Index of all Unity Skills modules — functional (REST) modules and advisory (design) modules. Browse available modules, check operating-mode requirements (Approval/Auto/Bypass), and pick the right module for a task. Use when looking for which Unity module handles something, browsing the module catalog, or checking a module's mode requirements, even if the user just says "有哪些 Unity 技能" or "Unity 模块列表". Unity Skills 所有模块的索引(功能型 REST 模块与建议型设计模块);当用户要查找某事由哪个 Unity 模块处理、浏览模块目录、或确认模块的模式要求时使用。
npx skills add https://github.com/Besty0728/Unity-Skills --skill unity-skills-index
Module docs. Start with ../SKILL.md for mode switching and schema-first rules.
> Multi-instance: For version-specific projects, call unity_skills.set_unity_version(...) first.
> Schema-first: Use GET /skills/schema or unity_skills.get_skill_schema() for exact signatures. Load module docs for workflow guidance and guardrails.
> Mode legend (v1.9.0+, caller-facing — describes what the caller can do, not the C# attribute):
> - SA — module skills mostly run directly in all three modes (Approval / Auto / Bypass) without a grant.
> - FA — module skills mostly require user grant under Approval (single-shot one-step execution); under Auto / Bypass they run directly with audit only.
> - Mixed — module is split between SA and FA; check per-skill mode returned by GET /skills before calling.
> - Suffix * — module contains auto-forbidden skills (Delete / Play Mode / Domain Reload / high-risk). These return MODE_FORBIDDEN under Approval and Auto; only Bypass runs them, or the user can permanently allow them via the Allowlist. Never attempt grant for them.
>
> Labels are guidance only; the per-skill mode field on GET /skills is authoritative.
| Module | Mode | Description | Batch Support |
|--------|:----:|-------------|---------------|
| gameobject | FA* | Object create/move/parent | Yes |
| component | Mixed* | Component add/remove/configure | Yes |
| material | FA | Material property edits | Yes |
| light | FA | Light create/configure | Yes |
| prefab | FA | Prefab create/apply/spawn | Yes |
| asset | SA* | Asset refresh/find/info | Yes |
| batch | SA | Batch and async jobs | Built-in |
| ui | FA | UGUI Canvas/UI creation | Yes |
| uitoolkit | Mixed* | UXML/USS/UIDocument | No |
| script | SA* | Script create/read/update | Yes |
| scene | SA* | Scene load/save/query | No |
| editor | SA* | Play/select/undo/redo/change journal | No |
| animator | FA | Animator controllers | No |
| shader | Mixed* | Shader create/list | No |
| shadergraph | Mixed* | Shader Graph create/inspect/blackboard edit/constrained node editing | No |
| graphics | Mixed | GraphicsSettings / QualitySettings / SRP assets | No |
| volume | Mixed* | Volume / VolumeProfile / VolumeComponent | No |
| postprocess | FA* | Modern URP/HDRP post-processing | No |
| urp | Mixed* | URP asset / renderer / renderer features | No |
| decal | Mixed* | URP Decal Projector workflow | Yes |
| console | SA | Log capture/filter | No |
| validation | SA* | Broken reference checks | No |
| importer | Mixed | Texture/audio/model import | Yes |
| cinemachine | FA* | VCam operations | No |
| probuilder | FA* | ProBuilder mesh edits | No |
| xr | FA | XRI setup | No |
| terrain | FA | Terrain create/paint | No |
| physics | Mixed | Raycast/overlap/gravity | No |
| navmesh | Mixed* | NavMesh bake/query | No |
| timeline | FA* | Timeline tracks/clips | No |
| workflow | SA* | Task snapshots/undo, batch orchestration | No |
| cleaner | SA* | Unused/duplicate assets | No |
| smart | FA* | Query/layout/auto-bind | No |
| perception | SA | Scene/project analysis | No |
| camera | FA | Scene View camera | No |
| event | Mixed* | UnityEvent wiring | No |
| package | Mixed* | UPM install/query | No |
| project | SA | Project info/settings | No |
| profiler | SA | Perf statistics | No |
| optimization | Mixed | Asset optimization | No |
| sample | Mixed* | Demo/test skills | No |
| debug | SA | Compile/system diagnostics | No |
| test | Mixed | Unity Test Runner | No |
| bookmark | SA | Scene View bookmarks | No |
| history | SA | Undo/redo history | No |
| scriptableobject | Mixed* | ScriptableObject assets | No |
| netcode | Mixed* | Netcode for GameObjects setup, prefabs, lifecycle, host/server/client | Yes |
| yooasset | Mixed* | YooAsset hot-update: build bundles, Collector CRUD, BuildReport asset/dependency analysis, PlayMode runtime validation, Reporter/Debugger/AssetArtScanner tools | Yes |
| dotween | Mixed* | DOTween Pro DOTweenAnimation editor-time configuration (add/batch/stagger/tune) | Yes |
| primetween | Mixed* | PrimeTween Free inspection, factory discovery, and runtime tween/sequence script generation | No |
| behavior | Mixed* | Unity Behavior graph assets, agents, blackboard variables (com.unity.behavior, reflection-based) | Yes |
| hybridclr | Mixed* | HybridCLR hot-update settings, codegen, DLL compile/copy pipeline (com.code-philosophy.hybridclr, reflection-based) | Yes |
These modules provide design guidance only.
| Module | Description |
|--------|-------------|
| project-scout | Inspect existing project |
| architecture | Plan system boundaries |
| adr | Record tradeoffs |
| performance | Review hot paths |
| asmdef | Plan asmdef deps |
| blueprints | Small-game blueprints |
| script-roles | Assign class roles |
| scene-contracts | Define scene wiring |
| testability | Extract testable logic |
| patterns | Choose patterns |
| async | Choose async model |
| inspector | Design authoring UX |
| scriptdesign | Review script structure |
| netcode-design | Netcode source-anchored rules (lifecycle/ownership/RPC/variables/spawn/scene/transport/pitfalls) |
| yooasset-design | YooAsset v2.3.18 source-anchored rules (init/default-package shortcuts/playmode/handles/loading/update/filesystem/build/pitfalls) |
| addressables-design | Addressables dual-version (1.22.3 Unity 2022 / 2.9.1 Unity 6) source-anchored rules (init/handles/loading/scene/update/download/assetref/pitfalls) with migration table |
| unitask-design | UniTask 2.5.10 source-anchored rules (basics/playerloop/cancellation/composition/conversion/asyncenumerable/triggers/pitfalls) |
| dotween-design | DOTween 1.3.015 source-anchored rules (basics/tween/sequence/shortcuts/ease/lifetime/integration/pitfalls) |
| primetween-design | PrimeTween 1.4.6 source-anchored rules (factories/handles/sequences/cycles/callbacks/lifetime/integration) |
| shadergraph-design | ShaderGraph dual-version source-anchored rules (versions/node subset/recipes/pitfalls/review) |
| yaml-editing | Safe hand-edit rules for serialized YAML (.unity/.prefab/.asset/.meta/ProjectSettings) when REST cannot reach — reference/fileID repair, .meta/GUID safety, ProjectSettings patch, merge conflict |
When a task touches 2+ objects in Auto / Bypass mode (or after a successful grant under Approval), prefer *_batch skills over repeated single-item calls.
Skills follow <module>_<action> or <module>_<action>_batch.
Use schema to verify the exact prefix list.
Special: scene_analyze, hierarchy_describe, project_stack_detect → perception; job_* → batch.
If a skill name does not match a valid prefix or a schema result, do not invent it.
This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${CLAUDE_PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.
This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${CLAUDE_PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.
| SwiftUI 前端设计 skill — anti AI-slop rules, design direction advisor, brand asset protocol, and five-dimension review. Works with Claude Code, Cursor, Codex, and OpenCode.
An example user-invoked skill that demonstrates frontmatter options and the skills/<name>/SKILL.md layout
Interact with iOS simulator or Android emulator/device using snapshot-based coordinates. Uses accessibility tree snapshots for precise element targeting, with screenshot verification as fallback. Use when navigating the app on a simulator/emulator.
DeepChat app settings modification (DeepChat 设置/偏好) skill. Activate ONLY when the user explicitly asks to change DeepChat's own settings/preferences (e.g., theme, language, font size...). Do NOT activate for OS/system settings, editor settings, or other apps.
Stop coding agents from shipping generic UI. Use UIZZE's 800,000+ real web and iOS screens to build product-specific interfaces, define a design contract, cover required states, and run a hard finish gate. Use for web or iOS UI design, implementation, redesign, critique, and pre-ship review in Codex, Claude Code, Cursor, Copilot, and other coding agents.
> Use this skill when the user is doing hands-on DOCA Erasure Coding programming on a BlueField DPU, ConnectX NIC, or host — bringing up a doca_ec context, picking among the create / recover / update tasks, choosing matrix type / N / K / block size, querying doca_ec_cap_* before sizing, setting doca_mmap src/dst permissions, or debugging DOCA_ERROR_* returns from doca_ec_task_*. Trigger even when the user does not name "DOCA Erasure Coding" or "Reed-Solomon" — typical implicit phrasings include "one data block changed, how do I refresh parity without re-encoding", "a disk failed and 2 parity blocks are gone, can I rebuild", "RAID-6 resilience across 12 disks", "my doca_ec_task_create returns NOT_PERMITTED", or "is this N+K layout still recoverable". Refuse and route elsewhere for non-Reed-Solomon codes (fountain / LDPC / raptor), pure-replication designs, network FEC, or other DOCA accelerator libraries (SHA / Compress / AES-GCM / DMA) — those belong to other skills.
Take besty0728/unity-skills-index 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.