skills

Setup comprehensive SEO for a Next.js project using built-in metadata APIs. Use when user says "setup seo", "add seo", "configure metadata", "add sitemap", "add open graph", or "improve seo".

Setup a design system using shadcn/ui. Use this skill when the user says "setup design system", "set up design system", "create design system", "setup shadcn", or "initialize design system".

Rich artifact panel for AI chat — code, HTML, Mermaid diagrams, tables, and markdown render in a resizable side panel. Use this skill when the user says "add artifacts", "add code preview", "add side panel", "artifact panel", or "rich output".

Live closed captions for video rooms — floating caption overlay with speaker labels, configurable font size, position, and opacity. Powered by Deepgram transcription via LiveKit data channels. Use this skill when the user says "add captions", "setup closed captions", "add subtitles", "live captions", or "setup ai-captions".

Communication layer — streaming chat UI with Postgres persistence, session management, and composable route/renderer architecture for downstream AI skills. Use this skill when the user says "add chat", "setup AI chat", "add streaming chat", or "setup ai-chat".

Foundation AI layer — configures AI Gateway provider and exports getModel() for all downstream AI skills. Use this skill when the user says "setup AI", "add AI", "configure AI gateway", or "setup ai-core".

Data-driven generative UI — tool results render as rich React components in chat instead of raw JSON. Uses a registry pattern with _ui field, not createStreamableUI(). Use this skill when the user says "generative ui", "rich tool cards", "custom tool rendering", or "tool components".

AI image generation with Replicate and fal.ai — text-to-image, image-to-image, inpainting with multiple model support. Use this skill when the user says "add image generation", "setup ai images", "add replicate", "text to image", or "ai image gen".

Config-driven MCP (Model Context Protocol) server integration. Add external tool servers (GitHub, Brave Search, databases, etc.) by editing one config file — tools are auto-discovered, prefixed, and merged into the chat. Use this skill when the user says "add MCP", "connect MCP servers", "add external tools", or "setup ai-mcp".

AI-powered meeting notes — generates executive summaries, key decisions, action items, and timestamped timelines from transcripts using structured output. Use this skill when the user says "add meeting notes", "setup ai meeting notes", "meeting summary", "extract action items", or "ai meeting notes".

Cross-session memory with context injection. Persists user preferences and facts to Postgres, auto-injects relevant memories into the system prompt, and exposes save/recall tools. Use this skill when the user says "add memory", "remember things", "persistent context", or "cross-session memory".

Multi-agent orchestration — N AI agents with distinct personas debate sequentially in real-time. Each agent sees prior agents' output, creating adversarial pressure-testing. Use this skill when the user says "add multi-agent", "ai debate", "agent panel", "multi-agent chat", or "adversarial agents".

RAG-powered chat interface — retrieves relevant chunks via vector search, streams answers with source citations (page numbers + document titles), and persists conversations. Use this skill when the user says "add RAG chat", "chat with PDFs", "setup ai-rag-chat", or "add document Q&A".

PDF ingestion pipeline — chunked upload of large PDFs (up to 2GB) to S3 storage, parallel PDF parsing with unpdf, page-level text extraction, and processing status tracking with Postgres. Use this skill when the user says "setup PDF upload", "add PDF ingestion", "setup ai-rag-ingest", or "add document upload".

Vector embeddings layer — pgvector for Postgres, embedding generation via AI Gateway, recursive text chunking with overlap, cosine similarity search, and automatic indexing of parsed document pages. Use this skill when the user says "setup vectors", "add embeddings", "setup ai-rag-vectors", or "add semantic search".

Task extraction and management — the AI creates structured tasks from conversation, persisted to Postgres with a task list UI panel. Use this skill when the user says "add tasks", "task management", "todo list", "extract tasks", or "ai tasks".

Tool calling framework with built-in calculator and datetime tools. Renders tool invocations as collapsible cards in the chat UI. Use this skill when the user says "add tools", "tool calling", "calculator", or "add ai tools".

AI video generation with Replicate and fal.ai — text-to-video, image-to-video with multiple model support. Use this skill when the user says "add video generation", "setup ai video", "text to video", "image to video", or "ai video gen".

AI voice agent for video rooms — dispatch an AI participant that listens, thinks, and speaks in real-time meetings via LiveKit. Supports configurable personas (note-taker, strategist, interviewer, tutor). Use this skill when the user says "add AI agent to room", "ai voice participant", "setup voice agent", "add ai to meeting", or "setup ai-voice-room".

Audio-only room with LiveKit — circular avatar grid, speaking indicators, raise hand queue. Twitter Spaces / Clubhouse style. Use this skill when the user says "add audio room", "audio chat", "voice room", "spaces", "clubhouse", or "audio-only room".

Dev-mode authentication tooling — seed dev users and quick sign-in buttons for each role. Use this skill when the user says "setup dev auth", "add dev login", "setup dev users", "seed test users", or "dev sign-in".

Setup better-auth authentication with email/password, social providers, role-based access control, account management, and session handling. Use this skill when the user says "setup auth", "add authentication", "setup better-auth", "add login", or "setup user auth".

Simple CMS with posts, pages, categories, Tiptap rich text editor, and media management. Built on better-auth, drizzle, and storage skills. Use this skill when the user says "setup cms", "add cms", "content management", or "blog system".

PostgreSQL database with Drizzle ORM — Docker for local dev, connection pooling for production. Type-safe schema, migrations, and query patterns. Use this skill when the user says "setup database", "add db", "setup drizzle", "setup postgres", or "database setup".

Setup transactional email with Resend (production) and Mailpit (local) for auth and notifications. Use this skill when the user says "setup email", "add email", "transactional email", or "auth emails".

Embeddable chat widget — iframe-based chat scoped by businessId, a widget.js loader script, appearance configuration API, and public (no-auth) customer-facing routes. Use this skill when the user says "add widget", "embeddable chat", "setup widget", "iframe chat", or "setup embeddable-widget".

Real-time group chat with threads, reactions, mentions, and file attachments — Drizzle for persistence, Liveblocks for real-time delivery. Use this skill when the user says "add group chat", "setup chat", "add messaging", "team chat", or "group chat".

Canvas image editor with Konva.js — crop, resize, rotate, filters, brush masking, and layer compositing. Runs entirely client-side. Use this skill when the user says "add image editor", "setup canvas editor", "add konva", "image editing", or "photo editor".

Iteratively refine and validate agent skill markdown files by implementing them in a sandbox, running validation checks (TypeScript, linting, build, browser tests), writing tests, reflecting on errors, and updating the skill documentation until it produces error-free code. Use this skill when you need to polish a skill, refine a skill, test a skill, improve skill documentation, validate a skill, debug skill instructions, or ensure a skill works end-to-end.

External knowledge sync — fetches data from an external REST API, maps items to RAG documents, ingests and indexes them via the RAG pipeline, with on-demand and scheduled sync. Use this skill when the user says "sync knowledge", "import knowledge base", "setup knowledge-sync", "external data ingestion", or "connect knowledge API".

Go-live from a LiveKit room to MUX via RTMP egress — supports MUX, YouTube, Twitch, and custom RTMP destinations. Auto-archives to MUX VOD when stream ends. Use this skill when the user says "add livestream", "go live", "stream to mux", "rtmp stream", "broadcast", or "live streaming".

Browser-based video processing with mediabunny — read, write, convert MP4/WebM/MKV using WebCodecs API. Server integration for storage and metadata tracking.

Web Push notifications with VAPID — subscribe devices, send targeted pushes, notification preferences, and in-app notification center. Use this skill when the user says "add push notifications", "setup notifications", "add web push", "notification bell", or "push notifications".

Setup OpenTelemetry tracing and structured logging for Next.js applications. Use this skill when the user says "setup observability", "add tracing", "setup logging", "add telemetry", or "instrument app".

Credit-based billing with Stripe — subscriptions, credit balance, usage metering, checkout, billing portal. Use this skill when the user says "add payments", "setup billing", "add stripe", "setup credits", "subscription billing", or "stripe integration".

Background job queue with Inngest — serverless, works on Vercel, no Redis needed. Durable functions with retry, progress tracking, and job history. Use this skill when the user says "add queue", "setup jobs", "background jobs", "add inngest", or "async tasks".

Real-time collaboration with Liveblocks — presence cursors, conflict-free state sync, and room-based access. Use this skill when the user says "add realtime", "setup collaboration", "add liveblocks", "multiplayer", "live cursors", or "real-time sync".

Server-side room recording with LiveKit Egress — composite and track-based recording, S3 storage, recording metadata in Postgres. Use this skill when the user says "add recording", "record room", "record video", "record meeting", "egress recording", or "save recording".

Setup RSS, Atom, and JSON Feed generation for Next.js with Payload CMS integration. Use this skill when the user says "setup rss", "add rss feed", "setup atom feed", "add feed", "rss integration", or "syndication feeds".

Screen sharing components for LiveKit video rooms — toggle button, full-width screen share view with PiP camera overlay, and an auto-switching presenter layout. Use this skill when the user says "add screen share", "setup screen sharing", "presenter mode", "screen share view", or "setup screen-share".