TypingMindTypingMindThe best frontend for AI
3d Model Generator By Threejs logo

3d Model Generator By Threejs

Community
Yuki001
3d-model-generator-by-threejs

Generate procedural 3D models from natural-language requests by writing a constrained buildModel(ctx) module that uses Three.js, bundled builders and helpers, deterministic validation and export scripts, PNG previews, and optional browser visual review. Use when needs to create, revise, export, or visually audit programmatic 3D assets in GLB, glTF, OBJ, or STL without Blender or another DCC tool.

Overview

PublisherYuki001
Repositorygame-dev-skills
Skill name3d-model-generator-by-threejs
Stars
104
Forks
13
Bundled files
28
Links
Skill sourceRepository
  • 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.

  • 28 bundled files

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

  • Open source

    Published by Yuki001 on GitHub. Read the source before you install it.

Installation

Install the 3d Model Generator By Threejs 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/Yuki001/game-dev-skills/tree/main/skills/3d-model-generator-by-threejs
  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/Yuki001/game-dev-skills.git /tmp/game-dev-skills
mkdir -p .claude/skills
cp -r /tmp/game-dev-skills/skills/3d-model-generator-by-threejs .claude/skills/3d-model-generator-by-threejs
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable 3d Model Generator By Threejs 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 3d Model Generator By Threejs 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 3d Model Generator By Threejs 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.

3D Model Generator by Three.js

Generate model-specific JavaScript while keeping model construction helpers, validation, export, and review deterministic and reusable.

Workflow

  1. Choose a task output directory outside this skill.

  2. Run node scripts/init-model-task.mjs --out <task-dir> to copy the build-module template without overwriting existing work.

  3. Read references/build-contract.md. Read references/builder-api.md before using bundled builders or helpers. Read references/export-formats.md before choosing formats.

  4. Edit only <task-dir>/model-build.mjs. Export one buildModel(ctx) function and keep it deterministic.

  5. Install the pinned runtime once with npm ci --prefix scripts.

  6. Build, validate, and export:

    text
    node scripts/build-and-export.mjs --build <task-dir>/model-build.mjs --out <task-dir> --formats glb,obj,stl

  7. Inspect <task-dir>/validation.json. Fix every error and evaluate warnings that affect the requested formats.

  8. Render a deterministic PNG preview of the exported artifact:

    text
    node scripts/render-preview.mjs --model <task-dir>/model.glb --out <task-dir>/preview.png --views iso,front,top

    Read references/preview-rendering.md for supported formats, views, and rendering limitations.

  9. When interactive visual review is useful, run:

    text
    node scripts/serve-viewer.mjs --artifact-dir <task-dir> --model model.glb

    Open the printed local URL with an available browser tool. Review the exported artifact, not only the source scene. Use --source model-build.mjs when source-scene comparison is needed.

  10. Iterate by modifying only model-build.mjs, rebuilding, and reviewing again.

Build Rules

  • Return a THREE.Object3D or { root, animations, metadata }.
  • Use ctx.builders and ctx.helpers for common construction. Use ctx.THREE directly for custom geometry.
  • Do not import modules from generated build code. Do not access files, processes, environment variables, network APIs, dynamic imports, eval, or Function.
  • Use ctx.rng instead of Math.random() so revisions are reproducible.
  • Treat Y as up and meters as the default unit unless the request requires otherwise.
  • Prefer MeshStandardMaterial, MeshPhysicalMaterial, or bundled material presets for GLB.
  • Keep textures out of the default Node export path. Texture encoding requires a browser or a separate image-capable runtime.
  • Set meaningful node names and organize multipart assets under groups.
  • Keep triangle counts proportional to the requested use case. Use lower segment counts for distant or mobile assets.

Validation and Review

Run numeric validation before visual review. The validator checks finite transforms and vertices, empty geometry, normals, bounds, counts, unsupported shader materials, textures, and configured limits.

For visual review, inspect:

  • silhouette and recognizable shape;
  • relative scale and proportions;
  • symmetry, alignment, grounding, and unintended intersections;
  • front, rear, side, top, and perspective views;
  • material separation and final-format fidelity;
  • wireframe density when topology matters.

Prefer round-trip review of GLB, OBJ, or STL. Source mode can look correct even when export loses hierarchy, materials, transforms, or animations.

Completion Criteria

Complete a model task only when:

  • the build module runs without forbidden capabilities;
  • validation contains no errors;
  • every requested file exists and is non-empty;
  • exported-file review is satisfactory when browser review is available;
  • the build is reproducible with the recorded seed;
  • generated source and artifacts remain outside this skill directory.

Resources

  • scripts/runtime/: Stable build context, builders, helpers, seeded RNG, source checks, and scene validation.
  • scripts/exporters/: Format-specific GLB/glTF, OBJ, and STL exporters.
  • scripts/build-and-export.mjs: Main deterministic pipeline.
  • scripts/render-preview.mjs: Standalone exported-model PNG renderer.
  • scripts/serve-viewer.mjs: Local source and round-trip viewer server.
  • assets/model-build.template.mjs: Generated-task starting point.
  • assets/viewer/: Browser review application.
  • references/build-contract.md: Generated module contract and safety rules.
  • references/builder-api.md: Builder and helper API.
  • references/export-formats.md: Format capabilities and limitations.
  • references/preview-rendering.md: Standalone preview command and limitations.

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 3d Model Generator By Threejs AI skill do?

Generate procedural 3D models from natural-language requests by writing a constrained buildModel(ctx) module that uses Three.js, bundled builders and helpers, deterministic validation and export scripts, PNG previews, and optional browser visual review. Use when needs to create, revise, export, or visually audit programmatic 3D assets in GLB, glTF, OBJ, or STL without Blender or another DCC tool.

Why use 3d Model Generator By Threejs on TypingMind?

Because you install it once and use it with any model. 3d Model Generator By Threejs 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 3d Model Generator By Threejs in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Yuki001/game-dev-skills/tree/main/skills/3d-model-generator-by-threejs. 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 3d Model Generator By Threejs?

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 3d Model Generator By Threejs?

As many as you like. As long as a model supports skills, you can use 3d Model Generator By Threejs with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the 3d Model Generator By Threejs AI skill free?

It is published on GitHub by Yuki001. 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.

Related AI Skills

View all
openclaw logo

Release Openclaw Maintainer

openclaw
OrganizationPopular

Prepare, publish, recover, or verify OpenClaw beta, stable, and extended-stable releases, including approved backports.

82.2K
391K
11 files
View
openclaw logo

Release Openclaw Plugin Testing

openclaw
OrganizationPopular

Plan and run pre-release OpenClaw plugin validation across bundled plugins, package artifacts, lifecycle commands, doctor/fix, config round-trip, gateway startup, SDK compatibility, Docker E2E,…

82.2K
391K
1 files
View
openclaw logo

Solid

openclaw
OrganizationPopular

Write, port, review, or test Solid 2 UI in OpenClaw (Control UI, plugin views, Canvas hosts), including state ownership, Lit interop during the migration, native overlays, testing, performance, and…

82.4K
391.7K
9 files
View
openclaw logo

Auto Qa

openclaw
OrganizationPopular

Run OpenClaw-wide autonomous QA and live/stress campaigns across independent subsystem lanes, with verified fixes and a resumable evidence report.

82.2K
391K
5 files
View

Set up your own AI workspace now

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