TypingMindTypingMindThe best frontend for AI
Threejs App Director logo

Threejs App Director

Organization
mintdotgg
threejs-app-director

Build and upgrade general Three.js apps including model and material viewers, configurators, walkthroughs, simulations, visualizations, editors, showcases, and interactive experiences.

Overview

Publishermintdotgg
Repositorymint-threejs-skills
Skill namethreejs-app-director
Stars
125
Forks
11
Bundled files
17
LicenseMIT
Links
Skill sourceRepositoryHomepage
  • 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.

  • 17 bundled files

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

  • Open source

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

Installation

Install the Threejs App Director 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/mintdotgg/mint-threejs-skills/tree/main/skills/mint-threejs-skills/skills/threejs-app-director
  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/mintdotgg/mint-threejs-skills.git /tmp/mint-threejs-skills
mkdir -p .claude/skills
cp -r /tmp/mint-threejs-skills/skills/mint-threejs-skills/skills/threejs-app-director .claude/skills/threejs-app-director
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Threejs App Director 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 Threejs App Director 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 Threejs App Director 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.

Three.js App Director

Own the complete non-game 3D application outcome. Do not invent game objectives, scoring, failure, or progression unless the experience genuinely needs them.

Read references/app-patterns.md for the matching application archetype. For a fresh model, animation, asset-pack, material, material-pack, or Mint-world delivery whose asset is the requested product, read ../../references/asset-viewer.md and start from the packaged Asset Viewer scaffold. For imported-model orientation, manipulation, simulation, terrain, or other spatially complex work, read ../../references/spatial-contracts.md.

Route The Work

NeedSkill
Models, composition, materials, lighting, shaders, VFX../threejs-visual-systems/SKILL.md
Cameras, controls, picking, selection, configuration, manipulation, UI../threejs-interaction-systems/SKILL.md
Rendering, loading, input bugs, profiling, optimization../threejs-debug-profiler/SKILL.md
Browser QA, visual regression, production release../threejs-qa-release/SKILL.md
Game mechanics or game feel inside a mixed experience../threejs-gameplay-systems/SKILL.md

Workflow

  1. Inspect the existing stack, scene lifecycle, assets, interactions, UI, data ownership, loading states, target devices, and deployment constraints.
  2. Define the app brief: user goal, primary 3D subject, essential interactions, camera/control model, state or data flow, loading/error behavior, outputs, and performance budget.
  3. If the work needs Mint assets, resolve one Mint Project for the local codebase through ../../references/mint-project-workspaces.md. Infer its name from the app brief when no association or explicit destination exists.
  4. Establish one owner for renderer, scene, camera, animation frame, resize, asset lifecycle, and disposal.
  5. Use Mint MCP through ../../references/mint-mcp-assets.md when production assets are needed. Register ordinary artifacts and remote world runtime configuration in the project-root mint-assets.json through ../../references/asset-pipeline.md; stream world RAD manifests through ../../references/mint-world-splats.md.
  6. Implement the smallest complete user journey before secondary polish.
  7. Apply visual systems and interaction guidance appropriate to the archetype.
  8. Reproduce and measure defects or performance issues before optimizing.
  9. Follow ../../references/verification-policy.md: run the automatic minimum, then offer a scoped desktop/browser QA pass. Treat mobile as a separate approval.

Asset Viewer Scaffold

For a greenfield asset-delivery viewer, create the canonical vanilla Three.js project:

bash
python3 <this-skill-dir>/scripts/create_threejs_asset_viewer.py ./my-asset-viewer

Use --force only when overwriting the target is intended. Configure src/asset-manifest.ts from the synchronized mint-assets.json; do not replace the scaffold's model, animation, material, pack, or RAD session with a bespoke scene unless the user requested a broader application.

Completion Gates

  • Build/typecheck or the nearest compile gate passes.
  • Focused non-browser tests for changed logic pass when available.
  • Referenced project-local assets and changed imports resolve.
  • mint-assets.json records every integrated Mint artifact or remote world runtime under a stable logical key and records the validated Mint Project.
  • Report that extended browser QA was not run unless the user approved it.

After the user approves the relevant QA scope:

  • The primary user journey works through real input.
  • Camera and controls match the task and do not fight each other.
  • Loading, empty, unsupported, and error states are handled when applicable.
  • Selection, configuration, manipulation, playback, or navigation state has one owner and visible feedback.
  • Assets load from stable local paths or the deliberate remote world runtime with correct scale, orientation, materials, animation, bounds, and disposal.
  • Desktop behavior is verified; mobile behavior is verified only under its separate approval.
  • Build/typecheck, browser errors, canvas pixels, screenshots, and changed risky paths pass.
  • Visual quality and renderer cost meet the requested bar.

Final Response

Lead with the implemented user journey. Report controls, state ownership, changed files, Mint links and artifact paths, screenshots, verification, performance evidence, deployment assumptions, and remaining risks. Explicitly name the extended desktop and mobile QA that was not run.

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 Threejs App Director AI skill do?

Build and upgrade general Three.js apps including model and material viewers, configurators, walkthroughs, simulations, visualizations, editors, showcases, and interactive experiences.

Why use Threejs App Director on TypingMind?

Because you install it once and use it with any model. Threejs App Director 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 Threejs App Director in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mintdotgg/mint-threejs-skills/tree/main/skills/mint-threejs-skills/skills/threejs-app-director. 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 Threejs App Director?

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 Threejs App Director?

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

Is the Threejs App Director AI skill free?

Yes. It is published on GitHub by mintdotgg under the MIT 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.

Related AI Skills

View all
openclaw logo

Openclaw Changelog Update

openclaw
OrganizationPopular

Regenerate OpenClaw release changelog sections from git history before beta, stable, or extended-stable releases.

82.2K
391K
1 files
View
openclaw logo

Openclaw Ci Limits

openclaw
OrganizationPopular

Manage OpenClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push single-flight, shard sizing, hosted-runner offload, queue health, and safe…

82.2K
391K
1 files
View
openclaw logo

Openclaw Debugging

openclaw
OrganizationPopular

Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code, including fetching stored…

82.2K
391K
1 files
View
openclaw logo

Openclaw Live Updater

openclaw
OrganizationPopular

Maintain the canonical live OpenClaw main checkout, macOS LaunchAgent-managed Gateway, local macOS app, exact-head main CI, and recurring full release validation. Use for fast-forward update…

82.2K
391K
2 files
View

Set up your own AI workspace now

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