
mint-threejs-skills
Build, revise, debug, and verify browser-based Three.js apps, games, asset viewers, model and asset-pack deliveries, material and material-pack deliveries, animated-model viewers, and explicitly requested Gaussian-splat worlds with Mint MCP as the production asset pipeline.
- Installs
- 620
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/mintdotgg/mint-threejs-skills --skill mint-threejs-skills- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads mint-threejs-skills automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Mint Three.js Skills
Mint's agent skill suite for browser-based Three.js work. It combines and adapts open source Three.js game, application, and graphics-agent workflows, generalized for 3D apps while retaining deep game workflows.
Choose A Route
- Fresh request whose primary deliverable is one generated model, an animated
model, a coherent model asset pack, one material, a material pack, or one
explicitly requested Mint world: read
references/asset-viewer.md, then use the app director. The asset is the product; the viewer is its inspection and download shell. - General 3D app, viewer, configurator, simulation, walkthrough, editor, or
interactive experience: read
skills/threejs-app-director/SKILL.md. - Game or game-like request with objectives, challenge, scoring, failure,
progression, or game feel: read
skills/threejs-game-director/SKILL.md. - Mixed experience: start with the app director, then add only the relevant game specialists.
Both routes share visual systems, interaction, debugging, QA, and
references/mint-mcp-assets.md. Before the first Mint MCP write for a codebase,
read references/mint-project-workspaces.md to resolve one Mint Project for the
work. Projects that use Mint assets also use the durable registry in
references/asset-pipeline.md.
Existing app or game context wins over asset delivery. Generate and integrate a requested asset into that project instead of scaffolding a separate viewer.
Invariants
- Existing project architecture wins. For greenfield work, default to TypeScript, Vite, and Three.js modules.
- Vanilla Three.js is the default; support React Three Fiber or another Three.js-based stack when the project or user chooses it.
- Mint MCP is the only generated-asset production pipeline. Keep MCP calls out of browser runtime code.
- Distinguish the local code project (the folder or repository being edited)
from its Mint Project (the remote workspace that owns Mint chats and assets).
Resolve or create the Mint Project once, persist it in
mint-assets.json, and reuse it for every independent generation started for that codebase. - For every project that imports Mint files or remote world configuration,
maintain a project-root
mint-assets.jsonthroughscripts/sync-mint-assets.mjs. Reuse stable logical keys and preserve the existing project's asset-root conventions. - For every Three.js path that loads Mint-generated GLBs, read
references/gltf-runtime-compatibility.mdand use a Draco-capable shared loader. Mint-optimized GLBs are not compatible with a bareGLTFLoader. - Prefer discrete generated models and compose them in Three.js. Generate a
Mint world only when the user explicitly chooses a generated environment;
then read
references/mint-world-splats.md. - Use procedural or user-provided assets when they are the right design choice or Mint MCP lacks the required capability. Never create a competing procedural version of a subject that Mint generated successfully.
- Before verification, read
references/verification-policy.md. Run its automatic minimum, ask before extended desktop/browser QA, and require a separate secondary approval for mobile QA. Its approval boundary overrides broader specialist completion gates. - Do not force game concepts such as objectives, pressure, rewards, or failure onto general 3D apps.
User-Owned UI
- Treat the delivered app as the user's product, not as a demo of the asset-generation pipeline.
- Keep provider names, branding, badges, generation links, asset IDs, and provenance out of runtime UI unless the user explicitly asks for them.
- Mention generation provenance and handoff links only in the final response or developer documentation.
- Default to the minimum UI required for the experience: loading and error status, essential controls, and explicitly requested actions.
- Do not add headers, title bars, navigation, marketing copy, attribution, or decorative application chrome unless requested.
- For the canonical asset viewer, keep the canvas dominant with a compact centered details dialog opened from an info button plus bottom-centered inspection controls. Do not reserve permanent sidebar space. For other simple viewers and walkthroughs, use a compact bottom-centered control group. Place loading, ready, or error status directly above it using the same compact visual language.
When the user asks for a reusable prompt, use
references/request-templates.md.
FAQ
What does the mint-threejs-skills skill do?
Build, revise, debug, and verify browser-based Three.js apps, games, asset viewers, model and asset-pack deliveries, material and material-pack deliveries, animated-model viewers, and explicitly requested Gaussian-splat worlds with Mint MCP as the production asset pipeline.
How do I install mint-threejs-skills?
Run npx skills add https://github.com/mintdotgg/mint-threejs-skills --skill mint-threejs-skills in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/mint-threejs-skills/ (personal) or .claude/skills/mint-threejs-skills/ (project).
Which AI agents can use mint-threejs-skills?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is mint-threejs-skills safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains mint-threejs-skills?
It is published by mintdotgg in mintdotgg/mint-threejs-skills. It has 620 recorded installs.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available