skills.rest
Entelligentsia
EntelligentsiaOFFICIAL
Explore all skills by this author →
WebsiteGitHub

rag

Retrieve external documents and integrate cited sources into LLM answers.

1|1|Updated Mar 30, 2026
Search Tags:#documentation#llm#rag#retrieval#provenance#grounding#vector-search
One-click install
npx skills add https://github.com/Entelligentsia/skillforge --skill rag-entelligentsia
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag
Source: https://github.com/Entelligentsia/skillforge/tree/main/llm-patterns/skills/rag
Command: npx skills add https://github.com/Entelligentsia/skillforge --skill rag-entelligentsia

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ground LLM outputs with up-to-date facts and domain data by retrieving and citing sources, reducing hallucinations and enabling auditing.

Core Features & Use Cases

  • Retrieval-Augmented Generation (RAG) pipeline for grounding answers with retrieved documents.
  • Chunking, ranking, and context assembly to fit within token budgets while preserving provenance.
  • Use Cases: internal knowledge bases, proprietary data access, customer support with sourced responses, regulatory or compliance documentation.

Quick Start

Ask the assistant to answer using only the retrieved context and to cite sources.

Frequently Asked Questions about rag

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

FAQPage Schema
How do I ground LLM answers with external knowledge and citations?▼

You can ground LLM answers by using a retrieval-augmented generation pipeline to fetch external documents, assemble the context, and instruct the LLM to answer using only those retrieved sources with citations. This reduces hallucinations and enables auditing.

What is the best way to reduce LLM hallucinations on proprietary data?▼

The best way to reduce LLM hallucinations on proprietary data is implementing a retrieval-augmented generation pipeline that chunks and ranks source documents, then restricts the LLM to answer strictly from the assembled context.

How does vector search fit into a retrieval-augmented generation pipeline?▼

Vector search fits into a retrieval-augmented generation pipeline as the retriever mechanism, finding relevant document chunks which are then ranked and assembled into the context window to ground the LLM.

Can I use retrieval-augmented generation for compliance documentation?▼

Yes, you can use retrieval-augmented generation for compliance documentation because it preserves provenance and provides cited responses, ensuring regulatory answers are auditable and grounded in trusted sources.

Do I need a specific retriever and context assembler to build a RAG pipeline?▼

Yes, building a RAG pipeline requires a retriever to fetch relevant documents, a context assembler to fit chunks within token budgets while preserving provenance, and a compliant LLM to generate answers using only the provided sources.

Why does my LLM hallucinate when answering questions from internal knowledge bases?▼

Your LLM hallucinates because it lacks grounding in current facts. By applying a retrieval-augmented generation pipeline that retrieves and cites external sources, you can restrict outputs to verified proprietary information.

Related Skills

Explore More Software Engineering Skills→
48Nauts-Operator48Nauts-Operator
3

hybrid-search-implementation

Implement hybrid search combining vector similarity with BM25 ranking.

Community
Advanced
skwuwuskwuwu

gvm_audit

Verify GVM audit log integrity and export compliance reports.

Community
Intermediate
h4vzzh4vzz
33

context-compression

Compress long chat histories and documents to fit token limits while preserving critical facts.

Community
Intermediate
EngineerWithAIEngineerWithAI
4

rag-implementation

Integrate vector databases and embedding models to build RAG systems for LLM applications.

Official
Advanced