Unity Ui logo

Unity Ui

CommunityPopular
Besty0728
unity-ui

Create and lay out Unity UGUI screens

Overview

PublisherBesty0728
RepositoryUnity-Skills
Skill nameunity-ui
Stars
1.9K
Forks
176
Bundled files
1
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.

  • 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 Besty0728 on GitHub. Read the source before you install it.

Installation

Install the Unity Ui 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/Besty0728/Unity-Skills/tree/main/SkillsForUnity/unity-skills~/skills/ui
  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.

Use it in TypingMind

Enable Unity Ui 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 Unity Ui 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 Unity Ui 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.

Before calling any skill in this module: if you are about to call a skill with parameters guessed from its name or description, STOP — read this file (or fetch its schema via GET /skills/recommend?includeSchema=true) first. If you already have the parameter definitions from recommend/schema, you may proceed straight to dryRun.

Triggers

  • Building UGUI screens
  • Adding Canvas elements
  • Arranging UI layout
  • 搭建 UGUI 界面、添加 Canvas 元素、排布 UI 布局

Unity UI Skills

Use this module for Unity UGUI / Canvas workflows. It is separate from UI Toolkit.

Batch-first: Prefer ui_create_batch when creating 2+ UI elements.

Operating Mode

  • Approval:查询类 skill(ui_find_all,源码标 SkillMode.SemiAuto)直接执行;其余创建/修改类(ui_create_* / ui_set_* / ui_add_* / ui_layout_children / ui_align_selected 等,标 SkillMode.FullAuto)需用户 grant,grant 后服务端一步执行返结果。
  • Auto / Bypass:所有 skill 直接执行;Auto 走 AI 自我评估,Bypass 全放行。
  • 本模块不含 Delete / PlayMode / Reload / 高危 skill,无 Bypass-only 拦截项。删除 UI 节点请走 gameobject 模块。

DO NOT (common hallucinations):

  • ui_add_canvas does not exist -> use ui_create_canvas
  • ui_create_label does not exist -> use ui_create_text
  • ui_create_checkbox does not exist -> use ui_create_toggle
  • ui_set_color does not exist -> use component_set_property on Image/Text, or the dedicated UI property skills when available
  • Do not confuse UGUI (ui) with UI Toolkit (uitoolkit)

Routing:

  • For UXML/USS/UIDocument -> use uitoolkit
  • For XR-compatible world-space Canvas conversion -> use xr_setup_ui_canvas
  • For text updates after creation -> use ui_set_text
  • For layout and alignment -> use ui_layout_children, ui_align_selected, ui_distribute_selected

Skills

Create Skills

SkillUseKey parameters
ui_create_canvasCreate Canvasname?, renderMode?
ui_create_panelCreate panel containername?, parent?, r/g/b/a?
ui_create_buttonCreate buttonname?, parent?, text?, width/height?
ui_create_textCreate text labelname?, parent?, text?, fontSize?, r/g/b?
ui_create_imageCreate imagename?, parent?, spritePath?, width/height?
ui_create_inputfieldCreate input fieldname?, parent?, placeholder?, width/height?
ui_create_sliderCreate slidername?, parent?, minValue?, maxValue?, value?
ui_create_toggleCreate togglename?, parent?, label?, isOn?
ui_create_dropdownCreate dropdownname?, parent?, options?, width/height?
ui_create_scrollviewCreate ScrollRect hierarchyname?, parent?, width/height?, horizontal?, vertical?
ui_create_rawimageCreate RawImagename?, parent?, texturePath?, width/height?
ui_create_scrollbarCreate scrollbarname?, parent?, direction?, value?, size?
ui_create_batchCreate multiple UI elementsitems (JSON string array)

Query and Layout Skills

SkillUseKey parameters
ui_find_allFind scene UI elementsuiType?, limit?
ui_set_textUpdate text contentname, text
ui_set_rectSet RectTransform size/offsetstarget, width, height, posX, posY, left/right/top/bottom?
ui_get_rect_transformRead full RectTransform datatarget
ui_set_rect_transformSet full RectTransform dataanchors, pivot, offsets, local transform, width/height
ui_set_rect_transform_batchSet full RectTransform data for multiple elementsitems
ui_set_anchorApply anchor presettarget, preset?, setPivot?
ui_layout_childrenVertical/Horizontal/Grid layouttarget, layoutType?, spacing?
ui_align_selectedAlign current selectionalignment?
ui_distribute_selectedDistribute current selectiondirection?

Property and Effect Skills

SkillUseKey parameters
ui_set_imageImage type/fill/spritetarget, type?, fillMethod?, fillAmount?, spritePath?
ui_add_layout_elementAdd LayoutElement constraintstarget, width/height prefs, flex values
ui_add_canvas_groupAdd CanvasGrouptarget, alpha?, interactable?, blocksRaycasts?
ui_add_maskAdd Mask or RectMask2Dtarget, maskType?, showMaskGraphic?
ui_add_outlineAdd Shadow/Outline effecttarget, effectType?, r/g/b/a?, distanceX/Y?
ui_configure_selectableConfigure transitions/navigation/colorstarget, transition?, navigationMode?, color values

High-Frequency Defaults

Canvas and Parenting

  • ui_create_canvas defaults to ScreenSpaceOverlay.
  • Most create skills accept parent; if omitted, Unity will create under the active Canvas or scene root depending on the implementation context.
  • For reusable menu groups, create the Canvas once, then create a Panel and put all child controls under that panel.

Common Create Parameters

SkillHigh-frequency fields
ui_create_buttontext, width, height
ui_create_texttext, fontSize, r/g/b
ui_create_imagespritePath, width, height
ui_create_sliderminValue, maxValue, value
ui_create_togglelabel, isOn
ui_create_dropdownoptions
ui_create_scrollviewhorizontal, vertical, movementType

Important:

  • Most create skills do not take explicit x/y placement.
  • Create first, then place/anchor with ui_set_rect, ui_set_anchor, or ui_layout_children.

Full RectTransform Editing

Use ui_set_rect_transform when you need Inspector-level RectTransform coverage instead of a preset.

SkillParameters
ui_get_rect_transformname, instanceId, path
ui_set_rect_transformtarget + anchorMinX/Y, anchorMaxX/Y, pivotX/Y, anchoredPosX/Y/Z, sizeDeltaX/Y, offsetMinX/Y, offsetMaxX/Y, localPosX/Y/Z, localRotX/Y/Z, localScaleX/Y/Z, width, height
ui_set_rect_transform_batchitems JSON array with the same per-target fields

ui_get_rect_transform

Get full RectTransform data for a UI element.

ParameterTypeRequiredDefaultDescription
namestringNo*nullGameObject name
instanceIdintNo*0GameObject instance ID
pathstringNo*nullHierarchy path

Returns: { success, name, instanceId, path, anchorMin, anchorMax, pivot, anchoredPosition3D, sizeDelta, offsetMin, offsetMax, localPosition, localEulerAngles, localScale, rect }

ui_set_rect_transform

Set full RectTransform data for a UI element.

ParameterTypeRequiredDefaultDescription
namestringNo*nullGameObject name
instanceIdintNo*0GameObject instance ID
pathstringNo*nullHierarchy path
anchorMinX / anchorMinYfloatNonullAnchor min
anchorMaxX / anchorMaxYfloatNonullAnchor max
pivotX / pivotYfloatNonullPivot
anchoredPosX / anchoredPosY / anchoredPosZfloatNonullAnchored position 3D
sizeDeltaX / sizeDeltaYfloatNonullSize delta
offsetMinX / offsetMinYfloatNonullOffset min
offsetMaxX / offsetMaxYfloatNonullOffset max
localPosX / localPosY / localPosZfloatNonullLocal position
localRotX / localRotY / localRotZfloatNonullLocal euler rotation
localScaleX / localScaleY / localScaleZfloatNonullLocal scale
width / heightfloatNonullSize with current anchors

Returns: same shape as ui_get_rect_transform.

ui_set_rect_transform_batch

Set full RectTransform data for multiple UI elements.

ParameterTypeRequiredDefaultDescription
itemsjson stringYes-JSON array of per-item target and RectTransform fields

Returns: { success, totalItems, successCount, failCount, results }

Layout and Anchoring Rules

  • ui_set_anchor is the fastest way to move a control into a standard layout position.
  • ui_set_rect is better for precise size/offset edits after anchoring.
  • ui_layout_children is preferred over hand-positioning every child when building vertical, horizontal, or grid menus.

Anchor presets commonly used in production:

  • MiddleCenter for modal/menu panels
  • TopLeft or TopRight for HUD corners
  • StretchAll for full-screen backgrounds

TextMeshPro Note

Text creation auto-detects TMP:

  • TMP available -> TextMeshProUGUI
  • TMP unavailable -> legacy Text

Read the response payload if you need to know which one was created before later component-specific edits.

Workflow Notes

  1. Create a Canvas first.
  2. Use panels to group related controls.
  3. Prefer ui_create_batch for menus, HUD groups, and repeated widgets.
  4. Use anchors and layout groups before hand-placing every child.
  5. Text creation auto-detects TextMeshPro. Responses indicate whether TMP was used.
  6. For world-space gameplay UI, build the Canvas here first, then convert for XR only if needed.
  7. ui_create_batch is mainly for bulk creation, not precise positioning. Follow it with layout or rect/anchor adjustments.
  8. ui_create_batch.items is a JSON string parameter in the current REST/API layer, not a raw array object.

Minimal Example

python
import unity_skills
import json

unity_skills.call_skill("ui_create_canvas", name="MainMenu")
unity_skills.call_skill("ui_create_panel", name="MenuPanel", parent="MainMenu", a=0.7)
unity_skills.call_skill("ui_set_rect", name="MenuPanel", width=320, height=240)
unity_skills.call_skill("ui_create_batch", items=json.dumps([
    {"type": "Button", "name": "StartBtn", "parent": "MenuPanel", "text": "Start", "width": 220, "height": 44},
    {"type": "Button", "name": "OptionsBtn", "parent": "MenuPanel", "text": "Options", "width": 220, "height": 44},
    {"type": "Button", "name": "QuitBtn", "parent": "MenuPanel", "text": "Quit", "width": 220, "height": 44}
]))

unity_skills.call_skill("ui_set_anchor", name="MenuPanel", preset="MiddleCenter")
unity_skills.call_skill("ui_layout_children", name="MenuPanel", layoutType="Vertical", spacing=12)

Exact Signatures

Exact names, parameters, defaults, and returns are defined by GET /skills/schema or unity_skills.get_skill_schema(), not by this file. Load UI_REFERENCE.md for extended element creation details, property tables, and larger UGUI examples.

Common Errors

Full transport-level codes (COMPILING/RATE_LIMIT etc.) → ../../references/protocol-error-codes.md

ErrorTriggerFix
TARGET_NOT_FOUNDThe parent GameObject, UI element, RectTransform, Text/Image/Selectable component, or sprite asset could not be found.Use ui_find_all, gameobject_find, or scene_get_hierarchy to locate the element, and verify sprite paths with asset_find.
SEMANTIC_INVALIDAn invalid value was supplied, such as an unknown anchor preset, layout type, alignment, or name/path with separators.Choose a valid preset/type from the error context (e.g., MiddleCenter, Vertical, TopLeft) and retry.
SKILL_ERRORA selection-based operation failed because fewer than the required number of UI elements were selected (e.g., Select at least 2 UI elements).Select the required UI elements in the Hierarchy before calling alignment/distribution skills.

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 Unity Ui AI skill do?

Create and lay out Unity UGUI screens

Why use Unity Ui on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Besty0728/Unity-Skills/tree/main/SkillsForUnity/unity-skills~/skills/ui. 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 Unity Ui?

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 Unity Ui?

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

Is the Unity Ui AI skill free?

Yes. It is published on GitHub by Besty0728 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 👇