Configure asset import settings — texture/audio/model importers, sprite settings, and per-platform overrides. Use when adjusting how assets import, setting texture compression or sprite modes, or applying per-platform import overrides, even if the user just says "导入设置" or "贴图压缩". 配置资源导入设置(texture/audio/model 导入器、sprite 设置、分平台覆盖);当用户要调整资源如何导入、设置贴图压缩或 sprite 模式、或应用分平台导入覆盖时使用。
npx skills add https://github.com/Besty0728/Unity-Skills --skill unity-importer
Use this module to change import settings for textures, audio, and models that already exist in the project.
> Batch-first: Prefer the batch setters when configuring 2+ assets of the same category.
Operating Mode (v1.9 three-tier):
texture_get_settings, texture_get_info, texture_find_assets, texture_find_by_size, texture_get_platform_settings, texture_get_import_settings, audio_get_settings, audio_get_clip_info, audio_find_clips, audio_find_sources_in_scene, audio_get_source_info, audio_get_import_settings, model_get_settings, model_find_assets, model_get_mesh_info, model_get_materials_info, model_get_animations_info, model_get_rig_info, model_get_import_settings, asset_get_labels) run directly. Setters / reimport are FullAuto — on MODE_RESTRICTED, run the grant protocol.RiskLevel="high" skills — nothing auto-classifies as forbidden. Importer mutations are reachable via grant in Approval mode.asset_reimport / asset_reimport_batch when Unity needs to fully refresh the asset.DO NOT (common hallucinations):
importer_import does not exist -> use asset_import in the asset module to bring files into the projectimporter_set_format does not exist -> use the specific texture/audio/model settersimporter_get_settings does not exist -> use the category-specific gettersRouting:
assettexture_*audio_*model_*texture_set_import_settings, audio_set_import_settings, model_set_import_settingsasset_reimport or asset_reimport_batchImport settings:
| Skill | Use | Key parameters |
|-------|-----|----------------|
| texture_get_settings | Read texture importer settings | assetPath |
| texture_set_settings | Set texture importer settings | assetPath, textureType?, maxSize?, filterMode?, compression?, mipmapEnabled?, sRGB?, readable?, wrapMode? |
| texture_set_settings_batch | Batch texture settings | items |
| texture_get_import_settings | Read minimal importer settings (type/maxSize/compression/filter/srgb/readable/mipmap) | assetPath |
| texture_set_import_settings | Alternative texture import bridge | similar texture fields |
Query and runtime info:
| Skill | Use | Key parameters |
|-------|-----|----------------|
| texture_find_assets | Search Texture2D assets by AssetDatabase filter | filter?, limit? (default 50) |
| texture_get_info | Inspect dimensions, format, and runtime memory size | assetPath |
| texture_find_by_size | Find textures in a dimension range (pixels) | minSize? (0), maxSize? (99999), limit? (50) |
Typed / platform overrides:
| Skill | Use | Key parameters |
|-------|-----|----------------|
| texture_set_type | Switch texture type | assetPath, textureType (Default/NormalMap/Sprite/EditorGUI/Cursor/Cookie/Lightmap/SingleChannel) |
| texture_set_platform_settings | Override per-platform settings | assetPath, platform (Standalone/iPhone/Android/WebGL), maxSize?, format?, compressionQuality?, overridden? |
| texture_get_platform_settings | Read per-platform override | assetPath, platform |
| texture_set_sprite_settings | Sprite-specific knobs (PPU, mode) | assetPath, pixelsPerUnit?, spriteMode? (Single/Multiple/Polygon) |
| sprite_set_import_settings | Sprite importer bridge (PPU, packingTag, pivot) | assetPath, spriteMode?, pixelsPerUnit?, packingTag?, pivotX?, pivotY? |
Common texture decisions:
textureType="Sprite", usually mipmapEnabled=falsefilterMode="Point"readable=true only when necessarytexture_set_platform_settings over global texture_set_settingsImport settings:
| Skill | Use | Key parameters |
|-------|-----|----------------|
| audio_get_settings | Read audio importer settings | assetPath |
| audio_set_settings | Set audio importer settings | assetPath, forceToMono?, loadInBackground?, loadType?, compressionFormat?, quality? |
| audio_set_settings_batch | Batch audio settings | items |
| audio_get_import_settings | Read minimal importer defaults (loadType/format/quality/forceToMono/loadInBackground) | assetPath |
| audio_set_import_settings | Alternative audio import bridge | similar audio fields |
Clip query and info:
| Skill | Use | Key parameters |
|-------|-----|----------------|
| audio_find_clips | Search AudioClip assets by filter | filter?, limit? (default 50) |
| audio_get_clip_info | Inspect length/channels/frequency/samples of a clip | assetPath |
Scene runtime (AudioSource / AudioMixer):
| Skill | Use | Key parameters |
|-------|-----|----------------|
| audio_add_source | Add an AudioSource to a GameObject | target (name/instanceId/path), clipPath?, playOnAwake? (false), loop? (false), volume? (1) |
| audio_get_source_info | Read the AudioSource configuration | target |
| audio_set_source_properties | Update AudioSource fields | target, clipPath?, volume?, pitch?, loop?, playOnAwake?, mute?, spatialBlend?, priority? |
| audio_find_sources_in_scene | List all AudioSources in the active scene | limit? (default 50) |
| audio_create_mixer | Create a new AudioMixer asset | mixerName? (default NewAudioMixer), folder? (default Assets) |
Common audio decisions:
loadType="Streaming"loadType="DecompressOnLoad"forceToMono=trueaudio_set_source_properties over manual component editsImport settings:
| Skill | Use | Key parameters |
|-------|-----|----------------|
| model_get_settings | Read model importer settings | assetPath |
| model_set_settings | Set model importer settings | assetPath, globalScale?, meshCompression?, isReadable?, generateSecondaryUV?, animationType?, importAnimation?, importCameras?, importLights?, materialImportMode? |
| model_set_settings_batch | Batch model settings | items |
| model_get_import_settings | Read minimal importer defaults (scale/compression/animationType/importAnimation/materialImportMode) | assetPath |
| model_set_import_settings | Alternative model import bridge | similar model fields |
Query and info:
| Skill | Use | Key parameters |
|-------|-----|----------------|
| model_find_assets | Search model assets by filter | filter?, limit? (default 50) |
| model_get_mesh_info | Mesh vertex / triangle / submesh stats | target (name/instanceId/path) or assetPath |
| model_get_materials_info | Inspect sub-asset materials embedded in the model | assetPath |
| model_get_animations_info | List animation clips and framerates on the model | assetPath |
| model_get_rig_info | Read animationType, avatar, skeleton binding info | assetPath |
Animation and rig:
| Skill | Use | Key parameters |
|-------|-----|----------------|
| model_set_animation_clips | Configure animation clip splits | assetPath, clips (JSON array of {name, firstFrame, lastFrame, loop}) |
| model_set_rig | Switch rig/skeleton mode | assetPath, animationType (None/Legacy/Generic/Humanoid), avatarSetup? |
Common model decisions:
animationType="Humanoid" when retargeting is requiredmodel_set_rig or model_set_animation_clips -> call asset_reimport to refresh clips and avatarAfter importer changes, use reimport when you need Unity to fully refresh the asset:
| Skill | Use |
|-------|-----|
| asset_reimport | Reimport one asset |
| asset_reimport_batch | Reimport assets matching a search scope |
import unity_skills
unity_skills.call_skill("texture_set_settings_batch", items=[
{"assetPath": "Assets/UI/icon_play.png", "textureType": "Sprite", "mipmapEnabled": False},
{"assetPath": "Assets/UI/icon_pause.png", "textureType": "Sprite", "mipmapEnabled": False}
])
unity_skills.call_skill("audio_set_settings",
assetPath="Assets/Audio/bgm.mp3",
loadType="Streaming",
compressionFormat="Vorbis",
quality=0.7
)
unity_skills.call_skill("asset_reimport", assetPath="Assets/Audio/bgm.mp3")
Exact names, parameters, defaults, and returns are defined by GET /skills/schema or unity_skills.get_skill_schema(), not by this file.
Load IMPORT_REFERENCE.md for extended asset search/query helpers, platform overrides, rig/animation details, and importer-side best practices.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.
Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.
Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.
Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.
Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.
Take besty0728/unity-importer from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.