Data Science & ML Claude 스킬

Supervised Learning Model Builder

Builds, tunes, and evaluates production-ready classification and regression models using industry-standard machine learning algorithms.

Transformers AI Model Integration

Integrates Hugging Face Transformers for advanced natural language processing, computer vision, and audio tasks within development workflows.

Globus Dataset Staging

Manages large-scale scientific dataset transfers between remote Globus endpoints and high-performance computing clusters.

Gemini CLI Integration

Integrates the Google Gemini CLI into Claude to provide large-context analysis, safe sandbox execution, and structured code modifications.

KINTSUGI GPU-Only SLURM Scheduling

Optimizes KINTSUGI batch processing by enforcing GPU-only SLURM scheduling to achieve up to 25x speedups over CPU fallback.

Statsmodels Statistical Toolkit

Provides a comprehensive suite of statistical modeling tools for rigorous inference, hypothesis testing, and econometric analysis in Python.

Snakemake Per-Channel Resume Logic

Implements granular skip-existing checks in Snakemake wrapper scripts to resume interrupted HPC jobs without re-processing completed channels.

arXiv Research Terminal

Fetches, searches, and manages academic papers from arXiv through a local CLI-based database.

Genome Analyzer

Analyzes genomic VCF files to provide personalized insights on health, metabolism, and genetic traits.

PubMed Database Research

Automates biomedical literature searches and data retrieval from the PubMed database using advanced MeSH queries and the E-utilities API.

Weighted Autofluorescence Subtraction

Enhances multiplex immunofluorescence images by applying range-specific weights to remove background noise while preserving delicate biological signals.

Gemini Image Generator

Generates and transforms high-quality images using Google's Gemini models through customizable Python scripts.

Claude Model Selection

Guides the selection of the optimal Claude model for custom agent tasks based on cost, speed, and reasoning requirements.

Custom Agent Architect

Streamlines the design and architecture of domain-specific AI agents using Claude Agent SDK patterns.

PyLabRobot Lab Automation

Automates laboratory workflows and controls liquid handling robots, plate readers, and analytical equipment through a unified Python interface.

Trading Backtest & Colab Optimizer v4

Corrects multi-action trading logic bugs and optimizes backtesting notebooks for Google Colab environments.

NLP Text Analyzer

Analyzes textual data to extract sentiments, keywords, and core topics using advanced natural language processing techniques.

PufferLib RL Framework

Develops high-performance reinforcement learning systems with optimized PPO training, vectorized simulations, and multi-agent support.

Histolab Pathology Toolkit

Processes and prepares whole slide pathology images for deep learning and digital pathology workflows.

Mass Spectrometry Analysis with PyOpenMS

Analyzes mass spectrometry data for proteomics and metabolomics workflows using the PyOpenMS library.

Scikit-learn ML Suite

Streamlines machine learning workflows in Python by providing expert guidance on scikit-learn algorithms, data preprocessing, and production-ready pipelines.

scvi-tools for Single-Cell Analysis

Facilitates advanced probabilistic modeling and analysis of single-cell omics data using deep generative models.

Seaborn Statistical Visualization

Generates professional, publication-quality statistical graphics and complex multi-panel data visualizations using Python's Seaborn library.

Dask Parallel Computing

Enables parallel and distributed computing for Python data science workflows to process datasets larger than available memory.

LLM Model Auto-Updater

Synchronizes and updates the latest LLM model specifications, pricing, and API documentation automatically.

Financial Modeling

Builds comprehensive financial models including DCF analysis, sensitivity testing, and Monte Carlo simulations for investment and valuation decisions.

Qiskit Quantum Computing

Builds, optimizes, and executes quantum circuits and algorithms across various hardware providers and simulators.

SymPy Symbolic Mathematics

Performs exact symbolic computation, calculus, and equation solving in Python to handle complex mathematical formulas without numerical approximation.

Trading Performance Analysis

Analyzes Interactive Brokers CSV statements to uncover trading edges, identify risk management patterns, and generate professional performance reports.

Kymera Mean-Reversion Optimizer

Optimizes mean-reversion trading strategy parameters through real-time performance analysis and pattern identification.