Skills
98,067 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Write C#/.NET Sinch Functions with the `Sinch.Functions.Runtime` NuGet package. Use when writing or editing a function controller: answering and controlling calls with Voice API v2, IVR menus, placing, bridging or transferring calls, realtime AI voice agents, SMS/WhatsApp/RCS webhooks, custom HTTP endpoints, dependency injection, cache/storage/database and authorization. Run and deploy with the sinch-cli skill.
Craft and optimize SQL for any warehouse dialect — Snowflake, BigQuery, Databricks, Redshift, PostgreSQL. Covers window functions, CTEs, aggregations, joins, funnel queries, cohort retention, deduplication, dialect translation, slow query tuning, and cross-platform syntax differences.
Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.
Build, integrate, and answer how-to questions for Stream Chat and Stream Video in Unity Engine games and apps. Use for Unity / C# / MonoBehaviour project work - the Chat .unitypackage and the Video UPM package, StreamChatClient / StreamVideoClient wiring, ConnectUserAsync and tokens, channels and messages, calls and participant tracks, camera and microphone devices, building the UI yourself on UGUI or UI Toolkit, IL2CPP, and Android / iOS / desktop / WebGL player settings. Triggers on unity, unity engine, unity 6, unity 2022, monobehaviour, .unitypackage, Packages/manifest.json, asmdef, il2cpp, ugui, rawimage, audiosource, webcamtexture, StreamChatClient, IStreamChatClient, IStreamChannel, StreamVideoClient, IStreamVideoClient, IStreamCall, StreamVideoTrack, in-game chat, unity video call. Chat and Video only - there is no Stream Feeds SDK for Unity.
Implements Syncfusion Flutter Circular Charts (SfCircularChart) for pie, doughnut, and radial bar data visualizations in Flutter. Use when working with PieSeries, DoughnutSeries, or RadialBarSeries using the syncfusion_flutter_charts package. This skill covers chart setup, data labels, legends, tooltips, selection, annotations, gradients, animation, accessibility, and chart export.
Build responsive dashboard layouts with drag-and-drop panels, dynamic resizing, and state persistence. Guide users to implement DashboardLayout control with panel management, dragging, resizing, floating, and persistence features. Includes event handling, dynamic panel addition/removal, and comprehensive API reference.
Implement and configure the Syncfusion TypeScript Splitter control for creating responsive multi-pane interfaces. Use this skill when implementing pane configuration, orientation changes, resizing, collapse/expand functionality, and content loading. This skill covers nested layouts, styling customization, and all API properties, methods, and events for the Splitter component.
Create WinForms applications featuring the Syncfusion WinForms PDF Viewer, customized to meet specific user requirements. It supports essential PDF operations such as loading, saving, printing, text search, text extraction, and bookmark or hyperlink navigation. Additional capabilities include zooming, interaction modes, localization, theming, rendering engine selection, and robust error handling, enabling the creation of tailored and fully functional PDF viewing solutions.
Use the tailwind-animations npm package (CSS-only Tailwind CSS v4 plugin) to add ready-made animation utilities: fade, slide, zoom, flip, bounce, jelly, dialog entry/exit, scroll/view timelines, scroll-mask edge fades, duration/delay/steps/ iteration/fill-mode, and animate-slide-distance. Use when the user wants CSS animations with Tailwind, animate-* classes, motion utilities, dialog animations, scroll-driven CSS motion, scroll-mask fading edges, or to install/configure tailwind-animations. Triggers: "tailwind animations", "animate-fade-in", "animate-dialog", "scroll-mask", "slide-distance", "tailwind motion plugin", /tailwind-animations.
Odoo theme scaffolding and creation pipeline. Generates complete, installable Odoo theme modules with proper file structure, SCSS configuration, page templates, mirror models, theme.utils activation, and auto-fix installation. Supports Odoo 14-19. <example> Context: User wants to create a new Odoo website theme user: "Create a new website theme for Odoo 17" assistant: "I will use the theme-create skill to scaffold a complete theme module." <commentary>Core trigger - new theme creation.</commentary> </example> <example> Context: User wants to scaffold a theme from Figma user: "Build an Odoo 17 theme from this Figma design" assistant: "I will scaffold the theme module and extract design tokens from Figma." <commentary>Theme creation with Figma extraction.</commentary> </example> <example> Context: User wants mirror models for multi-website user: "Create theme mirror models for my website pages" assistant: "I will generate theme.ir.ui.view and theme.website.page records." <commentary>Mirror model generation.</commentary> </example> <example> Context: User wants to fix a broken theme installation user: "My theme won't install, I get an undefined variable error" assistant: "I will diagnose the SCSS load order issue and fix the map-merge pattern." <commentary>Theme installation debugging.</commentary> </example>
Implement and debug Three.js motion with AnimationMixer, clips and actions, GLTF animation playback, skeletal rigs, morph targets, cross-fades, and frame-rate-independent procedural animation. Use when playing or blending model animations, driving bones or morphs, creating timeline motion, or fixing animation lifecycle and performance issues. Triggers on: Three.js animation, AnimationMixer, AnimationAction, AnimationClip, GLTF animation, skeletal animation, bones, morph targets, crossfade, procedural motion.
Choose, configure, and optimize Three.js mesh materials: basic, Lambert, Phong, Standard, Physical, toon, points, lines, and shader-backed surfaces; PBR maps, transparency, environment reflections, cloning, and disposal. Use when styling meshes, tuning PBR, fixing transparency or material sharing bugs, or reducing material cost. Triggers on: Three.js material, MeshStandardMaterial, MeshPhysicalMaterial, PBR, roughness, metalness, transparency, environment map, mesh surface, material clone.
Install, set up, verify, update, pin, uninstall, or troubleshoot the ToolUniverse plugin on Google Antigravity (AGY / Antigravity IDE / Antigravity 2.0). ALWAYS consult this skill for any of those — don't answer from memory, because the exact CLI name (agy), the "agy plugin install <path>" flow, the uvx tooluniverse MCP server, and the API-key env vars are easy to get wrong. Use it whenever someone wants to get ToolUniverse (or "the 1000+ scientific tools" / "the harvard tools") working on Antigravity, says the Antigravity plugin or its tools/skills won't load, hits a uvx or MCP-server startup error, asks how Antigravity updates it, wants to pin or remove it, or finds it running an old tool version. Not for the Codex plugin (use tooluniverse-codex-plugin) or Claude Code plugin (use tooluniverse-claude-code-plugin), for running research with the tools, or for authoring new tools or skills.
State-of-the-art Machine Learning for PyTorch, TensorFlow, and JAX. Provides thousands of pretrained models to perform tasks on different modalities such as text, vision, and audio. The industry standard for Large Language Models (LLMs) and foundation models in science.
Use when writing, editing, reviewing or debugging TypoScript, TSconfig or Fluid templates in TYPO3 projects (v14.3 LTS is the current target). Also use for code reviews of .typoscript, .tsconfig and Fluid .html files, v13->v14 migration (INCLUDE_TYPOSCRIPT->@import, userFunc opt-in #108054, getTSFE() condition removed, updateReferenceIndex toggle removed, site.locale expression), Fluid 4->5 breaking changes, and when suggesting improvements or checking for deprecated patterns.
Use this skill for plain CSS and style-block architecture. Apply it when the task involves .css files, selectors, specificity, cascade layers, tokens, layout or theming, accessibility styling, browser-support fallbacks, or CSS architecture in Vue, Nuxt, or Tailwind-bearing projects.
Reviews a Unity 6 URP ScriptableRendererFeature that uses the Render Graph API, checking resource wiring, material binding, execution structure, and best practices. Use to validate a renderer feature.
MUST be used for Vue.js tasks. Strongly recommends Composition API with `<script setup>` and TypeScript as the standard approach. Covers Vue 3, SSR, Volar, vue-tsc. Load for any Vue, .vue files, Vue Router, Pinia, or Vite with Vue work. ALWAYS use Composition API unless the project explicitly requires Options API.
Use when building, extending, or debugging WordPress REST API endpoints/routes: register_rest_route, WP_REST_Controller/controller classes, schema/argument validation, permission_callback/authentication, response shaping, register_rest_field/register_meta, or exposing CPTs/taxonomies via show_in_rest.
Expand a raw product idea into a research-backed spec at docs/specs/<slug>/_idea.md — targeted questions, parallel codebase + market research, business-viability scoring, a trade-off debate, and an opportunity scan before drafting. The _idea.md feeds write-prd.
Use when a pull request needs to be written or opened for the current branch — "write a PR description", "create a PR", "draft a pull request", "open a PR for this branch", "generate PR text" — and when an existing PR description needs to be rewritten to team conventions.
Train and deploy a TinyML model for the XIAO ESP32S3 (Sense) using the Edge Impulse REST API only — no edge-impulse-cli needed (its serialport dep fails to build on modern Node/Windows). Covers: dataset upload, impulse creation (audio MFCC / vision transfer-learning), training jobs, downloading the Arduino library, and the on-device fixes required to actually run it on the ESP32-S3. Use this skill whenever the user wants to train/retrain a model ("재훈련", "edge impulse", "TinyML 훈련", "모델 배포"), upload a dataset to Edge Impulse, or gets EI Arduino-library build/runtime errors (mel filterbank, objs.a, tensor arena, EI_MAX_OVERFLOW_BUFFER_COUNT).
Define and use Zod schemas for TypeScript-first validation: primitives, objects, arrays, unions, refinements, transform, z.infer, parse, safeParse. Use when validating input, parsing API data, form validation with react-hook-form, or when the user mentions Zod, schema validation, or z.infer.
Configures Active Storage for file uploads with variants and direct uploads. Use when adding file uploads, image attachments, document storage, generating thumbnails, or when user mentions Active Storage, file upload, attachments, or image processing. WHEN NOT: Storing data in database columns, external URL references, static assets in the asset pipeline, or simple text/JSON storage.
Add privacy-aware session recording and replay to React applications using the Temps SDK. Captures user interactions for playback while respecting privacy through input masking, element blocking, and GDPR-compliant consent flows. Use when the user wants to: (1) Add session recording to their app, (2) Implement session replay functionality, (3) Record user sessions for debugging, (4) Add privacy-compliant screen recording, (5) Debug user issues with visual replay, (6) Implement rrweb-based recording, (7) Set up GDPR-compliant session capture. Triggers: "session recording", "session replay", "record sessions", "user replay", "screen recording", "rrweb", "session capture".
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about AI coding agents, agent runtimes, or similar internals (5) want to build agents for business, research, creative, or operational tasks Keywords: agent, assistant, autonomous, workflow, tool use, multi-step, orchestration
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.