Unity Optimization logo

Unity Optimization

CommunityPopular
Besty0728
unity-optimization

Optimize project assets and scenes

Overview

PublisherBesty0728
RepositoryUnity-Skills
Skill nameunity-optimization
Stars
1.8K
Forks
164
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 Optimization 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.

Use it in TypingMind

Enable Unity Optimization 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 Optimization 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 Optimization 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

  • Reducing build size
  • Batch-compressing assets
  • Analyzing scene poly/material usage
  • 缩减包体、批量压缩资源、分析场景面数与材质用量

Optimization Skills

Optimize project assets (Textures, Models).

Operating Mode

  • Approval: 只读分析类 skill(optimize_analyze_scene / optimize_find_large_assets / optimize_get_static_flags / optimize_find_duplicate_materials / optimize_analyze_overdraw,标 SkillMode.SemiAuto)直接执行;写型 skill(optimize_textures / optimize_mesh_compression / optimize_audio_compression / optimize_set_static_flags / optimize_set_lod_group,默认 SkillMode.FullAuto)需用户 grant,grant 后一步执行返结果。
  • Auto / Bypass: 直接执行。
  • 本模块不含 Delete / PlayMode / Reload / RiskLevel=high 类 skill —— 写型 skill 改的是 Importer / 组件设置,会重新导入资源,但不会触发 Domain Reload,也不会被 IsForbiddenInSemi 拦截。批量操作前务必检查筛选范围(filter / assetType),改完无 dry-run 回滚。

DO NOT (common hallucinations):

  • optimize_scene / optimization_run do not exist → use specific skills: optimize_analyze_scene, optimize_find_large_assets, optimize_find_duplicate_materials, etc.
  • optimize_compress / optimize_compress_textures / optimize_compress_meshes / optimize_compress_audio do not exist → use optimize_textures (textures), optimize_mesh_compression (meshes), optimize_audio_compression (audio)
  • optimize_set_lod / optimize_setup_lod do not exist → use optimize_set_lod_group
  • Optimization skills are analysis + action tools — always review results before applying batch changes

Routing:

  • For profiler metrics → use profiler module
  • For static batching flags → optimize_set_static_flags (this module)
  • For performance review guidance → load performance advisory module

Skills

optimize_textures

Optimize texture settings (maxSize, compression). Returns list of modified textures.

ParameterTypeRequiredDefaultDescription
maxTextureSizeintNo2048Max texture size
enableCrunchboolNotrueEnable crunch compression
compressionQualityintNo50Compression quality 0-100
filterstringNo""Asset filter

Returns: { success, count, message, modified }

optimize_mesh_compression

Set mesh compression for 3D models.

ParameterTypeRequiredDefaultDescription
compressionLevelstringNo"Medium"Compression level: Off/Low/Medium/High
filterstringNo""Asset filter

Returns: { success, count, compression, modified }

optimize_analyze_scene

Analyze scene for performance bottlenecks (high-poly meshes, excessive materials).

ParameterTypeRequiredDefaultDescription
polyThresholdintNo10000Triangle count threshold for high-poly warning
materialThresholdintNo5Material slot count threshold for excessive materials warning

Returns: { success, totalRenderers, totalTriangles, totalMaterialSlots, issueCount, issues }

optimize_find_large_assets

Find assets exceeding a size threshold (in KB).

ParameterTypeRequiredDefaultDescription
thresholdKBintNo1024Size threshold in KB
assetTypestringNo""Asset type filter (e.g. Texture2D, AudioClip)
limitintNo50Maximum number of results

Returns: { success, threshold, count, assets }

optimize_set_static_flags

Set static flags on GameObjects. flags is comma-separated, drawn from ContributeGI, OccluderStatic, OccludeeStatic, BatchingStatic, ReflectionProbeStatic, plus the two deprecated members NavigationStatic and OffMeshLinkGeneration.

Everything means the five non-deprecated flags, not literally everything. StaticEditorFlags declares neither Everything nor Nothing, so both are aliases this API adds: Nothing clears all bits, and Everything is the OR of the members Unity's own Static dropdown still offers — numerically 87, not the full 127. NavigationStatic and OffMeshLinkGeneration are deprecated and excluded, so name them explicitly if you want them. Every listed part must resolve: one unknown name fails the whole call rather than silently applying the subset that parsed, and a raw number carrying bits outside the enum's declared mask ("999") is rejected too.

ParameterTypeRequiredDefaultDescription
namestringNonullGameObject name
instanceIdintNo0GameObject instance ID
pathstringNonullGameObject hierarchy path
flagsstringNo"Everything"Comma-separated static flags, or the Everything / Nothing aliases (see above)
includeChildrenboolNofalseApply to all children recursively

Returns: { success, gameObject, flags, affectedCount }

optimize_get_static_flags

Get static flags of a GameObject.

ParameterTypeRequiredDefaultDescription
namestringNonullGameObject name
instanceIdintNo0GameObject instance ID
pathstringNonullGameObject hierarchy path

Returns: { success, gameObject, flags, isStatic }

optimize_audio_compression

Batch set audio compression. compressionFormat: PCM/Vorbis/ADPCM. loadType: DecompressOnLoad/CompressedInMemory/Streaming

ParameterTypeRequiredDefaultDescription
compressionFormatstringNo"Vorbis"Audio compression format: PCM/Vorbis/ADPCM
loadTypestringNo"CompressedInMemory"Audio load type: DecompressOnLoad/CompressedInMemory/Streaming
qualityfloatNo0.5Compression quality 0.0-1.0
filterstringNo""Asset filter

Returns: { success, count, compressionFormat, loadType, modified }

optimize_find_duplicate_materials

Find materials with identical shader and properties.

ParameterTypeRequiredDefaultDescription
limitintNo50Maximum number of duplicate groups to return

Returns: { success, duplicateGroups, groups }

optimize_analyze_overdraw

Analyze transparent objects that may cause overdraw.

ParameterTypeRequiredDefaultDescription
limitintNo50Maximum number of results

Returns: { success, transparentObjectCount, objects }

optimize_set_lod_group

Add or configure LOD Group. lodDistances: comma-separated screen-relative heights (e.g. '0.6,0.3,0.1')

ParameterTypeRequiredDefaultDescription
namestringNonullGameObject name
instanceIdintNo0GameObject instance ID
pathstringNonullGameObject hierarchy path
lodDistancesstringNo"0.6,0.3,0.1"Comma-separated screen-relative transition heights

Returns: { success, gameObject, lodLevels, distances }


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 Optimization AI skill do?

Optimize project assets and scenes

Why use Unity Optimization on TypingMind?

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

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

Which AI models can use Unity Optimization?

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 Optimization?

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

Is the Unity Optimization 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 👇