RAG Engineer
FreeOptimize retrieval for better LLM performance.
Free · Opens the source repo
What RAG Engineer does
The RAG Engineer skill is designed for developers and data scientists focused on building Retrieval-Augmented Generation (RAG) systems. This skill equips users with the knowledge and strategies needed to effectively bridge the gap between raw documents and their understanding by large language models (LLMs). By emphasizing the importance of retrieval quality, the skill provides insights into chunking strategies, embedding models, and retrieval optimization, ensuring that the input data significantly enhances the output generated by LLMs.
Users will learn how to implement vector embeddings and similarity search, which are crucial for creating effective retrieval systems. The skill covers document chunking techniques that prioritize semantic meaning over arbitrary token counts, enabling better context preservation. It also delves into the design of retrieval pipelines and the implementation of hybrid search strategies that combine both keyword and semantic matching, allowing for more precise information retrieval.
This skill is particularly suited for those who have a foundational understanding of LLMs and embeddings, as it builds on these concepts to develop advanced retrieval techniques. It is ideal for engineers and researchers working on applications that require sophisticated document retrieval capabilities, such as semantic search and context-aware information extraction. By mastering these techniques, users can significantly improve the accuracy and relevance of the information provided by their LLM applications.
When to use it
Use this skill when developing RAG systems, implementing vector search, or optimizing document retrieval processes.
When not to use it
This skill may not be suitable for users without a basic understanding of LLMs and embeddings, as it assumes familiarity with these foundational concepts.
What you can build with it
Building a RAG System
Utilize the RAG Engineer skill to design and implement a robust retrieval system that enhances the performance of your LLM application.
Improving Document Retrieval
Apply advanced chunking and retrieval strategies to optimize how your application retrieves and processes documents, ensuring more relevant outputs.
Implementing Hybrid Search
Leverage hybrid search techniques to combine keyword and semantic matching, improving the precision of search results in your applications.
How to install RAG Engineer
View source1. Install with the skills CLI
npx skills add davila7/claude-code-templates/rag-engineer --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by davila7RAG Engineer
Role: RAG Systems Architect
I bridge the gap between raw documents and LLM understanding. I know that retrieval quality determines generation quality - garbage in, garbage out. I obsess over chunking boundaries, embedding dimensions, and similarity metrics because they make the difference between helpful and hallucinating.
Capabilities
- Vector embeddings and similarity search
- Document chunking and preprocessing
- Retrieval pipeline design
- Semantic search implementation
- Context window optimization
- Hybrid search (keyword + semantic)
Requirements
- LLM fundamentals
- Understanding of embeddings
- Basic NLP concepts
Patterns
Semantic Chunking
Chunk by meaning, not arbitrary token counts
- Use sentence boundaries, not token limits
- Detect topic shifts with embedding similarity
- Preserve document structure (headers, paragraphs)
- Include overlap for context continuity
- Add metadata for filtering
Hierarchical Retrieval
Multi-level retrieval for better precision
- Index at multiple chunk sizes (paragraph, section, document)
- First pass: coarse retrieval for candidates
- Second pass: fine-grained retrieval for precision
- Use parent-child relationships for context
Hybrid Search
Combine semantic and keyword search
- BM25/TF-IDF for keyword matching
- Vector similarity for semantic matching
- Reciprocal Rank Fusion for combining scores
- Weight tuning based on query type
Anti-Patterns
❌ Fixed Chunk Size
❌ Embedding Everything
❌ Ignoring Evaluation
⚠️ Sharp Edges
| Issue | Severity | Solution |
|---|---|---|
| Fixed-size chunking breaks sentences and context | high | Use semantic chunking that respects document structure: |
| Pure semantic search without metadata pre-filtering | medium | Implement hybrid filtering: |
| Using same embedding model for different content types | medium | Evaluate embeddings per content type: |
| Using first-stage retrieval results directly | medium | Add reranking step: |
| Cramming maximum context into LLM prompt | medium | Use relevance thresholds: |
| Not measuring retrieval quality separately from generation | high | Separate retrieval evaluation: |
| Not updating embeddings when source documents change | medium | Implement embedding refresh: |
| Same retrieval strategy for all query types | medium | Implement hybrid search: |
Related Skills
Works well with: ai-agents-architect, prompt-engineer, database-architect, backend
Frequently asked questions about RAG Engineer
Similar skills
Mini Context Graph
Build a persistent knowledge base with structured retrieval.
Pinecone RAG
Build RAG pipelines with Pinecone as your vector database.
Amazon Bedrock
Build generative AI applications on AWS Bedrock.
Supermemory
Enhance AI agents with persistent memory and context.
RAG Implementation
Build knowledge-grounded AI systems with RAG.
Memory Management
Enhance learning and knowledge sharing with persistent memory.