Try it
Add the skill to a bot, then ask your Chief of Staff:
“Use the RAG Architect skill on this: [describe the job, or paste your notes].”
Retrieval-Augmented Generation (RAG) enhances LLM outputs by grounding them in external knowledge. A well-architected RAG system requires careful decisions across ingestion, indexing, retrieval, and generation stages. This skill covers production-grade RAG design from document processing through quality assessment.
What it covers
- RAG Architecture Layers
- Document Chunking Strategies
- Embedding Model Selection
- Vector Database Selection
- Retrieval Strategies
- Context Window Packing
- Question
- Quality Assessment Framework