Cuboid Carousel logo

Cuboid Carousel

OrganizationPopular
heygen-com
cuboid-carousel

A chain of bevelled cuboids rides a travelling wave as a content carousel. HyperFrames block, 1920×1080, 6.666666666666667s, 40 variables.

Overview

Publisherheygen-com
Repositoryhyperframes
Skill namecuboid-carousel
Stars
73.3K
Forks
6.6K
Bundled files
10
LicenseApache-2.0
Links
  • 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.

  • 10 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 Cuboid Carousel AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/heygen-com/hyperframes/tree/main/registry/blocks/cuboid-carousel
  4. 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.
2

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/registry/blocks/cuboid-carousel .claude/skills/cuboid-carousel
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cuboid Carousel 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 Cuboid Carousel 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 Cuboid Carousel 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.

Cuboid Carousel

Rounded, bevelled cuboids carrying card content fly in from the right as one rigid group, cruise with a per-cuboid rotation stagger, decelerate to a hero hold, then exit left. Spacing is derived from the cuboid dimensions and the largest reachable X half-extent, so cuboids can never overlap. Forty variables carry the original DialKit schema: geometry, materials, lights, shadows, backdrop, camera and every segment duration and easing. Cards come from the built-in list or a JSON variable.

Composition id: cuboid-carousel. Duration 6.666666666666667 s at 30 fps, 1920×1080.

Files

  • cuboid-carousel.html (38 KB)
  • assets/Three-LICENSE.txt (1 KB)
  • assets/addons/environments/RoomEnvironment.js (5 KB)
  • assets/addons/utils/BufferGeometryUtils.js (36 KB)
  • assets/cuboid-motion.js (593 KB)
  • assets/gsap-3.14.2.min.js (128 KB)
  • assets/GSAP-NOTICE.txt (1 KB)
  • assets/three.core.min.js (554 KB)
  • assets/three.module.min.js (468 KB)

Install

Install with npx hyperframes add cuboid-carousel; by default the files above land under compositions/cuboid-carousel/. Then mount the block from the host index.html:

html
<div
  data-composition-id="cuboid-carousel"
  data-composition-src="compositions/cuboid-carousel/cuboid-carousel.html"
  data-start="0"
  data-duration="6.666666666666667"
  data-track-index="1"
  data-width="1920"
  data-height="1080"
></div>

Render with custom values by targeting the composition file directly:

sh
npx --yes hyperframes@0.8.12 render 'compositions/cuboid-carousel/cuboid-carousel.html' --variables '{"cardsJson":"","heroCard":4}'

Variables

Read at runtime via window.__hyperframes.getVariables(); declared on the composition root as data-composition-variables (single-quoted attribute, plain JSON).

idtypedefaultlabel / range
cardsJsonstring""Content · Cards JSON (optional, see CARDS in source)
heroCardnumber4Content · Hero card (1-based) 1–12 step 1
countnumber8Content · Repeating card count 1–12 step 1
gapnumber0.01Layout · Extra gap between cuboids 0–1.5 step 0.005
cuboidWidthnumber1.7Cuboid · Width 0.3–5 step 0.01
cuboidHeightnumber2.4Cuboid · Height 0.3–6 step 0.01
cuboidDepthnumber0.14Cuboid · Thickness (depth) 0.02–2 step 0.01
cornerRadiusnumber0.105Cuboid · Corner radius 0–0.6 step 0.005
bevelSizenumber0.03Cuboid · Bevel size (edge chamfer) 0–0.3 step 0.001
bevelThicknessnumber0.04Cuboid · Bevel thickness 0–0.3 step 0.001
smoothnessnumber32Cuboid · Smoothness (segments) 1–32 step 1
bodyColorcolor"#242424"Cuboid · Body colour
roughnessnumber0.6Cuboid · Roughness 0–1 step 0.01
metalnessnumber0.4Cuboid · Metalness 0–1 step 0.01
heroScalenumber1Hero · Isolated scale 1–1.6 step 0.01
heroFillIntensitynumber0.55Hero · Face light intensity 0–2 step 0.05
heroExitXnumber288Hero · Exit X rotation degrees -720–720 step 1
heroExitYnumber-234Hero · Exit Y rotation degrees -720–720 step 1
heroExitZnumber198Hero · Exit Z rotation degrees -720–720 step 1
ambientIntensitynumber0.35Lights · Ambient intensity 0–4 step 0.01
ambientColorcolor"#ffffff"Lights · Ambient colour
topIntensitynumber3.1Lights · Top rig intensity 0–12 step 0.05
topColorcolor"#ffffff"Lights · Top rig colour
bottomIntensitynumber2.15Lights · Bottom rig intensity 0–12 step 0.05
bottomColorcolor"#ffcaad"Lights · Bottom rig colour
keyIntensitynumber5Lights · Key rig intensity 0–12 step 0.05
keyColorcolor"#ffe9d6"Lights · Key rig colour
shadowRadiusnumber44.5Shadows · Softness at map size 2048 0–50 step 0.5
shadowMapSizenumber2048Shadows · Map size 512–4096 step 256
backdropcolor"#0b0d13"Background · Colour
cameraFovnumber11Camera · Initial Field of view 10–90 step 0.5
cameraXnumber-1.65Camera · Initial X -20–20 step 0.05
cameraYnumber8.5Camera · Initial Y -20–20 step 0.05
cameraZnumber-8.508708Camera · Initial Z (distance) -20–50 step 0.1
cameraSettleFramenumber70Camera · Settle frame (30 fps) 20–90 step 1
handheldStrengthnumber1Camera · Handheld hold strength 0–1 step 0.05
cameraTargetFovnumber34Camera target · Field of view 10–90 step 0.5
cameraTargetXnumber-7.25Camera target · X -20–20 step 0.05
cameraTargetYnumber1.15Camera target · Y -20–20 step 0.05
cameraTargetZnumber6.2Camera target · Z 2–50 step 0.1

Runtime contract

  • One paused GSAP timeline registered as window.__timelines["cuboid-carousel"].
  • Re-syncs on the hf-seek CustomEvent; every frame is a closed-form function of time (seeded PRNG only, no rAF loops, no Date.now).
  • Renderer: WebGL, GSAP, Canvas 2D, PMREM, Shadow maps. Budget roughly 350 MB per live instance; run one at a time.
  • External runtime dependencies: ./assets/three.module.min.js, ./assets/addons/.
  • Web fonts from Google Fonts: Inter.

Editing rules (from the source project)

  1. Keep data-composition-variables a single-quoted attribute with plain " JSON. Never save it through Studio's Design panel.
  2. Do not put <canvas> in static markup; create it at runtime.
  3. Keep every visual state a function of t; seek-safety is what makes the block renderable.

Bundled files

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

Frequently asked questions

What does the Cuboid Carousel AI skill do?

A chain of bevelled cuboids rides a travelling wave as a content carousel. HyperFrames block, 1920×1080, 6.666666666666667s, 40 variables.

Why use Cuboid Carousel on TypingMind?

Because you install it once and use it with any model. Cuboid Carousel 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 Cuboid Carousel in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/heygen-com/hyperframes/tree/main/registry/blocks/cuboid-carousel. 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 Cuboid Carousel?

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 Cuboid Carousel?

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

Is the Cuboid Carousel 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇