context-retrieval

Retrieve and synthesize relevant knowledge base information using RAG techniques.

147|32|Updated Feb 11, 2026

Search Tags:#context #llm #rag #vector database #knowledge base #retrieval

Ready to run

npx skills add https://github.com/seb1n/awesome-ai-agent-skills --skill context-retrieval-seb1n

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: context-retrieval
Source: https://github.com/seb1n/awesome-ai-agent-skills/tree/main/context-engineering/context-retrieval
Command: npx skills add https://github.com/seb1n/awesome-ai-agent-skills --skill context-retrieval-seb1n

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the challenge of AI hallucinations by retrieving and synthesizing relevant information from a knowledge base, ensuring AI-generated responses are accurate and verifiable.

Core Features & Use Cases

Retrieval Augmented Generation (RAG): Leverages vector databases and reranking models to find the most pertinent information.
Context Assembly: Organizes retrieved chunks with source metadata for clear citation.
Use Case: When an AI agent needs to answer a complex question about a company's internal documentation, this skill fetches the most relevant sections to provide a grounded, factual answer.

Quick Start

Use the context-retrieval skill to find and synthesize information relevant to the query "How does the authentication middleware validate JWT tokens?".

Frequently Asked Questions about context-retrieval

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

FAQPage Schema

How does RAG context retrieval stop LLM hallucinations?▼

RAG context retrieval stops LLM hallucinations by embedding a query, searching a vector database, and reranking results with cross-encoders to synthesize factual context. This grounds AI responses in verifiable knowledge base information instead of fabricated outputs.

What is the best way to retrieve relevant information from a knowledge base for an LLM prompt?▼

The best way to retrieve knowledge base information for an LLM prompt is using RAG techniques. This involves embedding the query, searching vector stores for pertinent chunks, reranking results with cross-encoders, and assembling the context with source metadata for citation.

How do I ground AI answers using internal documentation?▼

You ground AI answers in internal documentation by using RAG context retrieval to fetch the most relevant sections. It searches a vector database, reranks the matching chunks, and assembles them into the LLM prompt to ensure factual, verifiable responses.

Can I get source citations from retrieved vector database chunks?▼

Yes, you can get source citations from retrieved vector database chunks. The context assembly process organizes the fetched information with source metadata, ensuring that AI-generated responses are grounded and clearly cite their originating documentation.

Does context retrieval with cross-encoders improve vector search accuracy?▼

Yes, context retrieval improves vector search accuracy by applying cross-encoders to rerank the initial results. This RAG mechanism refines the relevance of the fetched chunks before assembling them into the LLM context, leading to more precise factual answers.