AI Skills for Data Scientist

Implements eval-driven development for Claude Code sessions, enhancing AI reliability through structured evaluation frameworks.

Enhances multi-agent workflows by refining context retrieval through iterative search patterns, improving task execution efficiency.

Automatically extracts reusable patterns from Claude Code sessions for future use, enhancing learning and efficiency.

Optimizes LLM API costs with model routing, budget tracking, retry logic, and prompt caching for efficient usage.

Provides best practices and idioms for building robust and maintainable Python applications, focusing on readability and type hints.

Enhances SQL query performance through optimization techniques, indexing strategies, and EXPLAIN analysis for faster database operations.

Enables comprehensive testing of smart contracts using Hardhat and Foundry, ensuring robust and secure blockchain applications.

Enhances Python code with type safety using type hints, generics, and strict checking for better error detection.

Facilitates the creation of end-to-end MLOps pipelines, automating data preparation, model training, validation, and deployment processes.

Enhances Python code quality through style guidelines, linting, and documentation standards for maintainable codebases.

Facilitates data quality validation using Great Expectations and dbt tests to ensure reliable data pipelines and metrics.

Enhances LLM performance through advanced prompt engineering techniques for optimized outputs and structured reasoning.

Optimizes vector index performance for latency, recall, and memory, enhancing vector search infrastructure efficiency.

Guides implementation of GDPR-compliant data handling, focusing on consent management and privacy controls for EU personal data.

Designs advanced LLM applications using LangChain and LangGraph for AI agents, memory management, and tool integration.

Implements evaluation strategies for LLM applications using metrics, human feedback, and benchmarking to ensure quality and performance.

Enables the creation of knowledge-grounded AI systems using Retrieval-Augmented Generation (RAG) with vector databases and semantic search.

Optimizes Python code performance through profiling and best practices, enhancing application speed and efficiency.

Creates robust backtesting systems for trading strategies, addressing biases and ensuring reliable performance evaluations.

Equips analysts with techniques to bypass software protections for authorized analysis, enhancing malware research and security assessments.