Godot 3d Scenes logo

Godot 3d Scenes

Community
MRCalderon3D
godot-3d-scenes

Compose Godot 3D scenes with sound Node3D structure, cameras, physics bodies, environment ownership, and 3D performance patterns.

Overview

PublisherMRCalderon3D
Repositoryeverything-game-dev-code
Skill namegodot-3d-scenes
Stars
85
Forks
13
Bundled files
Instructions only
LicenseMIT
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by MRCalderon3D on GitHub. Read the source before you install it.

Installation

Install the Godot 3d Scenes 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.
  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/MRCalderon3D/everything-game-dev-code.git /tmp/everything-game-dev-code
mkdir -p .claude/skills
cp -r /tmp/everything-game-dev-code/skills/godot/godot-3d-scenes .claude/skills/godot-3d-scenes
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Godot 3d Scenes 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 Godot 3d Scenes 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 Godot 3d Scenes 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.

Godot 3D Scenes

Purpose

Compose Godot 3D scenes with sound Node3D structure, cameras, physics bodies, environment ownership, and 3D performance patterns.

Use When

  • starting or reviewing a 3D Godot project (or adding 3D to a 2D one)
  • 3D entities, cameras, or physics bodies are composed inconsistently across scenes
  • frame cost traces to lights, draw calls, or scene density in 3D levels

Inputs

  • gameplay entity inventory and their physics behavior (static, dynamic, character, trigger)
  • camera requirements (follow, orbit, fixed, first-person)
  • unit scale and asset conventions from the 3D asset pipeline
  • target platforms and their 3D performance budgets

Process

  1. compose each 3D entity as its own inheritable scene with a single root Node3D whose transform is the entity's transform; children never compensate for a misplaced root
  2. keep visual mesh, collision shape, and gameplay script as distinct children with conventional names so entities stay swappable and auditable
  3. choose physics bodies deliberately: StaticBody3D for level geometry, CharacterBody3D for player/NPC movement, RigidBody3D only when the simulation should own motion, Area3D for triggers — and keep collision shapes simple primitives that match visuals at gameplay scale
  4. define collision layers and masks as a named project-level table; bodies declare what they are (layer) and what they scan (mask), never "everything collides with everything"
  5. build camera rigs as their own scenes (Camera3D plus pivot/arm nodes), manage the current camera explicitly on scene transitions, and fix FOV/near/far conventions once
  6. give each level exactly one WorldEnvironment owner and place lights against the budgets from the lighting/LOD pipeline; a DirectionalLight3D plus baked or ambient fill is the default starting point
  7. control 3D density with visibility ranges or LODs, occlusion culling where interiors justify it, and MultiMeshInstance3D for many repeated meshes
  8. validate scenes in isolation: every entity scene must instantiate and run standalone (F6) without depending on siblings or absolute node paths

Outputs

  • 3D entity scene template (root transform, mesh/collision/script children)
  • collision layer/mask table with named layers
  • camera rig conventions and current-camera handover rules
  • WorldEnvironment/lighting ownership notes and 3D density checklist

Quality Bar

  • every 3D entity scene runs standalone with its root transform as the single source of position
  • physics body types match gameplay intent and collision uses named layers/masks, not defaults
  • exactly one WorldEnvironment per level and lights stay within the scene budget
  • repeated meshes demonstrably batch via MultiMesh or shared meshes, verified with the renderer profiler

Common Failure Modes

  • entity position split between root and offset children, so code moves one and physics uses the other
  • RigidBody3D used for player movement and then fought with forces every frame instead of CharacterBody3D
  • collision left on default layer 1 project-wide, making every raycast and area hit everything
  • multiple WorldEnvironments fighting per level, or environment settings duplicated per scene
  • thousands of individual MeshInstance3D nodes for repeated props where one MultiMesh would do

Related Agents

  • godot-reviewer
  • gameplay-programmer
  • level-designer

Related Commands

  • godot-scene-audit
  • godot-review
  • perf-budget

Related Skills

  • godot-scene-architecture
  • godot-performance
  • godot-resource-management

Notes

  • Keep this skill aligned with the relevant rules layer and current project documentation.
  • Boundary: godot-scene-architecture owns general scene/autoload/signal structure; this skill owns the 3D-specific layer on top of it. Engine-neutral 3D content policy (assets, materials, lighting budgets) lives in the art-audio-content 3D pipeline skills.

Frequently asked questions

What does the Godot 3d Scenes AI skill do?

Compose Godot 3D scenes with sound Node3D structure, cameras, physics bodies, environment ownership, and 3D performance patterns.

Why use Godot 3d Scenes on TypingMind?

Because you install it once and use it with any model. Godot 3d Scenes 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 Godot 3d Scenes in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/MRCalderon3D/everything-game-dev-code/tree/main/skills/godot/godot-3d-scenes. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Godot 3d Scenes?

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 Godot 3d Scenes?

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

Is the Godot 3d Scenes AI skill free?

Yes. It is published on GitHub by MRCalderon3D 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.

View all

Set up your own AI workspace now

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