Godot Resources logo

Godot Resources

OrganizationPopular
gamedev-skills
godot-resources

Design data-driven Godot 4.7 games with custom Resource classes: define typed data with class_name + @export, save/load .tres/.res files, instance and duplicate resources, and load on demand with ResourceLoader (incl. threaded loading). Use when modeling items/stats/configs as data in a Godot project, creating .tres resources, or working with custom Resource subclasses and ResourceLoader/ResourceSaver.

Overview

Publishergamedev-skills
Repositoryawesome-gamedev-agent-skills
Skill namegodot-resources
Stars
1.3K
Forks
107
Bundled files
1
LicenseApache-2.0
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.

  • 1 bundled files

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

  • Open source

    Published by gamedev-skills on GitHub. Read the source before you install it.

Installation

Install the Godot Resources 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/gamedev-skills/awesome-gamedev-agent-skills/tree/main/skills/godot/godot-resources
  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/gamedev-skills/awesome-gamedev-agent-skills.git /tmp/awesome-gamedev-agent-skills
mkdir -p .claude/skills
cp -r /tmp/awesome-gamedev-agent-skills/skills/godot/godot-resources .claude/skills/godot-resources
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Godot Resources 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 Resources 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 Resources 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 Resources (4.x)

Model game data as reusable, Inspector-editable Resource objects instead of hard-coded values, and load/save them as .tres/.res. Targets Godot 4.7.

When to use

  • Use when representing items, stats, enemy configs, dialogue lines, or level metadata as data; authoring .tres files in the Inspector; or loading/saving custom resources.

When not to use: nodes/scene structure → godot-nodes-scenes; saving the player's runtime progress (engine-agnostic save format/slots) → save-systems; the C# variant of this pattern → godot-csharp.

Core workflow

  1. Subclass Resource with class_name and @export fields. It now appears in the "New Resource" dialog and as an @export type, editable in the Inspector.
  2. Create instances as .tres files in the FileSystem dock (text, diff-friendly) or .res (binary, smaller/faster). Edit their fields in the Inspector — no code needed.
  3. Reference resources from nodes via @export var data: ItemResource, or arrays @export var loot: Array[ItemResource].
  4. Load at runtime with preload (constant path) or load/ResourceLoader.load (variable path). Use threaded loading for large assets.
  5. Duplicate before mutating a shared resource at runtime, or every node using it changes too (resources are shared references).
  6. Save generated/edited resources with ResourceSaver.save.

Patterns

1. A custom data resource

gdscript
# item.gd
extends Resource
class_name ItemResource

@export var id: StringName = &""
@export var display_name: String = "Item"
@export_multiline var description: String = ""
@export var icon: Texture2D
@export var max_stack: int = 99
@export var value: int = 0

Create sword.tres from this class in the FileSystem dock and fill it in the Inspector.

2. Consume resources from a node

gdscript
extends Node
@export var starting_items: Array[ItemResource] = []   # drag .tres files in the Inspector

func _ready() -> void:
    for item in starting_items:
        print("Have: %s (x%d max)" % [item.display_name, item.max_stack])

3. Duplicate before mutating shared data

gdscript
func give_unique_copy(template: ItemResource) -> ItemResource:
    # true = deep copy sub-resources too; false = shallow (shares sub-resources).
    var copy: ItemResource = template.duplicate(true)
    copy.value += 5                # mutating the copy won't touch the template .tres
    return copy

4. Save and load a resource at runtime

gdscript
func save_config(cfg: Resource) -> void:
    ResourceSaver.save(cfg, "user://config.tres")   # user:// = writable app data dir

func load_config() -> Resource:
    if ResourceLoader.exists("user://config.tres"):
        return ResourceLoader.load("user://config.tres")
    return null

Pitfalls

  • Resources are shared by reference. A single .tres assigned to many nodes is the same object — mutating it changes all of them (and re-saving the file). Call duplicate(true) for per-instance state.
  • class_name required to instance from the editor. Without it the class won't appear in the "New Resource" dialog or as an @export type.
  • res:// is read-only in exported games. Write runtime data to user://, never res://. ResourceSaver.save to res:// only works in the editor.
  • Storing nodes in a Resource doesn't serialize them. Resources hold data, not live scene nodes. Reference scenes via PackedScene, not node instances.
  • Cyclic resource references (A holds B holds A) can fail to save/load cleanly — keep data graphs acyclic or use IDs/lookups.
  • preload vs load. preload needs a constant path and loads with the script; load accepts a variable path at runtime. Use ResourceLoader.exists() before load to avoid errors on missing files.
  • Don't put secrets in .tres — they ship in plain text inside the export.

References

  • For threaded/background loading (load_threaded_request), @tool resources with custom setup, custom ResourceFormatLoader/Saver, resource-local-to-scene, and resource UIDs, read references/resource-patterns.md.

Related skills

  • godot-gdscript — @export annotations used to define resource fields.
  • godot-nodes-scenes — instancing scenes vs. sharing resource data.
  • save-systems — persisting runtime progress (separate from static data).
  • unity-scriptableobjects — the equivalent data-asset pattern in Unity.

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 Godot Resources AI skill do?

Design data-driven Godot 4.7 games with custom Resource classes: define typed data with class_name + @export, save/load .tres/.res files, instance and duplicate resources, and load on demand with ResourceLoader (incl. threaded loading). Use when modeling items/stats/configs as data in a Godot project, creating .tres resources, or working with custom Resource subclasses and ResourceLoader/ResourceSaver.

Why use Godot Resources on TypingMind?

Because you install it once and use it with any model. Godot Resources 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 Resources in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/gamedev-skills/awesome-gamedev-agent-skills/tree/main/skills/godot/godot-resources. 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 Godot Resources?

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 Resources?

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

Is the Godot Resources AI skill free?

Yes. It is published on GitHub by gamedev-skills under the Apache-2.0 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 👇