Skills
98,639 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Build modern, interactive terminal user interfaces with Textual. Use when creating command-line applications, dashboard tools, monitoring interfaces, data viewers, or any terminal-based UI. Covers architecture, widgets, layouts, styling, event handling, reactive programming, workers for background tasks, and testing patterns.
Tool lifecycle UI components for React/Next.js from ui.inference.sh. Display tool calls: pending, progress, approval required, results. Capabilities: tool status, progress indicators, approval flows, results display. Use for: showing agent tool calls, human-in-the-loop approvals, tool output. Triggers: tool ui, tool calls, tool status, tool approval, tool results, agent tools, mcp tools ui, function calling ui, tool lifecycle, tool pending
Plan and build agents, apps, or harnesses with You.com Search, Contents, Research, Finance, and other agentic resources found through the `you-discover` tool. Use when designing an integration — inference provider, BYOK local harness, agent behind MCP, SDK or direct-API app, or plugin for an existing agent — not when answering a question with web search.
The language-neutral foundation for Airflow language SDKs — implement task logic in a non-Python language while the DAG stays in Python. Use when the user wants to run an Airflow task in another language (Java, Kotlin, Go, or other JVM/native languages), asks how the Python `@task.stub` pairs with native task code, how task/DAG IDs must match across the two sides, how data passes via XCom as JSON, or which language SDKs exist. This skill owns the shared Python-stub pattern and conceptual model; for a specific language's native API, build, and runtime, use that language's skill (e.g. authoring-java-sdk-tasks, authoring-go-sdk-tasks)
Use when planning comprehensive Liquid Glass adoption across an app, auditing existing interfaces for Liquid Glass compatibility, implementing app icon updates, or understanding platform-specific Liquid Glass behavior — a comprehensive reference guide covering all aspects of Liquid Glass adoption from WWDC 2025
Use for Bitrix SQL and ORM patterns: raw SQL or Connection queries, DataManager maps or field definitions, Objectify objects or collections, ORM queries or filters, and ORM writes or batch persistence. Use when designing, reviewing, or implementing database reads, writes, schemas, or data access code.
Write and maintain a CHANGELOG that records every completed code change without becoming a commit dump. Use after any code change in a project that has a changelog, when setting one up, when preparing a release, or when the user asks why something was built this way. Keep mechanical entries brief; preserve reasons and rejected alternatives for non-obvious decisions. Do not use for commit messages, PR descriptions, or user-facing release notes.
Chat UI building blocks for React/Next.js from ui.inference.sh. Components: container, messages, input, typing indicators, avatars. Capabilities: chat interfaces, message lists, input handling, streaming. Use for: building custom chat UIs, messaging interfaces, AI assistants. Triggers: chat ui, chat component, message list, chat input, shadcn chat, react chat, chat interface, messaging ui, conversation ui, chat building blocks
Choosing or implementing an algorithm or data structure — asymptotic complexity, data-structure selection, sorting & searching, dynamic programming, graph algorithms, divide & conquer, greedy algorithms, string/sequence algorithms, and the at-scale toolbox (Bloom filters, HyperLogLog, Count-Min Sketch, reservoir sampling, consistent hashing, external merge sort, Aho-Corasick, MinHash/LSH). Trigger on tasks involving "what's the right algorithm for…", performance-critical code, code with nested loops over the same input, recursive solutions, shortest-path / scheduling / matching / DP problems, code review for accidental O(n²) blowup, and any "how do I do X at scale / on a stream / without enough RAM" question — even if the user doesn't explicitly mention "algorithm" or "complexity."
Configure Airflow to run language SDK tasks (Java, Go, and future native SDKs): register a coordinator, map a queue to it, ensure the runtime/artifact is available on workers, and tune coordinator options. Use when the user wants Airflow to route a queue to a native-language coordinator; asks about `[sdk]` `coordinators`/`queue_to_coordinator` settings, `AIRFLOW__SDK__COORDINATORS`, `jars_root`, `executables_root` or other coordinator `kwargs`, `task_startup_timeout`; or asks why native tasks aren't being picked up. Covers the shared routing mechanism and per-coordinator options (e.g. JavaCoordinator, ExecutableCoordinator).
Fixes content and semantic HTML issues. Adds server-side rendering, a correct heading hierarchy, semantic landmark elements, ARIA labels, image alt text, the lang attribute, descriptive link texts, form labels, autocomplete tokens, keyboard access, document titles, button names, correct aria-hidden use and widget state so AI agents can read and operate a page through the HTML and the accessibility tree. Use when asked to "fix semantic HTML", "add SSR", "fix heading hierarchy", "add alt text", "improve semantics score", "fix accessibility for AI", "fix form labels", "add autocomplete", "fix keyboard navigation", "fix button names", "fix aria-hidden", "add aria-expanded", or any semantic HTML task.
Explore and diagnose a PostHog endpoint's execution logs — error messages, failed runs, cache misses, slow runs, or unexpected row counts during endpoint invocations. Use when the user says "my endpoint is failing", "show me the logs for endpoint X", "what error did endpoint Y produce", "why did endpoint Z return no rows", "is this endpoint hitting cache", or "check the last N runs". Focused on a single named endpoint's runtime log entries, not project-wide auditing or query performance profiling.
This skill should be used when a task requires designing or implementing frontend UI (components, pages, layouts, styling) and no more specialized frontend skill is a better fit. It guides production-grade, brand-consistent visual implementation with distinctive but controlled aesthetics.
Refactors and reviews SwiftUI view files with strong defaults for small dedicated subviews, MV-over-MVVM data flow, stable view trees, explicit dependency injection, and correct Observation usage. Use when cleaning up a SwiftUI view, splitting long bodies, removing inline actions or side effects, reducing computed `some View` helpers, or standardizing `@Observable` and view model initialization patterns.
Registers external HTTP endpoints as iii functions using registerFunction(id, HttpInvocationConfig). Use when adapting legacy APIs, third-party webhooks, or immutable services into triggerable iii functions, especially when prompts ask for endpoint maps like { path, id } iterated into registerFunction calls.
Registers a boolean condition function and attaches it to triggers via condition_function_id so handlers only fire when the condition passes. Use when gating triggers on business rules, checking user permissions, validating data before processing, filtering high-value orders, rate-limiting events, or conditionally skipping handlers based on payload content.
Keep a written evidence ledger and delegate whole-repository searches during investigations spanning many files. Use for debugging, audits, and archaeology when the relevant code location is unknown. Do not use when the relevant files are already identified or for ordinary edits to known code.
Implements business requirements as scalable, maintainable Magento 2 features. Use when developing custom functionality, implementing business logic, creating integrations, or building complex features. Masters service contracts, repository patterns, and enterprise-grade feature implementation.
Write a complete requirements specification from UI and functional specs (a specs-ui skill project), publish it as a readable HTML artifact (table of contents, identifier search, diagrams, copying the full Markdown or sections), and also deliver it in Markdown. Include an overview and scope; users and roles; functional and UI specifications by batch with acceptance criteria; visual identity; non-functional requirements; architecture; detailed tech stack; infrastructure and operations; batch breakdowns with estimate ranges; schedule; risks; and open questions. Derive the architecture from the specs, present options, then validate it. Use whenever someone mentions requirements, a CDC, technical specifications, a design document, a document for the dev team, architecture or stack based on specs, estimation, or batch breakdowns—even without saying “requirements specification.”
Foundational software design principles applied specifically to robotics module development. Use this skill when designing robot software modules, structuring codebases, making architecture decisions, reviewing robotics code, or building reusable robotics libraries. Trigger whenever the user mentions SOLID principles for robots, modular robotics software, clean architecture for robots, dependency injection in robotics, interface design for hardware, real-time design constraints, error handling strategies for robots, configuration management, separation of concerns in perception-planning-control, composability of robot behaviors, or any discussion of software craftsmanship in a robotics context. Also trigger for code reviews of robotics code, refactoring robot software, or designing APIs for robotics libraries.
Provides comprehensive guidance for Spring Cloud Alibaba including Nacos, Sentinel, RocketMQ, and Alibaba Cloud integration. Use when the user asks about Spring Cloud Alibaba, needs to use Alibaba Cloud services, implement service discovery with Nacos, or work with Spring Cloud Alibaba components.
Upgrade a Strapi application to a new version. Always review the relevant breaking changes first (via the strapi-docs MCP server, or by fetching the docs directly if MCP is unavailable), then perform the upgrade using the official @strapi/upgrade tool. Use whenever the user wants to upgrade, update, or bump their Strapi version.
Implement and customize themes for Syncfusion WPF controls using SfSkinManager. Apply built-in themes (Windows 11, Fluent, Material, Office 2019), create custom themes with Theme Studio, and control visual effects like reveal animations and acrylic backgrounds. Use this skill whenever user needs to theme WPF applications, apply Syncfusion themes, customize colors/fonts, or configure theme-based visual effects and accessibility features.
Advanced TypeScript patterns for strict mode development. Covers type utilities (Pick, Omit, Partial, Record, Awaited), generics with constraints and inference, type guards and narrowing, discriminated unions, conditional and mapped types, template literal types, const assertions, the satisfies operator, module patterns, and modern JavaScript idioms (eslint-plugin-unicorn). Use when building type-safe APIs, preventing runtime errors through types, working with strict TypeScript configuration, debugging complex type errors, or enforcing modern JS idioms. Use for generics, type guards, utility types, strict mode, type inference, narrowing, type safety, const assertions, satisfies, module augmentation, unicorn, for-of, modern-js
Build real-time Indic voice agents with Sarvam STT/TTS/LLM on LiveKit or Pipecat (Python), plus JS/TS custom-pipeline notes. Use this skill when creating phone bots, IVR, or always-on conversational voice apps. For one-shot in-chat voice reply or dubbing via MCP, use sarvam-mcp instead.
Export, list, dump, and locate Wuji device logs using `wuji logs`. Use when you need to collect support bundles including hand model calibration recordings, collect a device-side diagnostic snapshot and flash history, inspect log files, or locate the log directory. Supports date/source filtering, device dumps, private-data redaction, and JSON output.
Interactively onboard a project to OpenSpec by running a structured interview and generating a complete QRSPI-configured openspec/config.yaml. Use this skill whenever a user mentions "openspec config", "config.yaml for openspec", "set up openspec", "onboard to openspec", "generate openspec config", "QRSPI config", or asks how to configure OpenSpec for their project — even if they just say "help me set up openspec" or "I want to use openspec". Always prefer this skill over ad-hoc config generation.
Onboard an AI coding agent to a Syncfusion project. Identifies the framework and product family, installs or selects the official component skills, finds current documentation, handles licensing safely, and verifies a working implementation. Use when starting, integrating, upgrading, migrating, evaluating, or troubleshooting Syncfusion UI components, document SDKs, viewers, or editors on any platform.
Use when designing, scaffolding, extending, or auditing a component library primarily consumed by an AI agent—that is, a design system requiring machine-readable metadata (props, variants, relationships, tokens, anti-patterns), not just prose documentation. Triggers include “agentic design system”, “design system for AI/Claude”, “make my design system AI-readable”, “component metadata schema”, “scaffold a UI library for an agent”, or planning a new component library primarily for an LLM. Don’t use for purely human-facing design system work; use figma:figma-generate-library instead
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.