skills.rest
stephanj
stephanjCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

rag-architect

Architect RAG systems integrating vector databases, embedding models, and retrieval pipelines.

9|2|Updated Jan 29, 2026
Search Tags:#system design#semantic search#embeddings#rag#vector database#retrieval
One-click install
npx skills add https://github.com/stephanj/claude-code-collections --skill rag-architect-stephanj
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-architect
Source: https://github.com/stephanj/claude-code-collections/tree/main/skills/rag-architect
Command: npx skills add https://github.com/stephanj/claude-code-collections --skill rag-architect-stephanj

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the complexity of building reliable Retrieval-Augmented Generation (RAG) systems, helping you avoid common pitfalls like poor retrieval quality, inefficient chunking, and hallucination-prone architectures.

Core Features & Use Cases

  • System Design: Architect end-to-end pipelines for document ingestion, vector storage, and retrieval.
  • Optimization: Fine-tune chunking strategies, embedding models, and hybrid search configurations to maximize accuracy.
  • Evaluation: Implement robust metrics (precision, recall, MRR) to monitor and debug retrieval performance.
  • Use Case: Use this when you need to build a knowledge-grounded chatbot that must accurately retrieve information from thousands of technical documents while maintaining low latency and high factual grounding.

Quick Start

Use the rag-architect skill to design a retrieval pipeline for my technical documentation knowledge base.

Frequently Asked Questions about rag-architect

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I design a production-grade RAG system for technical documents?▼

Evaluating RAG retrieval quality requires implementing robust metrics like precision, recall, and Mean Reciprocal Rank (MRR). These metrics monitor and debug retrieval performance to prevent hallucination-prone architectures and ensure factual grounding.

What's the best way to optimize chunking strategies and embeddings for a knowledge base?▼

Hybrid search in retrieval-augmented generation combines multiple search techniques to improve document retrieval accuracy. It is implemented by fine-tuning search configurations within your vector database pipeline to maximize precision across large technical knowledge bases.

How do I evaluate RAG retrieval quality and prevent hallucination-prone architectures?▼

Evaluating RAG retrieval quality requires implementing robust metrics like precision, recall, and Mean Reciprocal Rank (MRR). These metrics monitor and debug retrieval performance to prevent hallucination-prone architectures and ensure factual grounding.

Does building a knowledge-grounded chatbot require a vector database and continuous monitoring?▼

Building a knowledge-grounded chatbot requires a vector database for storage and continuous RAG performance monitoring for low latency. This architecture ensures high factual grounding when accurately retrieving information from thousands of technical documents.

Related Skills

Explore More Software Engineering Skills→
patornpatorn

langchain-rag

Build end-to-end RAG pipelines with LangChain document loaders, embeddings, and vector stores.

Community
Advanced
BagelHoleBagelHole
46

rag-observability-evals

Monitor RAG systems with retrieval and generation quality metrics.

Community
Advanced
ollieb89ollieb89

using-vector-databases

Implement vector database functionality for semantic search and RAG systems.

Community
Advanced
ai-kitchen-incai-kitchen-inc
2

data-layer

Chunk documents, generate embeddings, and index vectors in Pinecone for RAG.

Community
Intermediate