Skill: AI/LLM Engineering

Auto-Detect

Trigger this skill when:

• Task mentions: RAG, embeddings, vector database, LLM, prompt engineering, fine-tuning, AI
• Files: prompts/, embeddings/, *.prompt, rag/, chains/
• Patterns: retrieval augmented generation, semantic search, chat completion
• Dependencies: openai, @anthropic-ai/sdk, langchain, @pinecone-database/pinecone, @qdrant/js-client-rest

Decision Tree: RAG Architecture