Data Science & ML Claude 스킬

BayesFlow Model Validation

Validates neural posterior estimators through Simulation-Based Calibration (SBC) and comprehensive diagnostic testing.

Quantitative Risk Metrics Calculation

Calculates comprehensive portfolio risk metrics like VaR, CVaR, and Sharpe ratios to monitor and manage financial exposure.

Data Storytelling & Analytics Narratives

Transforms raw data into persuasive narratives and visualizations for business stakeholders and executive presentations.

LLM Evaluation & Benchmarking

Implements comprehensive evaluation frameworks for LLM applications using automated metrics, human-in-the-loop feedback, and A/B testing.

Similarity Search Patterns

Implements efficient semantic search and vector database patterns for production-grade retrieval systems.

Quantitative Backtesting Frameworks

Builds robust, production-grade backtesting systems for trading strategies while eliminating common statistical biases.

Financial Analysis & Modeling

Provides comprehensive financial frameworks for modeling, valuation, corporate finance decisions, and advanced statement analysis.

FinPlan Financial Projection Engine

Models complex personal finance scenarios using Monte Carlo simulations, US tax logic, and goal-based projection tools.

Gemini Flash Integration

Enables high-speed multi-modal analysis and document summarization using Gemini Flash within the Claude Code environment.

ML Pipeline Workflow

Orchestrates end-to-end MLOps pipelines from data preparation and model training to production deployment and monitoring.

Biopython Molecular Biology Toolkit

Simplifies computational molecular biology by providing tools for sequence analysis, structural bioinformatics, and biological database integration.

LangChain Architecture

Architects sophisticated LLM applications using agents, memory, and tool integration within the LangChain framework.

BayesFlow Keras Ops

Ensures backend-agnostic tensor mathematics using Keras 3 operations for BayesFlow extensions and custom layers.

Vector Index Tuning

Optimizes vector database performance by tuning HNSW parameters, quantization strategies, and memory usage for high-scale search applications.

Spark Optimization

Optimizes Apache Spark performance through advanced partitioning, memory tuning, and shuffle management strategies.

PubMed Research Assistant

Accesses and queries the PubMed database for biomedical literature, systematic reviews, and citation management.

Zarr Python Data Storage

Manages large-scale N-dimensional arrays with chunked storage, compression, and seamless cloud integration for scientific computing pipelines.

BayesFlow Adapter

Optimizes the creation and debugging of BayesFlow data preprocessing pipelines for simulation-based inference.

Aeon Time Series ML

Empowers Claude to perform advanced time series machine learning, including classification, forecasting, and anomaly detection using the specialized aeon toolkit.

PennyLane Quantum Machine Learning

Builds, trains, and optimizes hybrid quantum-classical models using automatic differentiation and hardware-agnostic circuit programming.

BayesFlow Package Manager

Streamlines the creation and maintenance of BayesFlow extension packages with standardized structures and API export management.

Embedding & Chunking Strategies

Optimizes vector search and RAG applications through intelligent embedding model selection and advanced document chunking strategies.

SimPy Simulation Engine

Builds process-based discrete-event simulations in Python to model complex systems with resource contention and time-based events.

Python Project Structure Refactor

Transforms monolithic Python research code and notebooks into modular, production-ready package structures.

Scientific Critical Thinking

Evaluates scientific research rigor and evidence quality using standardized frameworks like GRADE and Cochrane.

Cryptofeed Integration

Streams and normalizes real-time cryptocurrency market data from over 40 exchanges for algorithmic trading and analysis.

Fantasy Football Analytics & ML

Develops predictive player projection models using specialized feature engineering and sports-specific machine learning validation techniques.

Excel & Spreadsheet Management

Automates professional spreadsheet creation, financial modeling, and data analysis with rigorous formula verification and industry-standard formatting.

ETE Phylogenetic Toolkit

Provides comprehensive tools for phylogenetic tree manipulation, evolutionary analysis, and high-quality biological data visualization.

EdgarTools SEC Analysis

Accesses and analyzes real-time SEC filings and financial statements with token-efficient data retrieval.