skills.rest
bcastelino
bcastelinoCOMMUNITY
Explore all skills by this author →
Website𝕏@cas7elinoGitHub

rag-engineer

Design and optimize RAG systems for LLM applications.

2|Updated Feb 6, 2026
Search Tags:#embeddings#llm#rag#vector database#knowledge base#retrieval
One-click install
npx skills add https://github.com/bcastelino/agent-skills-kit --skill rag-engineer-bcastelino
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-engineer
Source: https://github.com/bcastelino/agent-skills-kit/tree/main/skills/rag-engineer
Command: npx skills add https://github.com/bcastelino/agent-skills-kit --skill rag-engineer-bcastelino

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the challenge of effectively integrating external knowledge into Large Language Models (LLMs) by optimizing the retrieval process, ensuring that the LLM receives accurate and relevant information for generation.

Core Features & Use Cases

  • Retrieval-Augmented Generation (RAG) System Design: Expert guidance on building robust RAG pipelines.
  • Embedding Model and Vector Database Expertise: Masters the selection and implementation of embedding models and vector stores.
  • Chunking and Retrieval Optimization: Implements advanced strategies for document preprocessing and efficient information retrieval.
  • Use Case: When developing a customer support chatbot that needs to access and synthesize information from a large knowledge base of product manuals, this skill can be used to design the optimal RAG architecture.

Quick Start

Use the rag-engineer skill to design a semantic chunking strategy for a collection of technical documents.

Frequently Asked Questions about rag-engineer

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

FAQPage Schema
How do I build a RAG system for an LLM application?▼

Build a RAG system by designing a pipeline that integrates embedding models, a vector database, document chunking, and retrieval strategies to feed accurate external knowledge into your LLM for generation.

What's the best way to chunk documents for retrieval-augmented generation?▼

Semantic chunking is an advanced strategy for document preprocessing in retrieval-augmented generation, optimizing how technical documents are divided to improve the relevance of information retrieved by the LLM.

How do I choose an embedding model and vector database for my knowledge base?▼

Selecting embedding models and vector stores requires evaluating their ability to map your knowledge base into searchable vectors, ensuring efficient information retrieval to enhance downstream LLM generation quality.

Does hybrid search improve retrieval quality for large knowledge bases?▼

Hybrid search is an architecture pattern that improves retrieval quality in large knowledge bases by combining multiple search strategies, ensuring the LLM receives more accurate and relevant information for generation.

Do I need NLP expertise to optimize retrieval-augmented generation pipelines?▼

Yes, optimizing retrieval-augmented generation pipelines requires NLP expertise to effectively implement embedding models, semantic chunking, and advanced retrieval strategies within your RAG architecture.

Related Skills

Explore More Software Engineering Skills→
sixscripts-aisixscripts-ai

rag-implementation

Implement RAG systems with vector stores, embeddings, and retrieval pipelines.

Community
Advanced
ruskibeatsruskibeats

rag-evidence-contract-testing

Validate retrieved graph edge evidence structure for LLM RAG context assembly.

Community
Intermediate
ryasrkryasrk

prompt-engineering

Design system prompts, RAG pipelines, and tool-calling workflows for LLM providers.

Community
Advanced
Supporter09Supporter09

sentence-transformers

Generate sentence, text, and image embeddings using PyTorch transformer models.

Community
Intermediate