Skills
97,725 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Build, review, debug, migrate, or plan TanStack Hotkeys keyboard shortcut systems with current docs. Use for @tanstack/react-hotkeys, @tanstack/hotkeys, useHotkey, useHotkeys, HotkeysProvider, useHotkeySequence, useHotkeySequences, useHotkeyRecorder, useHotkeySequenceRecorder, useHotkeyRegistrations, useHotkeyHint, useHeldKeys, useHeldKeyCodes, useKeyHold, formatForDisplay, findHotkeyConflicts, logical vs physical (Mod+[KeyS]) bindings, recordBy, recorder validation and conflict detection, shortcut palettes, custom shortcut settings, key sequences, scoped hotkeys, input handling, preventDefault, stopPropagation, conflictBehavior, devtools, accessibility, SSR-safe React usage, and cross-platform Mod/Ctrl/Cmd shortcuts.
Build, review, debug, migrate, or plan TanStack Query v5 (5.104.x) React server-state code with current docs. Use for @tanstack/react-query, QueryClient, QueryClientProvider, useQuery, useMutation, useInfiniteQuery, useQueries, queryOptions, mutationOptions, queryClient.query, queryClient.infiniteQuery, deprecated fetchQuery/prefetchQuery/ensureQueryData, query keys, cache defaults, staleTime, gcTime, invalidation, optimistic updates, SSR, hydration, prefetching, router integration, suspense, persistence, devtools, ESLint rules, testing, TypeScript, and v4-to-v5 migrations.
Build, review, debug, migrate, or plan TanStack Store (0.11.x, alpha) state management with current docs. Use for @tanstack/store, @tanstack/react-store, createStore, Store, ReadonlyStore, setState, subscribe, batch, flush, shallow, derived stores, createAtom, createAsyncAtom, useSelector, useStore migrations, useAtom, useCreateStore, useCreateAtom, createStoreContext, selector compare functions, immutable updates, actions factories, SSR-safe store lifetime, framework adapters, testing, and production state patterns.
Use only when the user explicitly names tdd or an upstream task explicitly invokes it to implement a feature or bug fix test-first. Execute vertical red-green-refactor cycles against the repository's real contract; proceed without redundant approval when an authoritative brief is ready, and stop before writes only when a material behavior, scope, interface, or authority decision remains unresolved.
Build, validate, or repair Adaptive Card layouts, actions, forms, and delivery wrappers for Microsoft Teams. Use when Teams is the target host, including bot, webhook, Graph, and MessageCard migration tasks. Exclude Windows/custom card hosts and Teams text-only formatting.
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.
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.
Create visual parameter tuning panels for iterative adjustment of animations, layouts, colors, typography, physics, or any numeric/visual values. Use when the user asks to "create a tuning panel", "add parameter controls", "build a debug panel", "tweak parameters visually", "fine-tune values", "dial in the settings", or "adjust parameters interactively". Also triggers on mentions of "leva", "dat.GUI", or "tweakpane".
UE5.6-UE5.8 world interaction systems for pickups, spawners, overlap/trace checks, and visual feedback. Use when requests involve interactive world actors, spawn logic, pickup behavior, interaction radius checks, success/failure feedback, and actor lifecycle control.
Create distinctive, production-grade frontend interfaces directly in code with a strong visual point of view. Use when Codex is asked to design or redesign a page, screen, flow, or component; improve UI quality; or ship polished frontend experiences that must feel intentional and non-generic. Default to Next.js unless the user specifies another framework, and use targeted 21st.dev inspiration with screenshot capture only for specific components that need references.
UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples.
Always invoke for `.uipx` files. UiPath Solution lifecycle via `uip solution`: init/download/restore/pack/publish/deploy/activate/upgrade/upload, projects add|import|remove, resources refresh|add|remove|edit, feeds list, `--feed` / `--personal-workspace`. DIAGNOSE lifecycle failures: pack/publish/deploy/activate errors, stale/missing bindings, unimported/unresolved resources, deploy error codes, `--acknowledge-permanent-deletion` consent, publish name+version/processKey collisions, redeploy blocked by an existing deployment (`deploy upgrade`), feed 'not an available publish location', package not in `packages list`, 'unknown command' after new→init rename. Bundles RPA/Flow/Case/Agents/API Workflow/AppV2 projects in one `.uipx`. Routing: PDD→SDD design & task derivation→uipath-planner; non-solution Orchestrator/IS/resources/auth/traces→uipath-platform; .xaml/.cs→uipath-rpa; .flow→uipath-maestro-flow; .bpmn→uipath-maestro-bpmn; agent.json/.py agents→uipath-agents; standalone coded-app deploy→uipath-coded-apps.
Type-safe file upload integration for Next.js App Router using UploadThing. Use when implementing secure file uploads with client-to-storage direct uploads, authentication middleware, upload completion handlers, and automatic database metadata storage.
Velt collaboration SDK setup guide for React, Next.js, Angular, Vue, and HTML applications. Use this skill when setting up Velt for the first time, configuring VeltProvider, implementing user authentication with authProvider and JWT tokens, initializing document collaboration with setDocuments, adding VeltUserInviteTool for share & invite flows, or debugging Velt setup issues. Triggers on any task involving Velt installation, VeltProvider configuration, auth token generation, document identity setup, share/invite components, or project structure for Velt integration — even if the user doesn't explicitly mention "setup".
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
Confirms or rejects findings from review-llm-artifacts before deletes or risky refactors. Loads review-verification-protocol-style checks per finding. Use after a review run, when the user wants to reduce false positives, before fix-llm-artifacts on dead code, or when validating a full-project scan.
This skill provides expert-level guidance for implementing VS Code WebView features. Use when creating WebView panels, implementing secure CSP policies, handling Extension-WebView communication, managing WebView state persistence, optimizing WebView performance, or debugging WebView rendering issues. Covers security best practices, message protocols, and VS Code-specific WebView patterns.
Apply Web Scraping with Python practices (Ryan Mitchell). Covers First Scrapers (Ch 1: urllib, BeautifulSoup), HTML Parsing (Ch 2: find, findAll, CSS selectors, regex, lambda), Crawling (Ch 3-4: single-domain, cross-site, crawl models), Scrapy (Ch 5: spiders, items, pipelines, rules), Storing Data (Ch 6: CSV, MySQL, files, email), Reading Documents (Ch 7: PDF, Word, encoding), Cleaning Data (Ch 8: normalization, OpenRefine), NLP (Ch 9: n-grams, Markov, NLTK), Forms & Logins (Ch 10: POST, sessions, cookies), JavaScript (Ch 11: Selenium, headless, Ajax), APIs (Ch 12: REST, undocumented), Image/OCR (Ch 13: Pillow, Tesseract), Avoiding Traps (Ch 14: headers, honeypots), Testing (Ch 15: unittest, Selenium), Parallel (Ch 16: threads, processes), Remote (Ch 17: Tor, proxies), Legalities (Ch 18: robots.txt, CFAA, ethics). Trigger on "web scraping", "BeautifulSoup", "Scrapy", "crawler", "spider", "scraper", "parse HTML", "Selenium scraping", "data extraction".
Receive and verify WhatsApp Business Platform (Cloud API) webhooks from Meta. Use when setting up WhatsApp webhook handlers, completing the GET verification handshake, debugging X-Hub-Signature-256 signature verification, or handling inbound message and message status (sent, delivered, read, failed) events under the whatsapp_business_account object.
Use when you need to clarify requirements and route to the right workflow (idea → executable input). Project intake + routing: help the user brainstorm and clarify intent, persist goal/context artifacts, then dispatch to the right workflow or step skill. Default route is workflow-ship-faster (Next.js 16.1.1) for idea/prototype→launch. Triggers: project kickoff, requirements clarification, brainstorm, ideas, discovery, intake.
Workleap's shared web configuration packages (@workleap/eslint-configs, @workleap/typescript-configs, @workleap/rsbuild-configs, @workleap/rslib-configs, @workleap/stylelint-configs, @workleap/browserslist-config). Use when setting up, customizing, extending, or troubleshooting shared web tooling configs in a Workleap project — including ESLint, TypeScript, Rsbuild, Rslib, Stylelint, Browserslist, and monorepo (Turborepo) strategies. Activate even if only one tool is mentioned, as the packages are designed to work together.
Use when integrating Gravity Forms with OpenAI via Gravity Connect: configuring OpenAI Fields (real-time pre-submission AI) or OpenAI Feeds (async post-submission processing), setting token ceilings, routing through OpenRouter, using GPT Image generation, voice-to-text transcription, or building AI-powered form workflows.
Use when working with Gravity Forms: installing or updating core and add-ons via wp gf CLI, managing forms and entries programmatically, exporting/importing form JSON for version control, testing notifications, configuring Cloudflare Turnstile anti-spam, or turning forms into MCP-compatible schemas for AI consumption. Also use for the GFAPI PHP class and hook/filter development.
Use when working with Gravity Wiz products: installing or managing Spellbook (the Gravity Wiz platform), Gravity Perks (48+ form enhancement plugins like GP Populate Anything, Nested Forms, Limit Submissions), or any individual perk. Also use for Gravity Shop (WooCommerce integration).
This skill should be used when a user wants to decompose an Epic into its complete set of Features all at once, invoked automatically after write-epic completes, or triggered by phrases like "create all features for this epic", "walk me through all the features", "let's break down this epic", or "plan the features for epic #N". Use this skill for bulk Feature decomposition. Supports two planning modes — `guided` (one Feature at a time, with questions) and `flow` (draft the whole set in parallel, one consolidated review) — passed as an argument or read from `.wtf/config.json`. Use `wtf.write-feature` for creating a single Feature in isolation.
This skill should be used when a user wants to create a task, write a ticket, decompose a feature into implementable work, break down a story, define a vertical slice for development, or write Gherkin scenarios — for example "create a task", "write a task for this feature", "break this feature into tasks", "define implementation work", or "add a sub-issue to this feature". Guides creation of a GitHub Task issue linked to a parent Feature and Epic, derives Gherkin acceptance scenarios from the Feature's ACs, enforces DDD ubiquitous language in scenarios, and checks for vertical-slice integrity and task dependencies.
Integrate LangChain applications with You.com tools (web search, content extraction, retrieval) in TypeScript or Python. Use when developer mentions LangChain, LangChain.js, LangChain Python, createAgent, initChatModel, DynamicStructuredTool, langchain-youdotcom, YouRetriever, YouSearchTool, YouContentsTool, or You.com integration with LangChain.
Complete guide to zapret-openwrt, an anti-DPI tool for OpenWrt routers. Use for any zapret-openwrt question: project architecture, configuration, DPI bypass strategies, LuCI web UI, scripts, updates, diagnostics, custom.d hooks, host lists, nfqws parameters, procd service management. Also use for development: adding strategies, changing the UI, writing custom.d scripts, debugging. Triggers: zapret, nfqws, DPI desync, обход блокировок, антиблокировка, zapret strategies, hostlist, autohostlist, стратегии zapret, роутер, блокировки.
Use for cross-module development, tracing which chain something belongs to, deciding which BK-CI module a requirement should land in, or quickly understanding how the full pipeline chain works together. For single-module changes, read the corresponding module skill first rather than staying here.
Expose an AG2 `Agent` over the Agent-to-Agent (A2A) protocol so any A2A-compliant client (or another AG2 agent) can call it across process/host boundaries. Wrap the agent with `A2AServer(agent)` and serve it via `build_jsonrpc(...)`, `build_rest(...)`, or `build_grpc(...)` — each returns a ready-to-serve ASGI/gRPC object that publishes an A2A `AgentCard` (built by `build_card`) at `/.well-known/agent-card.json`. Use when you want an AG2 agent reachable as a standard networked A2A service — interop with non-AG2 A2A clients, multi-transport (JSON-RPC / REST / gRPC) endpoints, declared auth schemes, push notifications, or multi-tenancy. To consume a remote A2A agent from AG2 instead, point an `Agent` at `A2AConfig(card_url=...)`. Covers `A2AConfig`, `A2AServer`, `build_card`, security schemes (`bearer_scheme`/`api_key_scheme`/`oauth2_scheme`/`require`), and the in-process `testing.py` helpers (`make_test_client_factory`, `make_test_rest_client_factory`).
Use this skill for Node.js backend AI via @cloudbase/node-sdk (>=3.16.0) — cloud functions, CloudRun, Express/Koa/NestJS, serverless APIs, scheduled jobs, LLM proxies, agent orchestration. The only SDK supporting image generation (ai.createImageModel + generateImage). Text via ai.createModel with groups cloudbase, hunyuan-exp, or custom-*; model ids (e.g. deepseek-v4-flash, glm-5, kimi-k2.6) go in the `model` field of generateText/streamText. MUST run two-step preflight before code — see body. NOT for browser/Web (use ai-model-web) or Mini Program (use ai-model-wechat).
Design, redesign, build, audit and validate distinctive production websites with cinematic scroll reveals, product films, burst or exploded-view effects, reference-led design systems, purposeful motion and multi-pass refinement. Use for landing pages, product sites, portfolios, interactive storytelling, premium or immersive web experiences, scroll-controlled product inspection, assembly or disassembly sequences, camera moves, image/video-led recreation, hero refinement, motion graphics, and anti-generic visual polish in Astro, React, Next.js, Vue, Svelte or static HTML/CSS. Infer cinematic intent from the requested experience or reference; the user does not need to say "wow" or name a tool.
Calculate text similarity using lexical and semantic methods for matching and deduplication. Use this skill when the user needs to find similar documents, detect near-duplicates, or measure semantic closeness between texts — even if they say 'how similar are these texts', 'find duplicates', or 'semantic matching'.
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.