Skills
97,725 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Create, redesign, extend, debug, validate, package, test, and upgrade distinctive production Bagisto storefront themes. Use for self-contained Bagisto UI/UX direction, ultra-polished brand and commerce design systems, design tokens, responsive storefront UX, guided beginner implementation, Shop theme registration, resource overlays, distributable packages, Blade layouts/components, inline Vue, Vite/Tailwind assets, dynamic admin-controlled content, channel and theme-customization content, localization/RTL, accessibility, performance, complete Playwright commerce coverage, deployment, or resolving theme inheritance and asset-manifest failures. Derive every identity, path, version, component, locale, and command from the target checkout.
Builds, tests, and analyzes bounded process-based discrete-event simulations in Python with SimPy 4.1.2: Environment, Timeout, Process, AnyOf/AllOf conditions, interrupts, Resource, PriorityResource, PreemptiveResource, Container, Store, time-weighted monitoring, and replication-based output analysis, plus bundled safe CLIs. Use when modeling queues, production lines, logistics, or service operations with generator processes; when contending entities need shared resources or preemption; when instrumenting queue length or utilization correctly; when running independent replications with seeds and confidence intervals; when debugging event ordering or run(until=) boundaries. Not for continuous-time ODE or agent-based modeling frameworks.
Use when a public website needs an AI assistant with source-bounded answers, RAG/content scope, injection protection, escalation, logging, rate limits, refusals, and no hallucinated product/legal/price claims. Planning or implementation handoff only; do not expose secrets or give destructive tools.
Use when the user wants to build, migrate, or troubleshoot a Smart X routine -- TOTVS's metadata-driven UI framework that generates modern PO-UI screens from a data dictionary Object/Model/Interface/Launcher chain. Covers the model.tlpp/interface.tlpp/launcher artifacts, ADVPL function integration via pageActions/tableActions/onChange, converting a legacy MVC browse to Smart X, and common troubleshooting. Also triggers on Portuguese phrasing like "tela Smart X", "gerar tela por metadados", "migrar MVC para Smart X", "criar Modelo e Interface Smart X", "launcher Smart X", or names like FINA050SM/MATA110SX.
Software architecture engineering consultancy skill. Analyzes overall application structure, recommends sustainable approaches, enforces architectural consistency, and documents decisions for future sessions. Use this skill whenever the user asks about system design, architecture decisions, feature integration strategy, technology choices, data management consistency, codebase structure review, migration planning, technical debt assessment, or any question about "how should I build/structure/organize" their application. Also trigger when the user mentions architecture, ADR, bounded contexts, clean architecture, hexagonal architecture, microservices, modular monolith, dependency management, coupling/cohesion, fitness functions, or technical debt. This skill ensures the app does NOT develop mixed approaches for data management, core logic, or integration patterns — and that every architectural decision is documented so future sessions can build on prior decisions rather than contradict them.
Use when the user asks to confirm feature trade-offs in a PRD or development plan item by item; not for quality reviews, writing documents from scratch, or implementation. Briefly explain each feature, its value, and the planned approach; revise the document after confirmation, rejection, or changes
Optional skill. Reconstruct a human-review-preparation file from an existing pull request, merge request, branch diff, or commit range in a repository the user trusts. Use when the user wants retrospective understanding of already-implemented changes, AI-side assessment and recommendations, and an optional provider-specific sharing variant written to a local file when needed.
Declarative HTTP client for microservices communication with Spring Cloud OpenFeign. Covers @FeignClient, error handling, interceptors, and circuit breaker integration. USE WHEN: user mentions "feign", "openfeign", "@FeignClient", "declarative HTTP client", "service-to-service communication", "microservices client" DO NOT USE FOR: external APIs - consider WebClient or RestClient, simple HTTP calls - use RestClient
Uses an intake, research, and clarify loop—including bounded subagent research when available—to produce a phased implementation plan in `PLAN.md` or `plans/<task-name>.md`. Use for complex features, refactors, migrations, architectural work, and other multi-step changes.
Guide implementation of the Syncfusion WinUI AutoComplete control (SfAutoComplete) for creating searchable dropdowns with single or multiple selection, filtering suggestions, and customizable token display. Use this skill when implementing search-as-you-type functionality, autocomplete dropdowns with multi-select, tagging systems with token/chip display, or filtered suggestion boxes in WinUI applications.
Learn to implement Syncfusion WinUI NumberBox (SfNumberBox) control for numeric input with validation, custom formatting, and value restrictions. Use this skill when you need numeric input fields with currency, percentage, or decimal formatting in WinUI applications.
Implementation guide for Syncfusion WinUI Polar Chart (SfPolarChart) control. Use this when working with polar charts, radar charts, or spider charts for radial data visualization in WinUI applications. This skill covers line and area series for visualizing data in terms of values and angles, multi-dimensional data comparison, and directional data visualization with PolarLineSeries and PolarAreaSeries.
Guide for implementing Syncfusion WinUI TreeGrid (SfTreeGrid) components for displaying hierarchical or self-relational data. Use this skill when working with tree-structured grids, parent-child data relationships, or expandable grid rows. Covers TreeGrid features for organizational charts, file system displays, and multi-level data representation in WinUI applications.
Build, review, debug, configure, migrate, or plan TanStack Router React applications (v1, 1.170.x) with current docs. Use for @tanstack/react-router, file-based routes, code-based routes, route trees, generated routeTree.gen files, routeFileIgnorePrefix colocation (-components/-hooks/-lib), pathless layouts, typed navigation, Link/useNavigate/redirect, params, validateSearch, loaderDeps, loaders, beforeLoad, route context, auth guards, notFound, error boundaries, pending/deferred data, preloading, TanStack Query integration, SSR, testing, and production routing rewrites.
Build, review, debug, configure, migrate, or plan TanStack Start React applications (RC, 1.168.x) with current docs. Use for TanStack Start, @tanstack/react-start, file-based routing, route colocation (-components/-hooks/-lib beside routes), feature modules (src/modules reusable code), pathless layouts, TanStack Router integration, Vite/Rsbuild setup, SSR, streaming, server functions, server routes, middleware, loaders, TanStack Query integration (setupRouterSsrQueryIntegration, queryClient.query), environment variables, sessions/auth, deployment, hosting, production checklists, and Next.js migrations.
Build, review, debug, migrate, or plan TanStack Table v9 React tables with current docs. Use for @tanstack/react-table, @tanstack/table-core, useTable, tableFeatures, stockFeatures, createTableHook, createTableHookContexts, createColumnHelper, ColumnDef, table state, external atoms, Subscribe, React Compiler, sorting, filtering, faceting, grouping, aggregation, expanding, pagination (including cursor and Infinity page size), row selection, cell selection, cell spanning, row and column pinning, column visibility, column ordering, column sizing, column resizing, virtualization, devtools, worker row models, and v8-to-v9 migrations.
Use as the escalation strategy when local ADVPL/TLPP reference material lacks an answer -- a tiered approach (local cache first, then TDN Confluence REST API via WebFetch, then Playwright against the API, then WebSearch, then visual site search) for looking up native functions, entry points, unknown errors, or business processes on TDN (tdn.totvs.com). Also triggers on Portuguese phrasing like "buscar documentacao no TDN", "nao encontrei na referencia local", "pesquisar funcao no TDN", "documentacao oficial TOTVS", or "erro desconhecido nao listado".
Design deterministic technical SEO and schema.org guidance for crawlable public pages. Use this skill when the user asks for title and meta description rules, canonical and hreflang tags, JSON-LD schema, NewsArticle, Article, TechArticle, BreadcrumbList, WebSite, Organization, Person, OpenGraph, Twitter cards, sitemap, news-sitemap, RSS, robots.txt, llms.txt, publisher logo, ImageObject, or metadata templates that must match visible content.
Expert in building Telegram bots that solve real problems - from simple automation to complex AI-powered bots. Covers bot architecture, the Telegram Bot API, user experience, monetization strategies, and scaling bots to thousands of users. Use when "telegram bot, bot api, telegram automation, chat bot telegram, tg bot, " mentioned.
End-to-end setup for making a Telnyx AI assistant call a phone number. Covers provisioning a phone number, creating a TeXML application, assigning the number, configuring telephony settings, whitelisting destination countries, and triggering outbound calls via scheduled events. Use this skill (not telnyx-ai-assistants-python) when the task involves an AI assistant placing, making, or triggering an outbound phone call to a user.
Version-aware templUI v1 and shadcn-templ v2 component guidance for Go/templ apps. Use for component installation, UI blocks, Script() setup, HTML-to-templ conversion, or Go-to-JavaScript interpolation. Offers an upgrade when legacy templUI is encountered. Skips generic HTMX issues and full goilerplate application generation.
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review. User-invoked only.
Break a plan, spec, or conversation into tracer-bullet tickets assigned to autonomous or attended lanes, with pre-agreed test seams, blocking edges, and overlap-safe execution frontiers. Use when preparing work for unattended coding agents as well as human-guided implementation.
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).
PyTorch Geometric (PyG) for graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when working with torch_geometric, not for general NetworkX analytics or non-graph PyTorch models.
Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal tasks. Use when working with AutoModel, pipelines, tokenizers, or TrainingArguments—not for general ML outside the Transformers library.
TypeScript language. Covers types, generics, and advanced patterns. Use when writing type-safe JavaScript code. USE WHEN: user mentions "typescript", "types", "generics", asks about "type safety", "type errors", "tsconfig", "utility types", "type guards", "branded types" DO NOT USE FOR: reviewing existing TypeScript code - use `review/typescript`, which covers the defects `tsc` and typescript-eslint do not report DO NOT USE FOR: Plain JavaScript without types - use `javascript` skill instead DO NOT USE FOR: Node.js runtime - use `nodejs` skill instead DO NOT USE FOR: Framework-specific typing - use framework skills (React, Vue, etc.)
Data-Oriented Technology Stack (ECS, Job System, Burst). Authoring, baking, systems, queries, jobs paralleles. Triggers: /dots, /ecs, 'DOTS', 'ECS', 'ISystem', 'SystemAPI', 'IJobEntity', 'Burst', 'NativeArray', 'Entity', 'IComponentData', 'data oriented'.
Instant Unity gameplay prototyping. Triggers: /proto, /prototype, 'prototyper', 'idee de jeu', 'tester une mechanique', 'rapid proto'. Turns a gameplay idea into a playable scene with minimal code. Produces 1-3 MonoBehaviour scripts, scene setup instructions, and a test checklist. No architecture, no planning — just playable code.
Generate Unity shaders (HLSL/ShaderLab) for visual effects. Triggers: /shader, /shader-gen, 'creer un shader', 'effet visuel shader', 'dissolve', 'outline', 'toon shading', 'hologram', 'water shader'. Automatically detects the render pipeline (URP/HDRP/Built-in) and produces a ready-to-use .shader file with Material instructions.
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.