it, then verify frame by frame	every element; variables, catalog, presets apply
Hosted	code that can draw any requested frame in a browser: canvas, p5.js, Three.js, Lottie, WebGL, other JS animation	keep the code and drive it from HyperFrames time	timing, position, exposed parameters
Media	anything that outputs video or frames: Manim, After Effects, Blender, PIL, moviepy	render to a file and use it as a clip	cut, place, layer; not the pixels inside

Code that depends on wall-clock time, live physics or the network can only come in as media.

Native: translate, then verify

For Remotion, run python3 <SKILL_DIR>/scripts/lint_source.py <source dir> first. Blockers (useState, useReducer, useEffect with dependencies, async calculateMetadata, React UI kits such as MUI, Chakra, Mantine, antd, shadcn, Radix, NextUI) don't translate: host them or refactor them out, never approximate (references/escape-hatch.md). Warnings (@remotion/lambda config, delayRender, useMemo, custom hooks) are dropped and noted.
Translate to the /hyperframes contract: one sub-composition per scene, times in seconds (frame / fps), asset paths root-relative. Each Remotion API's equivalent is in references/api-map.md. Put Remotion's render-page rule * { box-sizing: border-box; } once in the root index.html <style>: without it every bordered or padded element grows by its border and padding.
Keep it editable: the source's props become data-composition-variables bound with data-var-text, data-var-src or var(--id); each Sequence becomes a timed clip or a sub-composition; a reused component becomes one sub-composition mounted several times with data-variable-values.
Compare frame by frame: npx hyperframes snapshot --at <t,…> --against <original.mp4> saves the original's frame at each time next to yours. Sample every scene and both sides of every cut; look for one late or recoloured element, not only the overall picture. For a scored check, scripts/render_diff.sh <original.mp4> <hf.mp4> <out> gives SSIM per frame and scripts/frame_strip.sh shows which frames diverged (thresholds per complexity tier in references/eval.md). Render the Remotion side with Config.setVideoImageFormat("png") and Config.setColorSpace("bt709"), or the diff measures the encoders (about 0.05 SSIM).
Write what didn't translate cleanly (dropped volume ramps, approximated presentations, substituted fonts) to TRANSLATION_NOTES.md.

Remotion	Read
`Composition`, `defaultProps`, `schema`, `calculateMetadata`	`references/parameters.md`
`Sequence`, `Series`, `Loop`, `AbsoluteFill`, `Freeze`	`references/sequencing.md`
`useCurrentFrame`, `interpolate`, `spring`, `Easing`, `interpolateColors`	`references/timing.md`
`Audio`, `Video`, `Img`, `IFrame`, `staticFile`, `delayRender`	`references/media.md`
`TransitionSeries`, `@remotion/transitions`	`references/transitions.md`
`@remotion/lottie`	`references/lottie.md`
`@remotion/google-fonts`, `Font.loadFont`, `@font-face`	`references/fonts.md`
What can't be ported	`references/limitations.md`

Before hand-building a named visual the source used, search npx hyperframes catalog --query "<the visual, in English>" --json: it ranks the whole registry with nothing installed.

Hosted

Keep the code and let HyperFrames own the clock: it draws the frame for the time it is given. The seek protocol and the built-in adapters for Lottie, Three.js, anime.js, WAAPI and CSS animations are in ../hyperframes/references/runtimes.md. No requestAnimationFrame loop or timer as the time source, seeded randomness only, and data-duration on the root when nothing else defines the length.

Media

<video class="clip" data-has-audio="true" src="assets/x.mp4" ...>, or muted when it is silent. Nothing else is needed.

In the final message, list each imported part with its level, what a person can change in Studio, and how the frame-by-frame comparison came out.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

and 5 more files.

Frequently asked questions

What does the Remotion To Hyperframes AI skill do?

Why use Remotion To Hyperframes on TypingMind?

Because you install it once and use it with any model. Remotion To Hyperframes is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Remotion To Hyperframes in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/heygen-com/hyperframes/tree/main/skills/remotion-to-hyperframes. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Remotion To Hyperframes?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Remotion To Hyperframes?

As many as you like. As long as a model supports skills, you can use Remotion To Hyperframes with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Remotion To Hyperframes AI skill free?

Yes. It is published on GitHub by heygen-com under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Archify

NousResearch

OrganizationPopular

Validated interactive HTML diagrams, upstream-maintained.

Auteur

Design and build cinematic, award-level web pages.

Concept Diagrams

Generate flat, minimal educational SVG visuals as HTML.

Hyperframes

Render MP4/WebM videos from HTML compositions.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Import into HyperFrames

Native: translate, then verify

Hosted

Media

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now