skills.rest
LauraFlorentin
LauraFlorentinCOMMUNITY
Explore all skills by this author →
GitHub

rag

Retrieves relevant documents from a knowledge base to ground responses.

1|Updated Feb 11, 2026
Search Tags:#rag#semantic-search#knowledge-base#vector-search#retrieval-augmented-generation#llm-prompting#contextual-generation
One-click install
npx skills add https://github.com/LauraFlorentin/skills-marketplace --skill rag-lauraflorentin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag
Source: https://github.com/LauraFlorentin/skills-marketplace/tree/main/agentic-skills/skills/rag
Command: npx skills add https://github.com/LauraFlorentin/skills-marketplace --skill rag-lauraflorentin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The RAG pattern connects an LLM to external data sources to ground responses, improving factual accuracy and enabling access to private knowledge bases.

Core Features & Use Cases

  • Retrieval from a vector store or knowledge base to gather relevant documents before answering.
  • Prompt construction that constrains generation to the retrieved context and cites sources.
  • Use cases include enterprise search, legal analysis, and customer support scenarios.

Quick Start

Enable a retrieval-augmented workflow by querying a vector store and incorporating top documents before answering.

Frequently Asked Questions about rag

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

FAQPage Schema
What is retrieval-augmented generation and how does it ground LLM responses?▼

Retrieval-augmented generation (RAG) connects an LLM to external data sources by retrieving relevant documents from a knowledge base before answering, constraining generation to the retrieved context to improve factual accuracy.

How do I build a RAG workflow for enterprise search and customer support?▼

To build a RAG workflow, chunk your data into a vector store, embed user queries to retrieve top results, and construct a context-aware prompt that generates answers while citing sources for enterprise search or customer support.

Does retrieval-augmented generation require a vector store for legal analysis?▼

Yes, retrieval-augmented generation requires a vector store or knowledge base to gather relevant documents. For legal analysis, it embeds user queries to retrieve top results and constrains generation to the retrieved context.

Why use RAG instead of standard LLM prompting for private knowledge bases?▼

RAG improves factual accuracy by connecting an LLM to private knowledge bases. Unlike standard LLM prompting, it retrieves relevant documents first, constrains generation to retrieved context, and cites sources for verifiable answers.

When should I avoid retrieval-augmented generation for my knowledge base?▼

Avoid retrieval-augmented generation if your task requires unconstrained creative generation rather than factual accuracy, as RAG deterministically constrains outputs to retrieved context and cites sources from the knowledge base.

Related Skills

Explore More Data & Analytics Skills→
PostalocityPostalocity
1

rag-engineer

Design and optimize RAG pipelines with embeddings, chunking, and vector stores.

Official
Advanced
ed3daied3dai
5

researching-on-the-internet

Gather current, well-sourced internet information with citations for planning decisions.

Official
Basic
jayll1303jayll1303
17

text-embeddings-rag

Generate local embeddings and build retrieval-augmented generation pipelines with sentence-transformers and FAISS.

Community
Advanced
Kingly-AgencyKingly-Agency

rag-implementation

Build RAG pipelines that ground LLM responses with retrieved external knowledge.

Official
Advanced