rag-engineer
Guides the architecture and implementation of Retrieval-Augmented Generation systems, focusing on embedding quality and retrieval precision.
Install
mkdir -p .claude/skills/rag-engineer && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/1659" && unzip -o skill.zip -d .claude/skills/rag-engineer && rm skill.zipInstalls to .claude/skills/rag-engineer
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.Key capabilities
- →Design retrieval pipeline
- →Implement semantic search
- →Optimize context window
- →Combine keyword and semantic search
- →Preprocess documents for chunking
- →Evaluate embedding models
How it works
This skill designs RAG systems by focusing on semantic chunking, hierarchical retrieval, and hybrid search to improve context quality for LLMs.
Inputs & outputs
When to use rag-engineer
- →Design a RAG pipeline
- →Optimize document chunking strategies
- →Implement semantic search
- →Evaluate hybrid search performance
About this skill
RAG 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
When not to use it
- →Using fixed chunk sizes
- →Embedding all content without selection
- →Ignoring evaluation metrics
Prerequisites
Limitations
- →Fixed-size chunking breaks sentences and context
- →Pure semantic search without metadata pre-filtering
- →Using same embedding model for different content types
How it compares
This approach optimizes retrieval by considering meaning and structure during chunking and combining search methods, unlike simple token-based splitting.
Compared to similar skills
rag-engineer side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| rag-engineer (this skill) | 3 | 6mo | No flags | Advanced |
| cocoindex | 6 | 9mo | Review | Intermediate |
| rag-implementation | 10 | 2mo | No flags | Intermediate |
| similarity-search-patterns | 3 | 2mo | No flags | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by davila7
View all by davila7 →You might also like
cocoindex
cocoindex-io
Comprehensive toolkit for developing with the CocoIndex library. Use when users need to create data transformation pipelines (flows), write custom functions, or operate flows via CLI or API. Covers building ETL workflows for AI data processing, including embedding documents into vector databases, building knowledge graphs, creating search indexes, or processing data streams with incremental updates.
rag-implementation
wshobson
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
similarity-search-patterns
wshobson
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
faiss
davila7
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
trulens-notebook-execution
truera
Execute and display Jupyter notebooks for TruLens demos and quickstarts
embedding-strategies
wshobson
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.