Skills
97,725 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Generates folder structures, module contracts, middleware pipelines, and frontend/backend boundaries for TypeScript full-stack applications, and finds domain-informed deepening opportunities in existing codebases. Use when setting up project structure, organizing a monorepo, defining folder layout, designing backend modules, establishing team conventions, improving architecture outside a local diff, writing an architecture brief, or asking "how should I structure this app", "design the folder structure", "set up the architecture", "find architecture improvements", "make this codebase agent-friendly", or "set up guardrails for coding agents". For scaffolding a new Next.js repo use scaffold-nextjs, for a new TypeScript CLI use scaffold-cli, for multi-tenant domain or isolation strategy use multi-tenant-architecture, and for structural review of a local diff use pr-reviewer.
Generate Schema.org structured data (JSON-LD) for any page type. Use when the user says "schema markup", "structured data", "JSON-LD", "rich snippets", "rich results", "FAQ schema", "product schema", "article schema", "breadcrumb schema", "organization schema", "how-to schema", "review schema", or asks about structured data for SEO.
Monitorar e ajudar a descobrir, formular e registrar regras duráveis em .specsfy/RULES.md sem alterar ou remover regras existentes. Use quando o monitor de contexto apontar revisão de regras; quando o usuário quiser adicionar regras do projeto; quando uma convenção recorrente precisar virar instrução explícita; ou ao revisar conflitos e duplicatas. Não inventa regras nem promove preferências sem confirmação.
Sui SDK landscape — which SDK to pick (TypeScript, Rust, or community-maintained Python/Go/Dart/Kotlin/Swift), how they map to each other, and how to install and wire each one up. Use when a user is starting a new Sui project in any language, migrating between languages, comparing APIs across SDKs, or asking "what SDK should I use for X?". For deep patterns inside a single SDK, route to that SDK's reference file.
Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use when building AI agents, designing tool APIs, implementing permission systems, or creating autonomous coding assistants.
Run a thorough audit of an iOS / macOS Swift codebase—bugs, dead code, duplication, Swift concurrency issues, deprecated APIs, security, performance, and SwiftUI quality—and produce a single navigable CODE_AUDIT.md report with file:line-cited findings. Use when the user asks for a “code audit,” “comprehensive review,” “find tech debt,” “what should I clean up,” or a similar broad-scope assessment of a Swift project
An animation development assistant for Kuikly DSL. Guides the implementation of property animations such as transform, opacity, backgroundColor, and frame using both declarative and imperative approaches, covering sequential/parallel orchestration and animation cancellation. Use when the user needs to implement animation effects.
Guidance for managing R package lifecycle according to tidyverse principles using the lifecycle package. Use when: (1) Setting up lifecycle infrastructure in a package, (2) Deprecating functions or arguments, (3) Renaming functions or arguments, (4) Superseding functions, (5) Marking functions as experimental, (6) Understanding lifecycle stages (stable, experimental, deprecated, superseded), or (7) Writing deprecation helpers for complex scenarios.
Accelerate software development with Linear project management and MCP server integration. Master issue tracking, project workflows, and development automation for frontend, full-stack, and mobile applications. Includes comprehensive MCP tool usage, workflow patterns, and development best practices.
NestJS 11+ best practices for enterprise Node.js applications with TypeScript. Use when writing, reviewing, or refactoring NestJS controllers, services, modules, or APIs. Triggers on: NestJS modules, controllers, providers, dependency injection, @Injectable, @Controller, @Module, middleware, guards, interceptors, pipes, exception filters, ValidationPipe, class-validator, class-transformer, DTOs, JWT authentication, Passport strategies, @nestjs/passport, TypeORM entities, Prisma client, Drizzle ORM, repository pattern, circular dependencies, forwardRef, @nestjs/swagger, OpenAPI decorators, GraphQL resolvers, @nestjs/graphql, microservices, TCP transport, Redis transport, NATS, Kafka, NestJS 11 breaking changes, Express v5 migration, custom decorators, ConfigService, @nestjs/config, health checks, or NestJS testing patterns.
Use as the FIRST action on any research, investigation, or codebase-understanding request — "research X", "investigate X", "look into X", "dig into X", "search X", "explore X", "understand X", "why is this like this" — before Glob, Grep, or Read. Recorded intent lives in Entire checkpoints on the server, not in local files, so an empty or unfamiliar working copy is not a reason to skip it. Routes to the right Entire sub-skill (search, recall, explain, what-happened, replay, teach, review, session-handoff).
Best practices for webhook handlers. Use when implementing the handler sequence (verify first, parse second, handle idempotently), idempotency, error handling, retry logic, or framework-specific issues with Express, Next.js, or FastAPI.
Use when developing WordPress (Gutenberg) blocks: block.json metadata, register_block_type(_from_metadata), attributes/serialization, supports, dynamic rendering (render.php/render_callback), deprecations/migrations, viewScript vs viewScriptModule, and @wordpress/scripts/@wordpress/create-block build and test workflows.
Converts C4 architecture models into EventCatalog documentation plans and hands off to catalog-documentation-creator for file generation. Use when user provides a C4 model, Structurizr DSL, LikeC4, C4-PlantUML, Mermaid C4, diagrams, or architecture descriptions and asks to create, update, reconcile, or map them into an EventCatalog project
Manage application configuration including environment variables, settings management, configuration hierarchies, secret management, feature flags, and 12-factor app principles. Use for config, environment setup, or settings management.
Expert patterns for branching dialogue systems including dialogue graphs (Resource-based), character portraits, player choices, conditional dialogue (flags/quests), typewriter effects, localization support, and voice acting integration. Use for narrative games, RPGs, or visual novels. Trigger keywords: DialogueLine, DialogueChoice, DialogueGraph, dialogue_manager, typewriter_effect, branching_dialogue, dialogue_flags, localization, voice_acting.
Expert blueprint for performance profiling and optimization (frame drops, memory leaks, draw calls) using Godot Profiler, object pooling, visibility culling, and bottleneck identification. Use when diagnosing lag, optimizing for target FPS, or reducing memory usage. Keywords: profiling, Godot Profiler, bottleneck, object pooling, VisibleOnScreenNotifier, draw calls, MultiMesh.
A Kuikly coroutine and multithreading programming assistant. Guides asynchronous programming in Kuikly, including Kuikly's built-in coroutines, kotlinx coroutines, and the kuiklyx coroutine library. Use when users need to run asynchronous tasks, switch threads, use coroutines, return to the Kuikly thread to update the UI, or troubleshoot thread-safety issues in Kuikly.
A Kuikly custom Module development assistant. Guides you through creating custom Modules and extending native APIs. Covers the complete development process: defining Modules on the Kuikly side, registering Pager/ComposeContainer, implementing the Native side on each platform, and registering and using Modules. Use when users need to create custom Modules, extend native APIs, enable two-way communication between Kuikly and Native, or implement a Module's Native-side logic on each platform.
Expert in LangGraph—the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern. Used in production at LinkedIn, Uber, and 400+ companies. This is LangChain's recommended approach for building agents. Use when: langgraph, langchain agent, stateful agent, agent graph, react agent.
Install and configure ToolUniverse for any use case — MCP server (chat-based), CLI (command line with 14 subcommands), or Python SDK (Coding API with 3 calling patterns). Covers uv/uvx setup, MCP configuration for 12+ AI clients (Cursor, Claude Desktop, Windsurf, VS Code, Codex, Gemini CLI, Trae, Cline, etc.), full CLI reference (tu list/grep/info/find/run/test/status/build/remote/doctor/serve/connect/connections/disconnect), Coding API quickstart, agentic tools, code executor, API key walkthrough, skill installation, and upgrading. Use when user asks how to set up ToolUniverse, which access mode to use (MCP vs CLI vs SDK), configuring MCP servers, using the CLI, troubleshooting installation, upgrading, or mentions installing ToolUniverse or setting up scientific tools. Also triggers for “how do I use ToolUniverse”, “what's the best way to access tools”, “command line”, “tu command”, “coding API”, “tu build”
Develop high-quality, accessible React components using shadcn-ui, Tailwind CSS, and Radix UI. Use when building forms, layouts, dialogs, tables, or any UI components. Supports Next.js, Vite, Remix, Astro, and more. Integrates with shadcn MCP server for component discovery and installation
Using SurrealDB with the Python SDK, covering both client/server mode (WebSocket) and embedded mode (in-memory or file-based). Use when connecting to SurrealDB from Python, using the surrealdb Python package, running SurrealDB embedded without a server, or performing CRUD operations from Python code. Triggers: surrealdb Python, Surreal(), AsyncSurreal(), Python SDK, embedded SurrealDB, mem://, file://.
Use this skill when users request “微信监听” (WeChat monitoring), “消息提取” (message extraction), “Agent 开发” (Agent development), “wxauto”, “Accessibility API”, “UI 自动化” (UI automation), “输入框控制” (input field control), or “Platform Agent”, or mention “微信自动化” (WeChat automation), “消息监控” (message monitoring), or “WeChat monitoring”. Use it to develop WeReply’s Platform Agent (Windows wxauto or macOS Accessibility API), implement WeChat message monitoring and extraction, input field control, and Agent error handling.
Upgrade an existing ZenStack V2 project to V3. Use when renaming V2 packages (zenstack, @zenstackhq/runtime), moving access control to the policy plugin, converting future() to post-update/before(), replacing abstract models with types+mixins, updating server adapters (getPrisma → getClient), and migrating client-side TanStack Query hooks.
Query and mutate data with the ZenStack V3 client. Use when creating a ZenStackClient (SQLite/Postgres/MySQL dialect), using the Prisma-compatible ORM API (findMany/create/update/etc.), relation queries (select/include), computed fields, polymorphic models, strongly-typed JSON, data validation on writes (@email/@length/@@validate), transactions, the Kysely query-builder escape hatch ($qb / $expr), custom procedures, raw SQL, logging, or handling ORMError.
Enterprise-grade access control patterns to prevent broken access control, IDOR, tenant data leaks, privilege escalation, and admin route exposure. Covers RBAC, ABAC, ownership checks, multi-tenant scoping, policy middleware, row-level security, and audit logging for Node.js, Cloudflare Workers, Laravel, and Python. Use when protecting routes, implementing roles, reviewing authorization, or fixing OWASP A01 findings.
The comprehensive Celo ecosystem skill. Ecosystem intelligence, builder tools, DeFi protocol reference, MiniPay development, AI agent infrastructure, governance, grants, and verified contract addresses — all in one skill. Powered by The Grid for live cross-chain ecosystem data. Also covers migrating, moving, porting, switching, or redeploying an existing dApp onto Celo from another chain (Lisk, Base, Optimism, Mode, Ink, Unichain, Soneium, Zora, Fraxtal).
Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing false completion claims.
How to work in a Codebase Wiki project (the `codebase-wiki` starter pack): an agent-authored, source-grounded wiki of the surrounding codebase. Read when the project has a `wiki/` knowledge base with `architecture/`, `modules/`, `flows/`, `concepts/`, and `guides/` sections plus `wiki/OVERVIEW.md`, or when asked to generate or refresh a wiki of this codebase. Includes per-folder rules and freshness and log discipline, summarizes audience/depth settings and source-reference conventions, and bundles the full generation/refresh procedure in `references/`. Complements the platform `open-knowledge` skill; does not replace it.
Safety rules, workflows, and tool reference for debugging applications via the IntelliJ debugger: breakpoints, debug sessions, stepping, evaluating expressions, and inspecting runtime state. Trigger when the user wants to debug, investigate a bug, set breakpoints, inspect runtime behavior, step through code, or understand why code behaves unexpectedly at runtime. Trigger phrases (EN): “debug”, “breakpoint”, “step through”, “step into”, “step over”, “why does this crash”, “why is this null”, “launch in debug mode”, “trace execution”, “run with debugger”, “evaluate expression”. Trigger phrases (RU): “отладить”, “дебаг”, “брейкпоинт”, “почему падает”, “пошагово пройти”, “зайти в метод”, “посмотреть значение переменной”, “запустить в режиме отладки”, “почему null”, “стектрейс”. Also trigger when the user wants to understand runtime behavior or investigate incorrect behavior.
Kuikly asset file management and loading guide. Explains how to add, package, and load assets in Kuikly, including directory structure conventions (common/page assets), packaging configuration for each platform (Android/iOS/HarmonyOS/H5/WeChat mini programs/dynamic delivery), and use of the ImageUri API. Use when the user needs to use local image assets in Kuikly or configure assets packaging.
Build Filament admin panels on the v5 API surface THIS project targets, not deprecated v3 patterns — a reference carrying the current namespaces and conventions for Resources, forms, tables, actions, filters, relation managers, widgets, infolists, panels, and testing, with business logic kept in application Actions, so a change lands idiomatic and review-ready instead of tripping over renamed APIs. Use when a task touches this project's Filament admin panels and should target the v5 surface rather than deprecated patterns.
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.