skills.rest
shalevamin
shalevaminCOMMUNITY
Explore all skills by this author →
GitHub

rag-architect

Designs and implements RAG systems with chunking, embedding generation, vector stores, hybrid search, reranking, and evaluation.

Updated Mar 7, 2026
Search Tags:#semantic search#embeddings#rag#vector database#knowledge base#retrieval augmented generation
One-click install
npx skills add https://github.com/shalevamin/The-_Ultimate_agents --skill rag-architect-shalevamin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-architect
Source: https://github.com/shalevamin/The-_Ultimate_agents/tree/main/.claude/skills/rag-architect
Command: npx skills add https://github.com/shalevamin/The-_Ultimate_agents --skill rag-architect-shalevamin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines the complex process of designing and implementing robust Retrieval-Augmented Generation (RAG) systems, ensuring efficient and accurate knowledge retrieval for AI applications.

Core Features & Use Cases

  • End-to-End RAG Design: Guides through requirements analysis, vector store design, chunking strategies, retrieval pipeline construction, and evaluation.
  • Production-Grade Implementation: Provides code examples and best practices for chunking, embedding, indexing, hybrid search, and reranking.
  • Use Case: When building a new AI-powered knowledge base or enhancing an existing application with external documents, use this Skill to architect a scalable and performant RAG system.

Quick Start

Use the rag-architect skill to design a RAG system for technical documentation.

Frequently Asked Questions about rag-architect

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

FAQPage Schema
How do I build a production-ready RAG system with semantic search and document retrieval?▼

To build a production-ready RAG system, you need to chunk documents, generate embeddings, configure vector stores, and construct hybrid search pipelines with reranking to achieve accurate knowledge retrieval.

What is the best way to implement chunking strategies and embeddings for a knowledge base?▼

Implementing chunking strategies and embeddings for a knowledge base involves splitting documents into manageable segments and converting them into vector representations to enable efficient similarity search and context augmentation.

How does hybrid search and reranking improve retrieval quality in a RAG pipeline?▼

Hybrid search and reranking improve retrieval quality in a RAG pipeline by combining multiple search methods to fetch broader candidate contexts and reordering them to prioritize the most relevant semantic results.

Can I use this approach to add external document retrieval to an existing AI application?▼

Yes, you can use this approach to add external document retrieval to an existing AI application by integrating an embedding-based indexing pipeline and vector database to ground responses with external knowledge.

What are the limitations of using embedding-based indexing for technical documentation?▼

Limitations of using embedding-based indexing for technical documentation include potential semantic mismatch during chunking and the need for continuous evaluation of retrieval quality to prevent context loss in specialized domains.

When do I need a vector database for my retrieval augmented generation application?▼

You need a vector database for your retrieval augmented generation application when you require scalable, similarity-based indexing to efficiently retrieve relevant document chunks from a large external knowledge base.

Related Skills

Explore More Software Engineering Skills→
vecearvecear

doc-to-vector-dataset-generator

Convert documents into chunked JSONL datasets with metadata for embedding search.

Community
Advanced
anukkrit149anukkrit149

rag-implementation

Build Retrieval-Augmented Generation systems grounding LLM answers in vector databases.

Community
Advanced
saddam-eng-techsaddam-eng-tech

token-cost-estimator

Calculate token usage and API costs for Claude models.

Community
Intermediate
giuseppe-trisciuogliogiuseppe-trisciuoglio
322

rag-implementation

Build retrieval-augmented generation pipelines with vector databases and embedding models.

Community
Advanced