skills.rest
0xRayAI
0xRayAIOFFICIAL
Explore all skills by this author →
GitHub

rag-engineer

Configure chunking boundaries, embedding dimensions, and similarity metrics for retrieval-augmented generation pipelines.

Updated Jun 5, 2026
Search Tags:#embeddings#llm#rag#retrieval#vector search#nlp
One-click install
npx skills add https://github.com/0xRayAI/xray --skill rag-engineer-0xrayai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-engineer
Source: https://github.com/0xRayAI/xray/tree/main/integrations/rag-engineer
Command: npx skills add https://github.com/0xRayAI/xray --skill rag-engineer-0xrayai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the common failure of LLM applications where poor retrieval quality leads to hallucinations and irrelevant responses by optimizing the entire document-to-context pipeline.

Core Features & Use Cases

  • Semantic Chunking: Implements context-aware splitting that respects document structure rather than arbitrary token limits.
  • Hierarchical Retrieval: Orchestrates multi-level indexing to improve precision through parent-child relationships.
  • Hybrid Search: Combines keyword-based BM25 matching with vector similarity to ensure both exact and conceptual relevance.

Quick Start

Use the rag-engineer skill to analyze my document repository and recommend an optimal chunking strategy for semantic retrieval.

Frequently Asked Questions about rag-engineer

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

FAQPage Schema
How do I optimize RAG retrieval to stop my LLM from hallucinating?▼

Optimizing RAG retrieval involves configuring context-aware semantic chunking, hierarchical indexing, and hybrid search combining BM25 with vector similarity to prevent LLM hallucinations and irrelevant responses.

What is the best way to chunk documents for semantic search?▼

The best way to chunk documents for semantic search is implementing context-aware splitting that respects document structure rather than relying on arbitrary token limits, ensuring high-precision indexing.

How does hybrid search improve retrieval-augmented generation pipelines?▼

Hybrid search improves retrieval-augmented generation by combining keyword-based BM25 matching with vector similarity, ensuring both exact term relevance and conceptual relevance are captured in the retrieved context.

When do I need hierarchical retrieval for my document repository?▼

You need hierarchical retrieval for large document repositories when improving precision through multi-level indexing and parent-child relationships is essential for managing context windows and relevance-based information retrieval.

How do I configure embedding dimensions and similarity metrics for vector search?▼

Configuring embedding dimensions and similarity metrics for vector search requires optimizing the document-to-context pipeline, balancing embedding sizes against retrieval precision to support high-precision document indexing.

Why does poor retrieval quality lead to irrelevant LLM responses?▼

Poor retrieval quality leads to irrelevant LLM responses because the context window receives inadequate or mismatched document fragments, failing to satisfy the technical requirements for high-precision information retrieval.

Related Skills

Explore More Software Engineering Skills→
giuseppe-trisciuogliogiuseppe-trisciuoglio
322

rag-implementation

Build retrieval-augmented generation pipelines with vector databases and embedding models.

Community
Advanced
h4vzzh4vzz
33

context-optimization

Optimize raw context chunks for AI models within a token budget.

Community
Intermediate
ricardorochericardoroche
2

rag-design-patterns

Standardizes chunking, vector database integration, embedding management, and retrieval reranking for RAG pipelines.

Community
Intermediate
Serg28Serg28

rag-architect

Guide design of RAG systems with chunking, embedding, and hybrid search.

Community
Advanced