Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 86 961 files from 2 125 authors, of which 68 678 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Advises on assigning Unity script roles — whether a class should be a MonoBehaviour, ScriptableObject, plain C# service, or installer. Use when deciding a class's role, splitting responsibilities across types, or choosing between MonoBehaviour and plain C#, even if the user just asks "这个该用MonoBehaviour吗" or "职责怎么分". 为 Unity 脚本职责划分提供建议(某个类应作 MonoBehaviour、ScriptableObject、纯 C# 服务还是 installer);当用户要确定类的职责、在类型间拆分职责、或在 MonoBehaviour 与纯 C# 间抉择时使用。
Advises on Unity gameplay script quality — code review, reducing coupling, improving maintainability, and refactoring. Use when reviewing code quality, untangling tightly-coupled scripts, or planning a refactor for maintainability, even if the user just says "看看我代码" or "代码有点乱". 为 Unity 游戏脚本质量提供建议(代码审查、降低耦合、提升可维护性、重构);当用户要审查代码质量、理顺高耦合脚本、或为可维护性规划重构时使用。
Create, read, and analyze C# scripts — create, read, replace, append, search, rename, move, and delete scripts, plus compile feedback. Use when authoring or editing C# code, searching across scripts, refactoring file layout, or checking compile errors, even if the user just says "写个脚本" or "改代码". 对 C# 脚本进行增删改查与分析(创建、读取、替换、追加、搜索、重命名、移动、删除脚本,以及编译反馈);当用户要编写或编辑 C# 代码、跨脚本搜索、重构文件布局、或检查编译错误时使用。
Manage ScriptableObject assets — create, read, modify, delete, duplicate, find, and list SO assets. Use when creating or editing ScriptableObject data assets, finding SO instances, or scripting SO management, even if the user just says "配置表" or "SO资产". 管理 ScriptableObject 资产(创建、读取、修改、删除、复制、查找、列出 SO 资产);当用户要创建或编辑 ScriptableObject 数据资产、查找 SO 实例、或脚本化管理 SO 时使用。
Manage HLSL/ShaderLab .shader files — create, read, list, find, delete, and inspect shader properties/keywords. Use when creating or editing handwritten shaders, listing or finding .shader files, or inspecting their properties and keywords, even if the user just says "写个shader" or "着色器文件". 管理 HLSL/ShaderLab .shader 文件(创建、读取、列出、查找、删除、检查 shader 属性/关键字);当用户要创建或编辑手写 shader、列出或查找 .shader 文件、或检查其属性与关键字时使用。
Create and inspect Shader Graph assets — create graphs, inspect structure, and perform constrained blackboard and node editing. Use when creating a Shader Graph, inspecting its structure, or making controlled edits to its blackboard or nodes, even if the user just says "shader graph" or "着色器图". 创建与检查 Shader Graph 资产(创建图、检查结构、受约束的黑板与节点编辑);当用户要创建 Shader Graph、检查其结构、或对黑板/节点做受控编辑时使用。
Operate on Unity Terrain — create TerrainData, sculpt heights, paint texture layers, and smooth/flatten regions. Use when creating or editing terrain, sculpting or smoothing the heightmap, or painting terrain texture layers, even if the user just says "地形" or "刷地面". 操作 Unity Terrain(创建 TerrainData、雕刻高度、绘制纹理层、平滑/压平区域);当用户要创建或编辑地形、雕刻或平滑高度图、或绘制地形纹理层时使用。
AI-powered scene operations — SQL-like and spatial object queries plus automatic layout and auto-binding. Use when querying scene objects by condition or proximity, auto-arranging objects, or auto-wiring references, even if the user just says "找出所有…的物体" or "自动排列". AI 驱动的场景操作(类 SQL 与空间对象查询、自动布局、自动绑定);当用户要按条件或邻近关系查询场景对象、自动排布对象、或自动连线引用时使用。
Source-anchored Shader Graph design rules for Unity 2022.3 — graph structure, node subset, SubGraph boundaries, master stack, blackboard/keywords, recipes, and review. Use when building or reviewing Shader Graphs, structuring node chains or SubGraphs, laying out blackboard/keywords, or following URP/HDRP graph recipes, even if the user just says "连个shader graph" or "着色器节点". 为 Unity 2022.3 的 Shader Graph 提供源码锚定的设计规则(图结构、节点子集、SubGraph 边界、主节点堆栈、黑板/关键字、配方、审查);当用户要构建或审查 Shader Graph、组织节点链或 SubGraph、布置黑板/关键字、或参考 URP/HDRP 图配方时使用。
Create and lay out Unity UGUI (Canvas-based UI) — Canvas, panels, buttons, text, images, and layout groups. Use when building UGUI screens, adding Canvas elements, or arranging UI layout, even if the user just says "做个UI" or "界面". 创建与布局 Unity UGUI(基于 Canvas 的 UI:Canvas、面板、按钮、文本、图片、布局组);当用户要搭建 UGUI 界面、添加 Canvas 元素、或排布 UI 布局时使用。
Edit Unity Timeline — create Timeline assets and add typed tracks (animation, activation, audio, signal, etc.). Use when building cutscenes or sequences, creating a Timeline asset, or adding tracks and clips, even if the user just says "时间轴" or "做个过场动画". 编辑 Unity Timeline(创建 Timeline 资产、添加带类型的轨道:动画、激活、音频、信号等);当用户要制作过场或序列、创建 Timeline 资产、或添加轨道与片段时使用。
Advises on Unity testability — isolating logic out of MonoBehaviour and planning EditMode/PlayMode tests. Use when improving testability, extracting logic for unit tests, or planning a test strategy, even if the user just says "怎么测试" or "代码不好测". 为 Unity 可测试性提供建议(把逻辑从 MonoBehaviour 中剥离、规划 EditMode/PlayMode 测试);当用户要提升可测试性、为单元测试抽取逻辑、或规划测试策略时使用。
Build Unity UI Toolkit (UITK) UIs — create/edit USS stylesheets and UXML layouts, configure UIDocument components, declare runtime data bindings in UXML, create world-space UI panels, and run UXML upgraders. Use when authoring runtime or editor UI with UI Toolkit, writing USS/UXML, wiring a UIDocument, binding UI to a data source, or building 3D/world-space UI, even if the user just says "UITK" or "UXML". 构建 Unity UI Toolkit(UITK)界面(创建/编辑 USS 样式表与 UXML 布局、配置 UIDocument 组件、在 UXML 中声明运行时数据绑定、创建世界空间 UI 面板、批量升级 UXML);当用户要用 UI Toolkit 编写运行时或编辑器 UI、编写 USS/UXML、接入 UIDocument、把 UI 绑定到数据源、或做 3D/世界空间 UI 时使用。
Advisory guidance for using the experimental Unity CLI (the official `unity` command-line tool) alongside UnitySkills — cold-start a bound project without Unity Hub, probe editor liveness, launch with arguments, run headless tests, run one-shot batch automation, and build headlessly. Only applies when the project has been bound in the UnitySkills panel (Library/UnitySkills/cli_config.json exists with enabled:true). 实验性 Unity CLI(官方 unity 命令行工具)与 UnitySkills 协同的指导文档——免 Unity Hub 冷启动已绑定项目、探测编辑器存活、传参启动、无头测试、批处理运行、无头构建;仅当项目已在 UnitySkills 面板完成绑定(存在 Library/UnitySkills/cli_config.json 且 enabled:true)时适用。
Source-anchored design rules for Cysharp UniTask 2.5.10 (Unity 2018.4+) — struct semantics, PlayerLoop timing, cancellation, composition, conversion, async enumerables, triggers, and pitfalls. Use when writing or reviewing async UniTask code, choosing PlayerLoopTiming, handling CancellationToken, or composing WhenAll/WhenAny, even if the user just says "异步" or "零分配async". 为 Cysharp UniTask 2.5.10(Unity 2018.4+)提供源码锚定的设计规则(struct 语义、PlayerLoop 时机、取消、组合、转换、异步流、触发器、陷阱);当用户要编写或审查 async UniTask 代码、选择 PlayerLoopTiming、处理 CancellationToken、或组合 WhenAll/WhenAny 时使用。
Manage the Universal Render Pipeline (URP) — URP assets, the renderer, and renderer features. Use when configuring the URP asset, adding or editing renderer features, or adjusting URP rendering settings, even if the user just says "URP配置" or "渲染特性". 管理通用渲染管线(URP:URP 资产、渲染器、渲染器特性);当用户要配置 URP 资产、添加或编辑渲染器特性、或调整 URP 渲染设置时使用。
Work with the SRP Volume framework — create/load VolumeProfile assets and create global/local Volume GameObjects with components. Use when setting up volumes, creating or loading a VolumeProfile, or adding global/local volumes to a scene, even if the user just says "Volume" or "体积". 使用 SRP Volume 框架(创建/加载 VolumeProfile 资产、创建全局/局部 Volume GameObject 及组件);当用户要搭建 Volume、创建或加载 VolumeProfile、或向场景添加全局/局部 Volume 时使用。
Validate project and scene health plus cleanup — find broken references, missing scripts, and other integrity issues. Use when checking for broken or missing references, validating scene/project integrity, or cleaning up issues before a build, even if the user just says "检查引用" or "有没有丢失". 校验项目与场景健康度并清理(查找断裂引用、丢失脚本及其他完整性问题);当用户要检查断裂或丢失引用、校验场景/项目完整性、或在构建前清理问题时使用。
Set up XR Interaction Toolkit (XRI) for VR/AR — XR rigs and grab/socket/ray interactors. Use when building VR/AR interaction, setting up an XR rig, or configuring grab/socket/ray interactors, even if the user just says "VR" or "XR交互". 搭建用于 VR/AR 的 XR Interaction Toolkit(XRI:XR rig、抓取/插槽/射线交互器);当用户要构建 VR/AR 交互、搭建 XR rig、或配置抓取/插槽/射线交互器时使用。
Persistent operation history and orchestration — snapshots, task/session undo, bookmarks, and batch planning/retry/rollback. Use when undoing a whole task or session, snapshotting before risky changes, planning or previewing batch operations, or rolling back, even if the user just says "撤销整个操作" or "回滚". 持久化操作历史与编排(快照、任务/会话级撤销、书签、批量规划/重试/回滚);当用户要撤销整个任务或会话、在高危改动前快照、规划或预览批量操作、或回滚时使用。
Last-resort guidance for safely hand-editing Unity serialized YAML (.unity/.prefab/.asset/.meta/ProjectSettings) — reference/fileID repair, GUID safety, and merge-conflict fixes. Use when REST cannot reach the change and YAML must be hand-edited — fixing m_Script GUIDs, broken fileID references, .meta files, or merge conflicts, even if the user just says "场景文件打不开" or "引用丢了". 安全手编 Unity 序列化 YAML(.unity/.prefab/.asset/.meta/ProjectSettings)的最后手段(引用/fileID 修复、GUID 安全、合并冲突修复);当 REST 无法触达、必须手编 YAML 时使用——修复 m_Script GUID、断裂 fileID 引用、.meta 文件或合并冲突。
Source-anchored design rules for YooAsset v2.3.18 — initialization, default-package shortcuts, play modes, asset handles, loading, updates, filesystem, build, and pitfalls. Use when writing or reviewing YooAsset code, initializing packages, loading assets via handles, setting up hot-update/download, or choosing a play mode, even if the user just says "热更" or "资源包". 为 YooAsset v2.3.18 提供源码锚定的设计规则(初始化、默认包快捷方式、运行模式、资源句柄、加载、更新、文件系统、构建、陷阱);当用户要编写或审查 YooAsset 代码、初始化 package、用句柄加载资源、配置热更/下载、或选择运行模式时使用。
Automate YooAsset hot-update and asset bundles — build bundles, run Editor simulate builds, manage Collector groups, analyze BuildReport, and validate runtime. Use when building or simulating YooAsset bundles, configuring collectors, or validating hot-update assets, even if the user just says "热更" or "打AB包". 自动化 YooAsset 热更新与资源包(构建 bundle、编辑器模拟构建、管理 Collector 分组、分析 BuildReport、运行时校验);当用户要构建或模拟 YooAsset 资源包、配置 collector、或校验热更资源时使用。
Use when writing or running Paparazzi screenshot tests in stripe-android — covers PaparazziRule setup, recording/verifying commands, and test structure
Use when writing or structuring unit tests in stripe-android — covers runScenario pattern, fakes, Turbine Flow testing, and Truth assertions
Use when writing Compose UI tests in stripe-android — covers composeRule setup, Robolectric annotations, node assertions, and test tag patterns
Use when writing NetworkRule integration tests in stripe-android — covers testBodyFromFile, inline JSON modification, request matchers, and fixture patterns
Use when creating a fake test implementation in stripe-android — covers FakeClassName pattern, Turbine call tracking, ViewActionRecorder, and ensureAllEventsConsumed validation
ERC-8004 Trustless Agents — on-chain agent identity + reputation. Resolve an agent by id (Identity Registry ERC-721 → owner + AgentCard), list the canonical registry addresses, and generate a spec-compliant agent registration card (registration-v1, with x402 support + trust models). Custody-free, read + scaffolding. Triggers: ERC-8004, trustless agent, agent identity, agent registry, AgentCard, agent reputation, on-chain agent, A2A, agent discovery, agent card, 8004.
x402 agentic payments (Coinbase's HTTP 402 protocol). Custody-free tools to pay x402-protected endpoints (build the EIP-3009 transferWithAuthorization the payer signs, assemble the X-PAYMENT header), call a facilitator (verify/settle/supported), and monetize your own API by generating PaymentRequirements. USDC on Base. Triggers: x402, HTTP 402, pay per request, agentic payment, machine payment, X-PAYMENT, transferWithAuthorization, EIP-3009, facilitator, monetize API, pay for API, agent pays.
Use when building wallet infrastructure, authenticating users, managing embedded wallets, configuring access controls and policies, or integrating blockchain transactions into applications. Reach for this skill when working with user onboarding, wallet creation, transaction signing, policy enforcement, or API integration across Ethereum, Solana, and other blockchains.
Create, track and update team goals + KPIs via the Deeplake virtual filesystem at memory/goal/ and memory/kpi/. Use whenever the user mentions a goal, objective, KPI, target, milestone, or asks to track progress on something measurable. ALSO use when the user says "task", "todo", "work item", "remind me to", "fix X", or any actionable work item — the goal system replaced the legacy `hivemind tasks` CLI and now covers both objectives and tasks.
Query the local code graph (functions, classes, calls, imports) through the Deeplake mount at memory/graph/. Use when the user asks structural questions about the codebase — "what calls X?", "what does Y import?", "where is Z defined?", "what's the architecture / which subsystems exist?", "what's the impact of changing this?". The graph is an AST-derived map of the repo, queried as files (no build needed — it rebuilds automatically).
Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.
Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.
Create, track and update team goals + KPIs via the Deeplake virtual filesystem at memory/goal/ and memory/kpi/. Use whenever the user mentions a goal, objective, KPI, target, milestone, or asks to track progress on something measurable. ALSO use when the user says "task", "todo", "work item", "remind me to", "fix X", or any actionable work item — the goal system replaced the legacy `hivemind tasks` CLI and now covers both objectives and tasks.
Query the local code graph (functions, classes, calls, imports) through the Deeplake mount at memory/graph/. Use when the user asks structural questions about the codebase — "what calls X?", "what does Y import?", "where is Z defined?", "what is the architecture / which subsystems exist?". The graph is an AST-derived map of the repo, queried as files (no build needed — it rebuilds automatically).
Create, track and update team goals + KPIs in Hivemind via the `hivemind` CLI. Use whenever the user mentions a goal, objective, KPI, target, milestone, or asks to track progress on something measurable. ALSO use when the user says "task", "todo", "work item", "remind me to", "fix X", or any actionable work item — the goal system replaced the legacy `hivemind tasks` CLI and now covers both objectives and tasks.
Query the local code graph (functions, classes, calls, imports) through the Deeplake mount at memory/graph/. Use when the user asks structural questions about the codebase — "what calls X?", "what does Y import?", "where is Z defined?", "what is the architecture / which subsystems exist?". The graph is an AST-derived map of the repo, queried as files (no build needed — it rebuilds automatically).
Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.
Create, track, and read team goals + KPIs via Hivemind from openclaw. Use whenever the user mentions a goal, objective, KPI, target, milestone, or asks to track progress on something measurable. ALSO use when the user says "task", "todo", "work item", "remind me to", "fix X", or any actionable work item — the goal system replaced the legacy `hivemind tasks` CLI and now covers both objectives and tasks.
Query the local AST-derived code graph (functions, classes, calls, imports) for structural codebase questions — what calls X, what does Y import, where is Z defined, blast radius of a change. The graph rebuilds automatically after each agent turn; use hivemind_graph_search and hivemind_graph_neighborhood tools (no manual build step).
Use when answering a question that needs data from a ktx-connected database - investigating, analyzing, "how many", "show me", "what's the breakdown of", finding records by value, exploring tables, comparing periods, explaining metrics, or any data-analysis request. Triggers even when the user does not say "analytics"; if the answer requires querying a configured ktx connection, this skill applies.
Map dbt `schema.yml` / `properties.yml` models and sources into ktx semantic-layer overlays and column notes. Covers `sources:` vs `models:`, column `data_tests` (not_null, unique, accepted_values, relationships), and how bundle-time writes complement manifest backfill from git sync. Load when the WorkUnit's `skillNames` includes `dbt_ingest` or when raw files are dbt YAML under `models/` / `sources/`.
Synthesize durable KTX wiki pages from staged Google Drive document pulls. Load when a WorkUnit contains Google Doc raw files from `docs/**`.
Identify recurring cross-table historic-SQL analytical intents from a bounded pattern shard and emit typed pattern evidence for deterministic wiki projection.
Convert one changed historic-SQL table usage bucket into typed table usage evidence for deterministic _schema projection.
Classify and resolve conflicts detected during bundle ingest (structural duplicates, definitional contradictions, near-duplicate clusters, re-ingest changes, evictions).
Capture semantic-layer and knowledge updates from a live database schema snapshot.
Extract durable ktx knowledge and semantic-layer contribution proposals from staged Looker runtime dashboard, Look, and explore JSON. Load for WorkUnits whose raw files are under explores/, dashboards/, or looks/.
Map a LookML view/model/explore into ktx semantic layer sources. Covers the LookML to ktx primitive table, provenance tagging, and three worked examples (overlay, standalone from derived_table, standalone with sql_always_where). Load when the turn contains `.lkml` content.
Convert Metabase questions, models, and metrics into ktx Semantic Layer source definitions. Covers result-metadata to KSL column type mapping, FK/PK detection, near-duplicate deduplication, pre-aggregation decomposition, join-graph connectivity, and how to react to priorProvenance from earlier ingest syncs. Load when the WorkUnit contains `cards/<id>.json` files under a Metabase bundle.
Map a MetricFlow semantic_model or metric into ktx semantic layer sources. Covers the MetricFlow to ktx primitive table, `extends:` inheritance flattening, metric-type handling (simple / derived / ratio / cumulative / conversion), `model: ref('x')` resolution, and four worked examples. Load when the turn contains `.yml`/`.yaml` files with top-level `semantic_models:` or `metrics:`.
Synthesize durable ktx wiki pages and semantic-layer sources from staged Notion pages, databases, data-source rows, and clustered Notion evidence. Load when a WorkUnit contains Notion raw files or Notion evidence chunks.
Extract durable ktx wiki knowledge from staged Sigma data model specs and workbook summaries. Load for WorkUnits with unitKey sigma-data-models or sigma-workbooks.
ktx's semantic layer - a structured catalog of sources (tables/views), measures, joins, and segments expressed as YAML. Covers the schema and how to query it via `sl_query`. Use when the task involves querying pre-defined metrics (ARR, churn, retention, LTV, MAU) or reading SL source YAML to understand the catalog. Capture is handled by the `sl_capture` skill (memory-agent only).
How to capture new reusable patterns into ktx's semantic layer - when a measure, segment, or join belongs in the catalog and how to write it generically so it stays small and useful over time. Loaded by the post-turn memory-agent only. The research agent does not write to the SL.
ktx's knowledge base - wiki pages for durable, reusable business knowledge. Covers capture workflow for user preferences, metric definitions, organizational conventions, and cross-references between wiki pages and semantic-layer sources. Loaded by the post-turn memory-agent only. The research agent reads wiki via `wiki_read`/`wiki_search` but does not write it.
Installs and configures ktx, the open-source context layer for data agents — runs ktx setup non-interactively with hidden CLI flags, configures database connections and embeddings, installs agent integration, and verifies readiness. Use when the user asks an agent to add ktx to a project, connect data sources, install agent rules, ingest schema, or troubleshoot a local ktx install.
Claude Skills — questions
Answers built from the skills we actually parsed.