소개
The LLM Integration skill provides a comprehensive toolkit for developers building sophisticated AI-powered applications, offering standardized patterns for integrating major LLM providers including Claude, GPT, Gemini, and local Ollama models. It simplifies complex AI workflows by providing advanced implementation guidance for extended thinking, sophisticated prompt engineering (such as few-shot and chain-of-thought), and intelligent token budget management. By implementing a unified multi-model abstraction layer, this skill enables developers to build resilient, provider-agnostic AI agents and applications that can seamlessly switch between or orchestrate across different large language models depending on the task requirements.
