Godot Ui Integration logo

Godot Ui Integration

Community
zimo-xiao-zheng
godot-ui-integration

Build or revise Godot UI from an approved design, separated art, or a visual reference when scene structure, gameplay binding, and runtime visual verification all matter. Use for complete Godot UI integration; use ordinary Godot UI guidance for isolated node or layout questions that do not require an end-to-end visual workflow.

Overview

Publisherzimo-xiao-zheng
Repositorygodot-ui-integration
Skill namegodot-ui-integration
Stars
344
Forks
49
Bundled files
8
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.

  • 8 bundled files

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

  • Open source

    Published by zimo-xiao-zheng on GitHub. Read the source before you install it.

Installation

Install the Godot Ui Integration 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/zimo-xiao-zheng/godot-ui-integration/tree/main
  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/zimo-xiao-zheng/godot-ui-integration.git \
  .claude/skills/godot-ui-integration
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Godot Ui Integration 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 Ui Integration 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 Ui Integration 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 UI Integration

Turn an approved UI direction into editor-visible Godot scenes, connected behavior, and verified runtime output.

Route the request

  • If the user already approved a design or supplied the exact reference to implement, lock that reference and proceed.
  • If the visual direction is new or materially changing, prepare one composed preview and obtain approval before producing final assets or editing scenes.
  • If the user asks for exact, strict, pixel-close, or design-faithful reproduction, read references/strict-reference-parity.md completely before editing.
  • For read-only diagnosis, inspect and report without changing project files.

After the composed preview is approved, continue through asset preparation, scene construction, binding, and validation. Pause only when the approved composition must change, asset rights are unclear, validation remains blocked after targeted retries, or gameplay behavior would expand beyond the requested UI scope.

Required project checks

Before editing:

  1. Read the project instructions and canonical UI/navigation documentation.
  2. Inspect the target viewport, existing scenes, themes, input patterns, data sources, and asset directories.
  3. Use the Godot MCP first for engine inspection and edits. If it is unavailable, diagnose and attempt reconnection before using a local script, CLI, or UI fallback; report the failure and fallback.
  4. Record the approved reference, its dimensions, the target screen or overlay, and the intended entry and exit paths.

Implementation invariants

  • Treat .tscn scenes as the visual source of truth. Every formal player-facing screen or major overlay must be directly openable with its representative composition visible before _ready() runs.
  • Runtime code may populate data, localized text, textures, availability, selection, and transient feedback. It must not construct or relocate the primary layout procedurally.
  • Give distinct formal screens distinct scenes; inherited scenes are acceptable. Serialize screen-specific hierarchy, visibility, anchors, offsets, styles, and representative state.
  • Keep dynamic names, prices, counts, statistics, labels, lock states, and localized strings as Godot nodes or runtime data rather than baking them into raster art.
  • Preserve the approved reference's silhouette, material, texture, edge treatment, proportions, and hierarchy. Use native Godot primitives only where the design itself is visually simple.
  • Store final resources inside the Godot project. Do not leave scenes referencing temporary generation or working directories.
  • Reuse project conventions unless doing so would contradict the approved design or the user's asset-source constraints.

Workflow

  1. Survey: identify the affected scenes, scripts, data, navigation, input, viewport, safe areas, fonts, and reusable components.
  2. Lock the design: choose the exact approved reference and map major regions, dynamic fields, hit targets, ownership, and responsive behavior.
  3. Plan assets: classify each visual as direct extraction, reference-guided generation, reconstruction, reusable project art, or native Godot styling. Confirm source rights before reuse.
  4. Prepare assets: create one final file per asset, remove temporary backgrounds, preserve intended transparency, normalize display size, and avoid destructive whole-canvas stretching.
  5. Build scenes: serialize the formal composition and reusable repeated components in .tscn; keep decorative children from intercepting input.
  6. Bind behavior: connect data, navigation, disabled/empty/error states, persistent selection, controller/keyboard focus, and save boundaries without rebuilding the authored layout.
  7. Validate: inspect the editor scene, run the UI at the target resolution, exercise interactions, check errors, compare against the reference, and update the project UI documentation.

Validation helpers

The included Python tools require Pillow:

bash
python -m pip install -r requirements.txt
  • Inspect alpha and visible bounds:

    bash
    python scripts/alpha_audit.py path/to/asset.png
  • Build a contact sheet for candidate review:

    bash
    python scripts/contact_sheet.py "path/to/candidates/*.png" --out path/to/contact-sheet.png
  • Compare an approved reference with a runtime capture:

    bash
    python scripts/reference_parity_audit.py reference.png runtime.png --out path/to/parity.png
  • Audit panel-like textures for deformation and invalid nine-slice margins:

    bash
    python scripts/stretch_audit.py --project-root path/to/project --scene res://path/to/screen.tscn
  • Remove an edge-connected white background from an approved cutout:

    bash
    python scripts/white_bg_to_alpha.py --input source.png --out asset.png

Review generated outputs visually. Passing deterministic checks does not prove design fidelity.

Completion gate

Do not report completion until:

  • the formal scene is editor-visible before runtime binding;
  • the runtime path reaches and exits the UI correctly;
  • dynamic content and interaction states behave correctly;
  • there are no new parse, import, or runtime errors caused by the change;
  • strict-reference work includes a same-resolution comparison artifact and disclosed deviations;
  • the canonical project UI documentation reflects the implemented behavior and validation evidence.

Report the changed scenes, scripts, assets, runtime captures, validation commands, MCP status, known deviations, and any deferred product decisions.

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 Ui Integration AI skill do?

Build or revise Godot UI from an approved design, separated art, or a visual reference when scene structure, gameplay binding, and runtime visual verification all matter. Use for complete Godot UI integration; use ordinary Godot UI guidance for isolated node or layout questions that do not require an end-to-end visual workflow.

Why use Godot Ui Integration on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zimo-xiao-zheng/godot-ui-integration/tree/main. 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 Ui Integration?

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 Ui Integration?

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

Is the Godot Ui Integration AI skill free?

Yes. It is published on GitHub by zimo-xiao-zheng 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 👇