LLM-Zero-to-Hundred

Run the RAG-GPT test suite and smoke-test the live app end-to-end. Use /test-pipeline to run all tests, or /test-pipeline <name|path> to run a single test.

Load this skill when working on the RAG-GPT sub-project pipeline — document ingestion, embedding, retrieval, prompt construction, or response formatting. Also load when debugging ChromaDB, LangChain, or Gradio issues in RAG-GPT.