Skill UI

Build production-ready GraphQL servers with SDL-first or code-first schemas, resolvers using DataLoader batching, field-level authorization, query complexity guards, and WebSocket subscriptions for realtime APIs.

Build live transcription with Deepgram's WebSocket API, managing microphone capture, interim/final handling, and speaker diarization for realtime audio workflows.

Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creatio...

Implements the Supabase secondary workflow that unites authentication, storage, and realtime subscriptions into one coherent setup for extending primary applications or delivering supporting features, complete with setup/process/completion steps and error handling guidance.

Expert in building voice AI applications - from real-time voice agents to voice-enabled apps. Covers OpenAI Realtime API, Vapi for voice agents, Deepgram for transcription, ElevenLabs for synthesis...

Explains building secure real-time communication with WebSocket servers, Socket.io rooms, SSE, Redis scaling, and resilient clients for multi-server Node.js apps.

Three.js Loaders collects patterns for loading GLTF, textures, HDR/EXR skies, cube/environment maps, and async asset coordination so you can manage progress bars and preprocess assets for realtime scenes.