RAG Implementer

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.

GitHub stars: 33
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add daffy0208/ai-dev-standards --skill 'RAG Implementer' --agent claude-code

Installs into .claude/skills of the current project.

Files

RAG Implementer

Build production-ready retrieval-augmented generation systems.

Core Principle

RAG = Retrieval + Context Assembly + Generation

Use RAG when you need LLMs to access fresh, domain-specific, or proprietary knowledge that wasn't in their training data.

⚠️ Prerequisites & Cost Reality Check

STOP: Have You Validated the Need for RAG?

Before implementing RAG, confirm:

Problem validated - Completed product-strategist Phase 1 (problem discovery)
Users need AI search - Tested with simpler alternatives (see below)
ROI justified - Calculated cost vs benefit of RAG vs alternatives