Unity Smart logo

Unity Smart

CommunityPopular
Besty0728
unity-smart

AI-powered scene queries, layout and auto-binding. AI

Overview

PublisherBesty0728
RepositoryUnity-Skills
Skill nameunity-smart
Stars
1.9K
Forks
176
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 Besty0728 on GitHub. Read the source before you install it.

Installation

Install the Unity Smart 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/smart
  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 Smart 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 Smart 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 Smart 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

  • Querying scene objects by condition or proximity
  • Auto-arranging objects
  • Auto-wiring references
  • 按条件或邻近关系查询场景对象、自动排布对象、自动连线引用

Unity Smart Skills

Operating Mode

  • Approval:本模块 Mixed —— 只读查询 skill smart_scene_query / smart_scene_query_spatial(标 ReadOnly = true, Mode = SkillMode.SemiAuto)可直接执行;其余布局/绑定/变换类 skill (smart_scene_layout / smart_reference_bind / smart_align_to_ground / smart_distribute / smart_snap_to_grid / smart_randomize_transform / smart_select_by_component) 为 SkillMode.FullAuto,需用户 grant 单次执行返结果。
  • Auto / Bypass:直接执行。
  • 含 NeverInSemi 高危 skill:smart_replace_objects(Operation.Modify|Delete,会替换并删除原对象)。该 skill 在 Approval/Auto 下返 MODE_FORBIDDEN,仅 Bypass 或 Allowlist 命中可调。

DO NOT (common hallucinations):

  • smart_create / smart_build do not exist → smart skills are query/layout tools, not creation tools
  • smart_search / smart_query do not exist → use smart_scene_query (component property filters) or smart_scene_query_spatial (spatial region filters)
  • smart_move does not exist → use smart_snap_to_grid or smart_align_to_ground

Routing:

  • For creating objects → use gameobject module
  • For simple object search → use gameobject_find or scene_find_objects
  • For complex scene queries (SQL-like) → smart_scene_query (this module)

Skills

smart_scene_query

Find objects based on component property values (SQL-like).

ParameterTypeRequiredDefaultDescription
componentNamestringYes-Component type (Light, Camera, MeshRenderer)
propertyNamestringYes-Property to query (intensity, enabled, etc.)
opstringNo"=="==, !=, >, <, >=, <=, contains
valuestringNonullValue to compare
limitintNo50Max results
querystringNonullUnsupported shorthand; if provided alone returns a guidance error

Rejected with SEMANTIC_INVALID (and a closest-name suggestion for a misspelled member) instead of silently matching nothing: an unknown propertyName, an op outside the list, >/</>=/<= on a non-numeric member or with a non-numeric value, and anything but ==/!= on a bool.

Example:

python
# Find all lights with intensity > 2
call_skill("smart_scene_query", componentName="Light", propertyName="intensity", op=">", value="2")

smart_scene_layout

Organize selected objects into a layout.

ParameterTypeRequiredDefaultDescription
layoutTypestringNo"Linear"Linear, Grid, Circle, Arc
axisstringNo"X"X, Y, Z, -X, -Y, -Z
spacingfloatNo2.0Space between items (or radius)
columnsintNo3For Grid layout
arcAnglefloatNo180For Arc layout (degrees)
lookAtCenterboolNofalseRotate to face center

Example:

python
# Arrange selected objects in a circle
call_skill("smart_scene_layout", layoutType="Circle", spacing=5)

smart_reference_bind

Auto-fill a List/Array field with matching objects.

ParameterTypeRequiredDefaultDescription
targetNamestringYes-Target GameObject
componentNamestringNo-Component on target
fieldNamestringYes-Field to fill
sourceTagstringNonullFind by tag
sourceNamestringNonullFind by name contains
appendModeboolNofalseAppend instead of replace

Example:

python
# Fill GameManager.spawns with all SpawnPoint tagged objects
call_skill("smart_reference_bind", targetName="GameManager", componentName="GameController", fieldName="spawns", sourceTag="SpawnPoint")

smart_scene_query_spatial

Find objects within a sphere/box region, optionally filtered by component.

ParameterTypeRequiredDefaultDescription
xfloatYes-Center X coordinate
yfloatYes-Center Y coordinate
zfloatYes-Center Z coordinate
radiusfloatNo10Search sphere radius
componentFilterstringNonullOnly include objects with this component
limitintNo50Max results

Returns: { success, count, center, radius, results }


smart_align_to_ground

Raycast selected objects downward to align them to the ground. Requires objects selected in Hierarchy first.

ParameterTypeRequiredDefaultDescription
maxDistancefloatNo100Maximum raycast distance
alignRotationboolNofalseAlign rotation to surface normal

Returns: { success, aligned, total }


smart_distribute

Evenly distribute selected objects between first and last positions. Requires at least 3 objects selected in Hierarchy first.

ParameterTypeRequiredDefaultDescription
axisstringNo"X"X, Y, Z, -X, -Y, -Z

Returns: { success, distributed, axis }


smart_snap_to_grid

Snap selected objects to a grid.

ParameterTypeRequiredDefaultDescription
gridSizefloatNo1Grid cell size

Returns: { success, snapped, gridSize }


smart_randomize_transform

Randomize position/rotation/scale of selected objects within ranges.

ParameterTypeRequiredDefaultDescription
posRangefloatNo0Position randomization range
rotRangefloatNo0Rotation randomization range (degrees)
scaleMinfloatNo1Minimum uniform scale
scaleMaxfloatNo1Maximum uniform scale

Returns: { success, randomized }


smart_replace_objects

Replace selected objects with a prefab (preserving transforms). Requires objects selected in Hierarchy first.

ParameterTypeRequiredDefaultDescription
prefabPathstringYes-Asset path to the replacement prefab

Returns: { success, replaced, prefab }


smart_select_by_component

Select all objects that have a specific component.

ParameterTypeRequiredDefaultDescription
componentNamestringNo-Component type name to search for (componentType is an alias used when componentName is omitted)

Returns: { success, selected, component }


Exact Signatures

Exact names, parameters, defaults, and returns are defined by GET /skills/schema or unity_skills.get_skill_schema(), not by this file.

Frequently asked questions

What does the Unity Smart AI skill do?

AI-powered scene queries, layout and auto-binding. AI

Why use Unity Smart on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Besty0728/Unity-Skills/tree/main/SkillsForUnity/unity-skills~/skills/smart. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Unity Smart?

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 Smart?

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

Is the Unity Smart 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 👇