Skills
98,639 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Implement and debug Motion for React in Next.js: local interaction, presence, layout, shared elements, scroll, reduced motion, and router integration. Use for explicit Motion/Framer Motion work or interactions that need it; prefer CSS for simple effects and framework-native view transitions for supported route cases.
This skill provides comprehensive guidance for using OpenCode, the open-source AI coding agent. Use this skill when working with OpenCode CLI commands, keyboard shortcuts, agents (build/plan), slash commands, tools, skills, MCP servers, or configuration. Automatically triggered when OpenCode-specific questions or tasks are detected.
Production pipeline for interactive and generative visual art using p5.js. Covers 2D/3D rendering, noise and particle systems, flow fields, GLSL shaders, pixel manipulation, kinetic typography, WebGL, and audio-reactive visuals, with headless export to HTML, PNG, GIF, MP4 or SVG. From NousResearch's Hermes agent.
Performs deep codebase analysis to generate 11 comprehensive documentation files. Adapts output based on the selected route -- Greenfield extracts business logic only (tech-agnostic), Brownfield extracts business logic + technical implementation (tech-prescriptive). Step 2 of 6 in reverse engineering. Use when asked to reverse engineer the codebase, extract business logic, or generate comprehensive documentation.
Use when a Three.js scene has performance problems: low FPS, memory leaks, too many draw calls, or high GPU memory usage. Prevents the common mistake of forgetting dispose(), creating objects in the render loop, or not using InstancedMesh for repeated objects. Covers disposal patterns, draw call optimization, InstancedMesh, LOD, texture compression, renderer.info, Stats.js profiling. Keywords: performance, memory leak, dispose, draw calls, FPS, slow, optimization, InstancedMesh, LOD, renderer.info, Stats, profiling, laggy, low FPS, stuttering, browser freezes.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".
Use when debugging 'file not syncing', 'CloudKit error', 'sync conflict', 'iCloud upload failed', 'ubiquitous item error', 'data not appearing on other devices', 'CKError', 'quota exceeded' - systematic iCloud sync diagnostics for both CloudKit and iCloud Drive
Use when writing raw SQL queries with GRDB, complex joins, ValueObservation for reactive queries, DatabaseMigrator patterns, query profiling under performance pressure, or dropping down from SQLiteData for performance - direct SQLite access for iOS/macOS
Use when integrating ANY iOS system feature - Siri, Shortcuts, widgets, IAP, camera, photo library, audio, ShazamKit, haptics, localization, privacy, alarms, calendar, reminders, contacts. Covers App Intents, WidgetKit, StoreKit, AVFoundation, ShazamKit, Core Haptics, Spotlight, EventKit, Contacts
Use when needing Vision framework API details for hand/body pose, segmentation, text recognition, barcode detection, document scanning, or Visual Intelligence integration. Covers VNRequest types, coordinate conversion, DataScannerViewController, RecognizeDocumentsRequest, SemanticContentDescriptor, IntentValueQuery
Expert knowledge for Azure Api Center development including best practices, security, configuration, integrations & coding patterns, and deployment. Use when setting API auth, provisioning API Center, automating linting/registration, self-hosting the portal, or syncing with API gateways, and other Azure Api Center related development tasks. Not for Azure API Management (use azure-api-management), Azure Resource Manager (use azure-resource-manager), Azure Portal (use azure-portal)
Expert knowledge for Azure Queue Storage development, including best practices, limits and quotas, security, configuration, integrations, and coding patterns. Use when configuring queue authentication or encryption, monitoring metrics or logs, handling limits, coding with Azure Queue SDKs, or performing other Azure Queue Storage development tasks. Not for Azure Service Bus (use azure-service-bus), Azure Event Hubs (use azure-event-hubs), or Azure Table Storage (use azure-table-storage).
Builds carousels with @blossom-carousel/vue in Vue 3 and Nuxt, covering BlossomCarousel setup, CSS scroll-snap layouts, BlossomPrev/BlossomNext/BlossomDots/BlossomDot controls, template-ref methods (prev, next, goTo), useBlossomNavigation for custom controls, and command and overscroll events. Use when a Vue or Nuxt project imports @blossom-carousel/vue or renders <BlossomCarousel>, or when the user wants a Blossom carousel, slider, or gallery in Vue or Nuxt.
Unvarnished technical criticism combining Linus Torvalds' precision, Gordon Ramsay's standards, and James Bach's BS-detection. Use when code/tests need harsh reality checks, certification schemes smell fishy, or technical decisions lack rigor. No sugar-coating, just surgical truth about what's broken and why.
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text.
An execution-focused skill for developing, maintaining, distributing, and validating DeepSeek Harness (DSH) plugins. Covers host/client form assessment, bundle/profile contracts, Service and function plugins, tools, HTTP, persistence, slots, Conversation Node, client builds, HMR, GitHub installation, and real-world integration testing.
Build and deploy machine learning models with PyTorch, HuggingFace Transformers, and scikit-learn. Use when you need model training, fine-tuning with LoRA/QLoRA, text classification, NER, embeddings, RAG pipelines, dataset preparation, model evaluation, hyperparameter tuning, ONNX export, quantization, inference optimization, or classical ML with XGBoost and scikit-learn.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics
Structured Git commit messages following Conventional Commits for Go projects. Generates well-scoped, atomic commits with clear descriptions. Use when committing changes, writing commit messages, preparing PRs, or reviewing commit history quality. Examples: “commit these changes,” “create commit,” “commit message,” “prepare PR,” “squash commits.” Not for code review (go-code-review) or changelog generation.
Correct usage of context.Context in Go: propagation, cancellation, timeouts, deadlines, values, and common anti-patterns. Use when: "context usage", "context.Context", "context cancellation", "timeout", "context.WithTimeout", "context.WithCancel", "context values", "context propagation". Not for: concurrency beyond context (go-concurrency-review), HTTP middleware (go-api-design), or error handling (go-error-handling).
Develop, debug, refactor, or design native HarmonyOS applications with ArkTS, ArkUI, Stage model, and HarmonyOS Kits. Use for HarmonyOS feature implementation, UI and state-management work, device adaptation, permissions, networking, persistence, API migration, build failures, and architecture decisions. Inspect an existing project before choosing APIs, derive its SDK and device constraints from repository configuration, and verify version-sensitive guidance against current official Huawei documentation. Use harmonyos-review instead when the primary request is a code audit.
Registers cron triggers with 7-field expressions to run functions on recurring schedules. Use when scheduling periodic jobs, timed automation, crontab replacements, cleanup routines, report generation, health checks, batch processing, or any task that should run every N seconds, minutes, hours, or on a weekly/monthly calendar.
Creates scoped key-value stores, reads and writes state entries, lists keys, and performs partial updates across functions. Use when persisting data between invocations, managing user sessions, caching computed values, storing feature flags, sharing state between workers, or building a KV data layer as an alternative to Redis or DynamoDB.
Query @lynx-js/css-defines compat_data to check Lynx CSS property and nested feature/value support by rendering backend and Lynx version, or check whether a newer dataset version exists. Use when asked whether CSS is supported in Lynx or ReactLynx, which backends support it, when support was added, whether a style change is compatible, whether the bundled data is current, or when inspecting the raw definition JSON.
mise — the tool-version manager, env-var loader, and task runner that replaces asdf, direnv, and make. Use for anything involving mise.toml or .tool-versions: installing or pinning tools, choosing a backend (core, packslip, aqua, github, cargo, npm, pypi/pipx), env vars, tasks, lockfiles, trust prompts, auto-updates, CI setup, migrating from asdf/direnv/make/npm scripts or off ubi, and install failures — including attestation/cosign/SLSA verification errors.
Parallel and concurrent processing patterns in bash, including GNU Parallel, xargs -P, job pools, and async patterns (2025). Proactively activate for: (1) running tasks in parallel from bash, (2) xargs -P for parallel command execution, (3) GNU parallel for complex distribution, (4) background jobs with & and wait, (5) implementing a concurrency cap (job pool of N workers), (6) collecting exit codes from parallel children, (7) preventing race conditions in shared output files, (8) parallel file processing across many cores. Provides: xargs -P recipes, GNU parallel quick reference, job-pool implementations in pure bash, exit-code aggregation patterns, and FIFO-based work queues.
When the user wants to create or update a README.md file for a project. Also use when the user says "write readme," "create readme," "document this project," "project documentation," or asks for help with README.md. This skill creates absurdly thorough documentation covering local setup, architecture, and deployment.
Use when building, redesigning, polishing, or refactoring SvelteKit pages and reusable components with shadcn-svelte, Bits UI, or the shadcn-svelte MCP. Trigger on landing pages, dashboards, marketing sites, app shells, forms, navbars, tables, dialogs, charts, sidebars, auth screens, blocks, responsive layouts, theming, icon selection, component or CLI installation questions, and requests to turn an idea or rough mockup into polished Svelte UI without inventing component APIs.
Provides comprehensive guidance for Spring AI including AI model integration, prompt templates, vector stores, and AI applications. Use when the user asks about Spring AI, needs to integrate AI models, implement RAG applications, or work with AI services in Spring.
Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
Full-stack guide to Telegram ecosystem development, covering Bot API, Mini Apps (Web Apps), and MTProto client development. Includes complete development resources for message handling, payments, inline mode, Webhook, authentication, storage, sensor APIs, and more.
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.