Blender To Web logo

Blender To Web

Community
cth9191
blender-to-web

Build interactive website sculptures from Blender assets, including the export-to-Three.js handoff, live motion, fallbacks, and visual verification. Use for Blender-backed living hero sections or adapting the included working reference.

Overview

Publishercth9191
Repositoryblender-to-web
Skill nameblender-to-web
Stars
98
Forks
8
Bundled files
76
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.

  • 76 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by cth9191 on GitHub. Read the source before you install it.

Installation

Install the Blender To Web 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/cth9191/blender-to-web/tree/codex/blender-to-web-workflow
  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/cth9191/blender-to-web.git \
  .claude/skills/blender-to-web
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Blender To Web 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 Blender To Web 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 Blender To Web 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.

Blender to Web

Turn an art direction into an editable Blender scene and a working browser interaction. This skill adds the handoff to the browser; it does not replace general Blender modeling, rigging, or rendering guidance. Use available Blender specialist skills when those tasks need them.

Start with the intended interaction

Decide what must respond to the visitor: whole-object rotation, separate moving parts, skeletal joints, soft deformation, or playback of a fixed animation. Read the workflow for the relevant route. A GLB does not carry Blender's simulation engine into a website. State which behavior is exported and which is implemented in the browser.

Resolve the user's concept, visual reference, product story, target viewport and mobile behavior from their brief. A concept image can establish composition, silhouette and materials before modeling; it is not proof that the 3D implementation will match it. Do not default every project to infinity, charcoal/yellow, tiles, or this demo's page layout.

Preserve the durable source

Keep deterministic Blender Python, the editable .blend, the runtime export, material roles, part IDs and rest transforms. Record the exact Blender version and export settings. Model repeated elements as linked geometry where appropriate. Export stable part names and ordering when browser code uses them.

Inspect a fresh import of the actual exported asset and fixed views, then inspect the actual browser result. Cycles lighting and simulation are not automatically reproduced by glTF/Three.js.

Use the reference selectively

  • For the proven repeated-part path, read infinity anatomy. The runnable reference is assets/reference-project. Copy it into a new destination with python scripts/new_project.py DESTINATION; never edit the installed reference as a new project.
  • For guide-driven fiber deformation, read fiber lessons. Included source extracts illustrate the architecture; they are not a standalone second demo.
  • For concept, modeling and implementation briefs, use prompt recipes. Exact recovered image prompts are linked separately from newly written recipes.

The infinity adapter contains geometry-specific counts, material names, tile IDs and pulse ordering. When replacing geometry, explicitly update that contract. Do not feed an unrelated asset to it and assume it is a generic model viewer.

Browser finish

Separate pointer intent: hover affects a local region, drag rotates after a movement threshold, click toggles only if no drag occurred. Keep rest transforms and bounded motion; for springs use a fixed simulation step with elapsed-time caps. For a moving assembly, transform the pointer ray into local coordinates.

Choose instancing, skeletal animation, shaders or a solver according to the asset. Preserve pause, offscreen/hidden-page suspension, context-loss cleanup and an appropriate fallback. APERTURE uses a still for coarse pointers, reduced motion and data saving; that is a useful precedent, not a requirement for every mobile product.

Compose the website around the sculpture. If it stays pinned while scrolling, give the text clear spatial progression unless the user prefers a stationary crossfade. Keep outgoing text out of keyboard focus and away from fixed navigation.

Verify representative idle, hover, drag, expanded, reset, paused, scroll and fallback states that the project actually implements. Measure draw calls, triangles, payload, frame time and device/GPU. A fast result on a desktop GPU is not evidence for phone or integrated-GPU performance. The reference measurements are historical examples, not universal budgets.

Deliver source, export, poster, runnable page, verified states and limitations. Repository publication, hosting and paid generation remain separate user-directed actions. Preserve dependency licenses.

Bundled files

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

and 16 more files.

Frequently asked questions

What does the Blender To Web AI skill do?

Build interactive website sculptures from Blender assets, including the export-to-Three.js handoff, live motion, fallbacks, and visual verification. Use for Blender-backed living hero sections or adapting the included working reference.

Why use Blender To Web on TypingMind?

Because you install it once and use it with any model. Blender To Web 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 Blender To Web in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cth9191/blender-to-web/tree/codex/blender-to-web-workflow. 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 Blender To Web?

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 Blender To Web?

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

Is the Blender To Web AI skill free?

It is published on GitHub by cth9191. Check the repository for licensing terms. 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 👇