skills.rest
LuisSambrano
LuisSambranoCOMMUNITY
Explore all skills by this author →
𝕏@luissambrano_uxGitHub

rag-mastery

Develop and optimize Retrieval-Augmented Generation systems with chunking, embedding models, vector stores, and retrieval strategies.

7|2|Updated Jan 28, 2026
Search Tags:#embeddings#ai#llm#rag#retrieval#vector search
One-click install
npx skills add https://github.com/LuisSambrano/antigravity-config --skill rag-mastery
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-mastery
Source: https://github.com/LuisSambrano/antigravity-config/tree/main/skills/2-ai/rag-mastery
Command: npx skills add https://github.com/LuisSambrano/antigravity-config --skill rag-mastery

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill addresses the challenges of ineffective Retrieval-Augmented Generation (RAG) systems by providing expert strategies for chunking, embedding, and retrieval, ensuring LLMs receive the most relevant information.

Core Features & Use Cases

  • Advanced Chunking: Implements semantic and hierarchical chunking to preserve meaning and context.
  • Optimized Retrieval: Utilizes hybrid search and reranking techniques for precise information retrieval.
  • Use Case: When building a customer support chatbot that needs to access a large knowledge base, this skill helps ensure the chatbot retrieves the most accurate and relevant answers to user queries, minimizing hallucinations.

Quick Start

Use the rag-mastery skill to implement semantic chunking for a given document.

Frequently Asked Questions about rag-mastery

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

FAQPage Schema
How do I improve retrieval accuracy in a RAG system?▼

Improve retrieval accuracy by utilizing hybrid search and reranking techniques for precise information retrieval. Optimized retrieval ensures LLMs receive the most relevant context, minimizing hallucinations and directly improving response quality.

What is the best way to chunk documents for LLM context?▼

The best way to chunk documents is implementing semantic and hierarchical chunking to preserve meaning and context. This ensures that the LLM receives coherent information blocks, which improves the overall response quality.

Why does my LLM hallucinate when querying a large knowledge base?▼

LLMs hallucinate when querying large knowledge bases due to ineffective retrieval delivering irrelevant context. Address this by mastering document chunking, embedding models, and vector search strategies to ensure precise information delivery.

How do I optimize RAG latency for customer support chatbots?▼

Optimize RAG latency by addressing retrieval accuracy and system challenges through efficient document chunking and embedding models. Streamlining these retrieval strategies ensures customer support chatbots deliver rapid, accurate answers from large knowledge bases.

Do I need a vector store to build an effective RAG pipeline?▼

Yes, a vector store is needed to build an effective RAG pipeline, as it supports the embedding models and vector search strategies required for retrieving precise information. Mastering vector stores directly improves LLM response quality.

Related Skills

Explore More Software Engineering Skills→
Himanshu040604Himanshu040604

embedding-strategies

Select and optimize embedding models for semantic search and RAG applications.

Community
Advanced
truongnattruongnat

fullstack-rag-pro

Construct a RAG pipeline with document ingestion, embeddings, vector querying, and LLM synthesis.

Community
Advanced
davpatel605-beepdavpatel605-beep

qdrant-vector-search

Build vector similarity search systems with Qdrant for RAG applications.

Community
Advanced
findinfinitelabsfindinfinitelabs

intelligent-text-chunking

Split long texts into coherent chunks while preserving semantic structure.

Community
Intermediate