This one cuts through the usual RAG hype with a production-focused framework that starts with a reality check. Before you spin up vector databases and embeddings pipelines, it walks you through validating whether you actually need RAG or if a simpler solution works. The core principle is clean: retrieval plus context assembly plus generation. It's built for teams who've seen too many overengineered RAG implementations and want guard rails for the real costs and complexity. The prerequisite checklist alone is worth reading before your next sprint planning meeting where someone suggests throwing RAG at a problem.
npx skills add https://github.com/daffy0208/ai-dev-standards --skill rag-implementer