Skills
97,905 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Build or review React Router v7/v8 animation in framework, data, or declarative mode: GSAP page transitions, component enter/exit, scroll effects, useBlocker, route reuse, and cleanup. Use even when GSAP is unnamed, including choosing viewTransition. Also covers hidden-content recovery and first-load performance. Not for Next.js, TanStack Router, React without routing, or isolated GSAP API questions.
Generates and customizes Ignite UI for Angular themes including color palettes, typography, elevations, and component-level styles using the Sass theming system and the igniteui-theming MCP server. WHEN TO USE: users ask to theme, restyle, or style Ignite UI components, change colors or the color palette, switch between light and dark themes, create or apply a global theme, customize typography or elevation shadows, adjust spacing, sizing, or roundness, or configure per-component design tokens. WHEN NOT TO USE: component behavior, APIs, or data binding (use igniteui-angular-components or igniteui-angular-grids); building whole views from a design image or Figma file (use igniteui-angular-generate-from-image-design or igniteui-angular-figma-to-app).
Initialize or update VSCode configuration files (.vscode/extensions.json and .vscode/settings.json), govern the lifecycle of extension recommendations and known replacement relationships, and establish clear boundaries between safe JSONC migration, workspace/user-level scope, preflight/postflight and rollback-verifiable acceptance; also converge `files.eol` to `"\n"`, work with `.gitattributes`, `.editorconfig` and Prettier to resolve CRLF/LF drift and git phantom modification issues on Windows, and fill in default performance optimizations for slow VSCode startup, file watching, search indexing and the TypeScript Server in large monorepos. Use this skill whenever the user mentions initializing vscode, editor configuration, workspace settings, extension replacement/deprecation migration, line ending normalization, EOL, CRLF/LF, phantom modifications, team conventions, slow VSCode startup, large repository performance, file watching noise reduction or search index optimization.
Apply iOS/SwiftUI design principles following Apple Human Interface Guidelines when building any iOS UI component. Only execute this when the current project is an iOS project and involves UI-related work. Use this skill for SwiftUI views, UIKit components, or iOS app development. Ensures HIG compliance with Clarity, Deference, and Depth principles, system colors with Dark Mode support, 8pt grid spacing, SF Pro typography with Dynamic Type, and native iOS interaction patterns. Prevents common anti-patterns like fixed text sizes, Dark Mode neglect, and Safe Area violations.
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.
Build and maintain software architecture as code with LikeC4 DSL. Use when tasks mention architecture diagrams, C4/context/container/component views, system landscape, dependency/integration maps, or when the user wants architecture generated/evolved from code. Apply for creating new `.c4`/`.likec4` models, updating existing models, validating with LikeC4 CLI, and preparing preview/build/export outputs.
Links a PostHog error occurrence or session's errors to OpenTelemetry traces, logs with the same trace ID, and Session Replay. Use when the user asks for trace or span IDs on an error, same-trace logs, or backend traces for errors in a session. Starts from an occurrence UUID, session ID, or error tracking issue URL. For a general issue diagnosis or replay summary, use investigating-error-issue or investigating-replay.
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
Route MaaFramework factual questions to version-pinned primary sources—field semantics and defaults, parameter version support, API signatures, JSON schemas, protocol behavior, and version changes. Use for any MaaFW fact-check ("what does this field mean / what is the default / which version introduced it") or whenever another MaaFW skill says to "route MaaLLMWiki." Answers must cite pinned sources; never answer from memory. Use for any MaaFramework factual question—field semantics and defaults, version support, API signatures, schemas, protocol behavior and version changes—and whenever another MaaFW skill says to route through MaaLLMWiki. Answers must cite the version-pinned upstream source, never model memory.
CRITICAL: Use for Makepad 2.0 DSL syntax and property system. Triggers on: makepad dsl, script_mod!, makepad syntax, makepad property, makepad 2.0 syntax, colon syntax, merge operator, named instance, let binding, mod.widgets, register_widget, script_component, type_default, widgets_internal
CRITICAL: Use for Makepad 2.0 event and action handling. Triggers on: makepad event, makepad action, MatchEvent, handle_event, handle_actions, on_click, on_render, on_return, on_startup, script_eval!, script_apply_eval!, button clicked, text changed, slider changed, checkbox toggled, Hit, FingerDown, FingerUp, KeyDown, KeyUp, Focus, ids!, TextCopy, TextCut, SelectionHandleDrag, PopupDismissed, clipboard, selection, IME, ImeAction, popup window events, video inputs, camera events, 事件, 动作, 点击, 输入, 回调, 交互, 事件处理, 剪贴板, 选择, 弹出窗口
CRITICAL: Use for Makepad 2.0 layout system. Triggers on: makepad layout, makepad width, makepad height, makepad flex, makepad flow, makepad padding, makepad margin, makepad spacing, makepad align, makepad sizing, Fill, Fit, Inset, Flow.Down, Flow.Right, ScrollXView, ScrollYView, 布局, 对齐, 间距, 填充, 排版, 滚动视图, 尺寸, 宽度, 高度
CRITICAL: Use for Makepad 2.0 shader system. Triggers on: makepad shader, Sdf2d, pixel shader, draw_bg, draw_text, draw_quad, makepad gpu, shader function, pixel fn, vertex fn, instance, uniform, shader variable, sdf, premultiply, Pal.premul, GaussShadow, makepad graphics, custom draw, DrawQuad, DrawVector, 着色器, 像素, 渲染, 自定义绘制, 距离场
Explains how to use Mamba selective state-space models (state-spaces/mamba package, Mamba-1 with d_state=16 and Mamba-2 with multi-head structure and d_state=128) for linear-time sequence modeling. Covers installation, the Mamba block, building a language model with MambaLMHeadModel, loading pretrained state-spaces checkpoints (130M to 2.8B) from HuggingFace, and benchmarking against Transformers. Use when implementing or loading Mamba models, processing very long sequences without a KV cache, building streaming applications, choosing between Mamba-1 and Mamba-2, or fixing install and CUDA memory problems. Requires Linux and an NVIDIA GPU. Do not use for standard Transformer models, or for RWKV, RetNet, or Hyena architectures.
MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. Use when writing MATLAB/Octave scripts for linear algebra, signal processing, image processing, differential equations, optimization, statistics, or creating scientific visualizations. Also use when the user needs help with MATLAB syntax, functions, or wants to convert between MATLAB and Python code. Scripts can be executed with MATLAB or the open-source GNU Octave interpreter.
Designs, reviews, and migrates MATLAB R2026a and GNU Octave numerical code, covering functions with arguments blocks, arrays and indexing, tables and timetables, matlab.unittest tests, MATLAB Projects, exportgraphics figures, MAT file inventory, and MATLAB-Python interoperability. Includes static helper scripts that scan .m files, plan argv commands, and hash artifacts without executing anything. Use when writing or reviewing .m code, migrating code between MATLAB releases or to Octave, setting up reproducible tests and projects, inspecting an untrusted MAT or .mlx file safely, or checking Python Engine compatibility. Do not use for pure Python numerical work with NumPy or SciPy.
Generates MATLAB Object Relational Mapping (ORM) code using Database Toolbox. Use when mapping MATLAB classes to database tables, reading/writing objects with ormread/ormwrite/ormupdate, defining Mappable classes, converting classes to SQL with orm2sql, or using object-oriented database workflows.
MatrixScan AR (Barcode AR, BarcodeAr) — scanning multiple barcodes at once with AR highlights and annotations over tracked barcodes in Android (Kotlin/Java) projects. Use for integration, scan settings, tracked-barcode handling, highlight and annotation providers, SDK version migration, or troubleshooting.
Add authentication to .NET MAUI apps. Covers WebAuthenticator for generic OAuth 2.0 / social login, and MSAL.NET for Microsoft Entra ID (Azure AD) with broker support (Microsoft Authenticator), token caching, Conditional Access, platform-specific setup (Android, iOS, Windows), DelegatingHandler for bearer token API calls, and Blazor Hybrid integration. USE FOR: "add authentication", "OAuth login", "MSAL.NET", "social login", "WebAuthenticator", "Entra ID MAUI", "Azure AD login", "Google login MAUI", "Apple login MAUI", "token caching", "bearer token", "sign in". DO NOT USE FOR: secure local storage of tokens (use maui-secure-storage), Aspire-specific auth setup (use maui-aspire), or server-side Entra ID provisioning (use entra-id-aspire-provisioning).
Guidance for custom drawing with Microsoft.Maui.Graphics, GraphicsView, canvas drawing operations, shapes, paths, text rendering, image drawing, shadows, clipping, and canvas state management. USE FOR: "custom drawing", "GraphicsView", "canvas drawing", "draw shapes", "draw path", "draw text", "ICanvas", "IDrawable", "shadows", "clipping", "Microsoft.Maui.Graphics". DO NOT USE FOR: view animations (use maui-animations), gesture handling on drawn elements (use maui-gestures), or app icons (use maui-app-icons-splash).
.NET MAUI safe area and edge-to-edge layout guidance for .NET 10+. Covers SafeAreaEdges property, SafeAreaRegions enum, per-edge control, keyboard avoidance, Blazor Hybrid CSS safe areas, migration from legacy APIs, and platform-specific behavior for Android, iOS, and Mac Catalyst. USE FOR: "safe area", "edge-to-edge", "SafeAreaEdges", "SafeAreaRegions", "keyboard avoidance", "notch insets", "status bar overlap", "iOS safe area", "Android edge-to-edge", "content behind status bar". DO NOT USE FOR: general layout or grid design (use maui-collectionview), app lifecycle handling (use maui-app-lifecycle), or theming (use maui-theming).
Interact with MCP (Model Context Protocol) servers using the mcporter CLI. Use this skill when you need to list available MCP servers, view tool schemas, call MCP tools, manage OAuth authentication, or generate CLI wrappers and TypeScript types for MCP servers.
Merge the current feature branch into main and (optionally) clean up the branch and worktree. Prefers fast-forward (--ff-only) for linear history; falls back to a merge commit (--no-ff) when the branch has diverged or the user wants the merge commit preserved. Interactive cleanup at the end. USE WHEN asked to "merge to main", "merge and cleanup", "integrate the feature branch", or "finish this branch" — i.e. a direct local merge with no review gate. For PR-based delivery (push → open a PR → link a work item → clean up after merge), use the `ship` skill instead.
Fetch metadata and manifest info for a remote Module Federation module — publicPath, remoteEntry, type file URLs, and the module's remotes/exposes/shared from its mf-manifest.json. Two modes: (1) inside a consumer project, pass only the remote name and the entry URL is resolved from mfConfig.remotes; (2) outside a consumer project, pass the remote name plus its remoteEntry URL directly. To inspect the current project's own config, use mf-context instead.
Port a Selenium WebDriver or Selenide (Java) test suite to CodeceptJS 4. Trigger when the project contains `pom.xml` declaring `selenium-java` / `selenide` / `webdrivermanager` / `junit-jupiter` / `testng`, a `build.gradle{,.kts}` with `org.seleniumhq.selenium` / `com.codeborne:selenide`, a `src/test/java/` tree with `*Test.java` / `*IT.java` / `*Steps.java`, imports from `org.openqa.selenium.*` (`WebDriver`, `By`, `WebDriverWait`, `ExpectedConditions`, `Actions`) or `com.codeborne.selenide.*` (`Selenide`, `SelenideElement`, `Condition`), JUnit/TestNG annotations (`@Test`, `@BeforeEach`, `@DataProvider`, `@FindBy`, `@ParameterizedTest`), `PageFactory.initElements(...)`, `new ChromeDriver(...)` / `Selenide.open(...)`, or Cucumber-JVM step defs (`@Given` / `@When` / `@Then`).
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.