Skills
98,639 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Write correct Sarvam AI chat-completion code (Sarvam-105B, Sarvam-30B) — OpenAI-compatible API, streaming, reasoning mode, and the content=None gotcha. Use this skill when building chatbots, Q&A, agents, or Indic LLM features in Python or JS/TS. For a live completion in chat via MCP, use sarvam-mcp instead.
Registers and manages custom format validators in z-schema. Use when the user needs to add custom format validation, create sync or async format validators, register formats globally or per instance, validate emails or dates or phone numbers or custom business rules with format, configure formatAssertions for vocabulary-aware behavior, use customFormats option, list registered formats, handle async format timeouts, or understand how format validation differs across JSON Schema drafts.
Create custom data visualizations with D3.js: bar, line and scatter charts, chord diagrams, heatmaps, force-directed networks and geographic maps, with proper data binding, scales, axes, transitions and interactivity. Works in React, Vue, Svelte or vanilla JavaScript.
Deeply researches a codebase, designs a feature through an annotated plan file, then decomposes it into an implementable issue hierarchy (parent + sub-issues with dependencies) on GitHub or Backlog. Nothing is published until you approve the exact content. Installs upstream's create-issue skill, which absorbed the earlier design-sprint skill.
Manages project directory setup and artifact organization. Use when starting a new project, resuming an existing one, or when a PLAN.md needs to be associated with a project directory. Creates the project folder structure (specs/, scripts/, notebooks/, manifests/, agent_memory/) and resolves project naming.
Create a Product Requirements Document (PRD) - Layer 2 of the SDD flow, defining product features, personas, success metrics, and acceptance criteria from an upstream BRD. Use after a BRD exists and before EARS. Single-document authoring primitive; for end-to-end or batch generation the autopilot (`doc-prd-autopilot`) drives this skill.
Explain Arduino and embedded compiler, upload, boot, power, and runtime errors in plain English. Use when a user shares an error or failure from Arduino IDE, Arduino CLI, PlatformIO, or a vendor-specific tool. Separate build, upload, hardware, and system evidence and give a board-specific recovery path without assuming UNO, ESP32, or RP2040 behavior.
Install and wire registry blocks and components into FrameVideo compositions. Use when running framevideo add, installing a block or component, wiring an installed item into index.html, or working with framevideo.json. Covers the add command, install locations, block sub-composition wiring, component snippet merging, and registry discovery.
Create, view, manage, approve, and merge GitLab merge requests. Use when working with MRs: creating from branches/issues, reviewing, approving, adding comments, resolving discussion threads, checking out locally, viewing diffs, rebasing, merging, or managing state. Triggers on merge request, MR, pull request, PR, review, approve, merge, resolve thread.
GSAP animation reference for FrameVideo. Covers gsap.to(), from(), fromTo(), easing, stagger, defaults, timelines (gsap.timeline(), position parameter, labels, nesting, playback), and performance (transforms, will-change, quickTo). Use when writing GSAP animations in FrameVideo compositions.
Uses @heybox/hb-sdk and its hb-sdk CLI to build, debug, review, and publish workshop mini-programs for the Heybox App. Use for public SDK APIs, persistent handshake state, lifecycle events, hb-sdk create/dev/login/doctor, browser Mock and device debugging, or publishing checks. Don't use for private credentials, internal Heybox client protocols, private package paths, or non-Heybox SDKs.
Guide to building static websites with the Hugo static site generator: blogs, documentation sites, landing pages and portfolios. Covers scaffolding new sites, choosing Hugo Extended over Standard, hugo.yaml and hugo.toml configuration, themes such as PaperMod via Git submodules or Hugo Modules, Go templates and Goldmark, Tailwind CSS v4 through Hugo Pipes and PostCSS, headless CMS integration with Sveltia CMS or TinaCMS, multilingual sites, GitHub Actions CI/CD, and deployment to Cloudflare Workers Static Assets or Pages with wrangler. Documents 15 pitfalls: Hugo version mismatch, baseURL errors, theme not found, YAML versus TOML frontmatter, and date-related build failures. Use when creating, styling, adding a CMS to, deploying or troubleshooting a Hugo site.
Guides interactive Horizon Platform SDK (PSDK) integration for Meta VR and Horizon OS Android/Kotlin apps—analyzes the codebase, recommends public platform features, plans the integration, and validates on device. Use for workflow guidance; use hz-platform-sdk for the detailed API reference. Build paths: Standard Android and Meta Spatial SDK; use hz-quest-verify-first if the path is unclear
Enqueues jobs, configures retry policies, sets concurrency limits, and orders messages via named standard or FIFO queues. Use when building background job workers, task queues, message queues, async pipelines, or any pattern needing guaranteed delivery with exponential backoff and dead-letter handling.
Patterns for building applications that integrate the Krea API. Before acting, ensure you have read krea-core/SKILL.md. Auth, polling discipline, error handling, validation, frontend integration (SvelteKit/React/Vue), and the 'prototype in chat, productize in app' workflow. Use when the user is writing code that calls the Krea API directly — building a generator UI, a content pipeline, a creative tool — not when they just want to generate one image. For interactive generation use krea-generate; for marketing workflow contracts use krea-marketing.
Emulated Microsoft Entra ID (Azure AD) OAuth 2.0 / OpenID Connect for local development and testing. Use to test Microsoft sign-in locally, emulate Entra ID OIDC discovery, handle Microsoft token exchange, configure Azure AD OAuth clients, work with Microsoft Graph /me, or test PKCE/client credentials flows without calling real Microsoft APIs. Triggers include “Microsoft OAuth”, “Entra ID”, “Azure AD”, “emulate Microsoft”, “mock Microsoft login”, “test Microsoft sign-in”, “Microsoft OIDC”, “local Microsoft auth”, or any task requiring a local Microsoft OAuth/OIDC provider
Implement secure payments using Clerk Billing and Stripe without ever touching card data. Use this skill when you need to set up subscription payments, handle webhooks, implement payment gating, understand PCI-DSS compliance, or integrate Stripe Checkout. Triggers include "payment", "Stripe", "Clerk Billing", "subscription", "PCI-DSS", "credit card", "payment security", "checkout", "webhook", "billing".
Conduz o brainstorm da Fase 0 de um fluxo SDD/AgentSpec por interação com o usuário: explora contexto, faz perguntas de descoberta uma por vez, coleta amostras, compara 2–3 abordagens, aplica YAGNI, valida incrementalmente e gera um BRAINSTORM pronto para a fase /define. Use para ideias vagas de software, automações, agentes, produtos ou features que ainda precisam de exploração antes de formalizar requisitos; também quando o usuário pedir para transformar uma conversa, problema ou notas iniciais em um brainstorm estruturado.
Fecha um ciclo de trabalho e passa o bastão para a próxima sessão: registra o que foi feito, o que ficou pendente (separando o que está quebrado do que é melhoria), quais são os próximos passos e o que não pode quebrar — e gera um prompt de retomada que funciona sozinho, sem depender da conversa anterior. Mantém um único arquivo de handoff por feature, com cada etapa nova no topo. Use quando o usuário disser que vai parar, que o contexto está acabando, que terminou uma etapa, que quer documentar para continuar depois, ou ao final da fase de Build de um fluxo SDD.
Comprehensive guide for implementing Syncfusion Angular Calendar components including Calendar, DatePicker, DateRangePicker, DateTimePicker, and TimePicker. Covers installation, data binding, date/time selection, range selection, formatting, localization, masking, validation, customization, templates, accessibility, and controlled component patterns in Angular applications.
Validate Tailwind CSS v4 configuration and detect/prevent Tailwind v3 patterns. Use this skill when setting up Tailwind, auditing CSS configuration, or when you suspect outdated Tailwind patterns are being used. Ensures CSS-first configuration with @theme blocks.
Debug Twilio integrations and set up production observability. Covers the Console Debugger, Monitor Alerts API, Event Streams for error log streaming, status callback tracking, common error codes, and a systematic debugging workflow. Use this skill whenever a Twilio integration produces errors, messages fail to deliver, calls drop unexpectedly, or you need to set up monitoring for a production deployment.
Look up phone number intelligence via Twilio Lookup v2 API. Covers number validation, line type detection (mobile/landline/VoIP), SIM swap detection, caller name, identity match, and SMS pumping risk scoring. Use this skill to validate numbers or assess fraud risk before sending messages or calls.
Build voice call logic with TwiML (Twilio Markup Language). Covers core verbs (Say, Play, Gather, Dial, Record, Conference), generating TwiML with Python and Node.js SDKs, and a complete inbound-call IVR example. Use this skill to define inbound or outbound call behavior
Creates a reusable use case specification file that defines the business problem, stakeholders, and measurable success criteria for model customization, as recommended by the AWS Responsible AI Lens. Use as the default first step in any model customization plan. Skip only if the user explicitly declines or already has a use case specification to reuse. Captures problem statement, primary users, and LLM-as-a-Judge success tenets.
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.
Clone a website — two modes. SNAPSHOT = a faithful, self-contained offline copy of a page (HTML+CSS+JS+images in one file, exact bytes, SingleFile-style). RECONSTRUCT = AI reverse-engineer the page into a clean editable Next.js/Tailwind codebase (design tokens → component specs → parallel builders → visual-diff QA, the ai-website-cloner-template method). Use when the user wants to "clone this site", copy a page's design/UI + interactions, mirror a layout, save offline, or rebuild a site as editable code. Built-now-adapt-later: snapshot builtin works now; faithful live capture + the reconstruct pipeline are one-config engine adapters.
Expert guide for WebGL API development including 3D graphics, shaders (GLSL), rendering pipeline, textures, buffers, performance optimization, and canvas rendering. Use when working with WebGL, 3D graphics, canvas rendering, shaders, GPU programming, or when user mentions WebGL, OpenGL ES, GLSL, vertex shaders, fragment shaders, texture mapping, or 3D web graphics.
Expert-level AI system design, MLOps, architecture patterns, and AI infrastructure. Use when the user mentions AI architecture, MLOps, system design, AI infrastructure, or scalability, or when the task involves AI System Architecture, MLOps Infrastructure, Scalability Patterns, or Architecture Design.
Maintains AI chat UIs built from elements.ai-sdk.dev AI Elements components already copied into the project. Use when changing or debugging those components (conversations, messages, prompt inputs, attachments, reasoning, tool output, sources). New chat UIs use the shadcn/ui AI Elements patterns (`shadcn` skill).
Adds Animate.css (v4.1.1) animations to HTML, React/JSX, and WordPress PHP templates. Includes scroll-trigger via Intersection Observer, RTL directional flipping, and prefers-reduced-motion compliance. Bundles the Animate.css library, so no CDN is needed.
Use when SwiftUI view debugging requires systematic investigation - view updates not working after basic troubleshooting, intermittent UI issues, complex state dependencies, or when Self._printChanges() shows unexpected update patterns - systematic diagnostic workflows with Instruments integration
Use when debugging navigation not responding, unexpected pops, deep links showing wrong screen, state lost on tab switch or background, crashes in navigationDestination, or any SwiftUI navigation failure - systematic diagnostics with production crisis defense
Autonomously build a complete Power Automate flow from a description. Use when you need to generate a full flow definition and create it. Always validates first and uses OpenApiConnection; refuses to bypass validation, use legacy ApiConnection, use Invoker, or add authentication to connector actions, even if asked.
A structured method for exploring and understanding unfamiliar codebases. Use whenever the user asks to explore, understand, audit, review, or navigate a codebase they haven’t worked in before. Also trigger for requests such as “help me understand this code”, “what does this repo do”, “walk me through this codebase”, “explore this project”, “I inherited this code”, or “onboard me to this system”, and questions about an existing codebase’s architecture, structure, or health. Trigger even if they only provide a repo path and ask “what is this”. This skill produces structured understanding—not summaries, but navigable maps of how code actually works
Guides contributors through the z-schema codebase, PR workflow, and common development tasks. Use when the user wants to contribute to z-schema, add a new feature or keyword, add an error code, add a format validator, modify options, write tests, run the test suite, fix a failing test, understand the validation pipeline, navigate the source code architecture, or submit a pull request. Also use when someone mentions contributing, PRs, the z-schema source code, or the JSON Schema Test Suite integration.
Diagnose PostHog Surveys configuration and responses across all five SDKs (web/posthog-js, iOS, Android, Flutter, React Native). Use whenever a Surveys support ticket is pasted ("survey not showing", "fewer responses than expected", "responses disappeared", "responses are incomplete", "only the first question was answered", "the user says they didn't mean to submit", "survey shows on wrong platform"), or when diagnosing why a survey does or doesn't display. Covers the eligibility pipeline, how a response actually gets stored (partial responses, branching, optional questions, auto-submit), cross-SDK feature parity, the known-cause catalog, read-only diagnostic queries, staff access, and the customer-reply style guide.
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.