RAG System Builder
Build a high-performance Retrieval-Augmented Generation system from scratch.
DAT-001-dataset-explorer
Generated Generative skill for Data Science. Focuses on execution and intent intelligence.
DAT-046-data-quality-checker
Generated Generative skill for Data Science. Focuses on execution and intent intelligence.
DAT-012-nlp-preprocessor
Generated Analytical skill for Data Science. Focuses on execution and intent intelligence.
embedding-strategies
Guide to selecting and optimizing embedding models for vector search applications.
DAT-058-embedding-visualizer
Generated Agentic skill for Data Science. Focuses on execution and intent intelligence.
vector-index-tuning
Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.
llm-evaluation
Master comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing.
DAT-100-experiment-tracker
Generated Transformative skill for Data Science. Focuses on execution and intent intelligence.
DAT-049-benchmark-comparator
Generated Conversational skill for Data Science. Focuses on execution and intent intelligence.
rag-implementation
RAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and retrieval optimization.
llm-structured-output
>
prompt-caching
You're a caching specialist who has reduced LLM costs by 90% through strategic caching. You've implemented systems that cache at multiple levels: prompt prefixes, full responses, and semantic similarity matches.
hybrid-search-implementation
Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
Vector Database (Pinecone/Milvus) Designer
High-power architectural assistant specializing in scaling semantic search for LLM apps using modern infrastructure patterns.
data ingestion
- 01dataset-explorer
- 02data-quality-checker
- 03nlp-preprocessor
embedding pipeline
- 01embedding-strategies
- 02embedding-visualizer
- 03vector-index-tuning
evaluation
- 01llm-evaluation
- 02experiment-tracker
- 03benchmark-comparator
generation layer
- 01rag-implementation
- 02llm-structured-output
- 03prompt-caching
retrieval engine
- 01hybrid-search-implementation
- 02similarity-search-patterns
- 03vector-db-pinecone-designer