RAGRetrievalLLMAI Agent Skill
rag
Guidance for designing a RAG (Retrieval-Augmented Generation) pipeline - chunking, embeddings, hybrid search - and when RAG is actually the right call.
Install Options
Install into Claude Code, Cursor, Codex, or Antigravity with:
$ npx skills add giuseppe-trisciuoglio/developer-kit@rag
Real Work Situation Solved
Decide between Prompting, RAG, or Fine-tuning for your AI feature
“The model lacks domain knowledge - do you fix the prompt, build RAG, or fine-tune?”
5-Step Action Framework
- 1Ask: Is the issue missing knowledge or wrong format/style? New knowledge → Prompt/RAG; Format/tone → Few-shot or Fine-tuning.
- 2Ask: Does the data change frequently? If yes → RAG is required; fine-tuning will go stale immediately.
- 3Check document size: If under 10 pages, inject directly into the context window before engineering a RAG pipeline.
- 4Evaluate engineering cost: Prompting (1 day) → RAG (1-2 weeks) → Fine-tuning (1-2 months + continuous retraining).
- 5Always prototype cheapest-first: Optimize system prompt → Build RAG when exceeding context → Fine-tune only if RAG fails on specialized formatting.
Before
"Let's just collect all data and fine-tune a model for maximum accuracy."
After
"Docs change weekly → Use RAG with hybrid search. Injected 3 few-shot examples into the system prompt to hit 80% quality without expensive fine-tuning."
Related Course Lesson
AI Product Management • Lesson 6
SKILL.md Source Instructions
SKILL.md • Read-only preview# RAG Skill Design document chunking, embedding, and hybrid retrieval strategies, and identify when frequently-changing knowledge makes RAG a better fit than fine-tuning.