webdev-llm-integration

What problem does it solve? Adding AI features to a Manus webdev fullstack or Expo mobile project normally requires managing API keys, SDK setup, and provider-specific quirks. This Skill provides preconfigured server-side LLM helpers with platform-injected credentials, so you can call chat completions, structured outputs, and reasoning models without manual credential setup. ## Core Features & Use Cases - Chat Completions via invokeLLM: Call LLMs from server-side code (e.g., tRPC procedures) with text, image, and file message content, keeping API keys off the client. - Structured JSON Responses: Enforce JSON Schema output via response_format for reliable data extraction and typed responses. - Model Discovery & Reasoning Controls: List available models at runtime with listLLMModels and pass thinking/reasoning parameters for Claude, GPT-5, and Gemini families. - Use Case: Build an AI feature in your web app that extracts a name and age from user text by calling invokeLLM with a strict json_schema, then render the markdown response with Streamdown. ## Quick Start Ask the AI to add an LLM-powered feature to your Manus webdev project using the invokeLLM helper from server/_core/llm inside a tRPC procedure.