Data Science & ML Agent Skills

Scientific Critical Thinking

Evaluates research rigor and methodology through systematic assessment of statistical validity, biases, and evidence quality.

Machine Learning Feature Engineering

Optimizes machine learning model performance by automating feature creation, selection, and complex data transformations.

RDKit Cheminformatics

Provides comprehensive tools for molecular analysis, chemical property calculation, and 3D structure generation within scientific research workflows.

Matchms Mass Spectrometry Analysis

Processes, filters, and analyzes mass spectrometry data for metabolomics research and chemical identification.

Google Gemini Integration

Integrates Google Gemini's advanced coding models into Claude Code for high-context refactoring, deep analysis, and automated file editing.

Pysam Genomic Data Toolkit

Processes and analyzes genomic data formats including BAM, VCF, and FASTA using a Pythonic interface to htslib.

ClinVar Database Assistant

Queries and interprets NCBI ClinVar data to provide standardized genetic variant classifications and clinical significance evidence.

Qiskit Quantum Computing

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

Histolab Pathology Processing

Automates digital pathology image processing and tile extraction for whole slide images in deep learning pipelines.

Quantitative Risk Metrics

Calculates advanced portfolio risk metrics including VaR, CVaR, and risk-adjusted returns for quantitative trading and financial analysis.

Plotly Visualization

Generates interactive, publication-quality scientific and statistical visualizations using the Plotly Python library.

Excel & Data Spreadsheet Toolkit

Creates, edits, and analyzes Excel spreadsheets with production-grade formulas, formatting, and rigorous error validation.

Scientific Resource Detector

Detects system hardware capabilities to provide strategic recommendations for computationally intensive scientific tasks.

Automated Data Preprocessing

Automates the cleaning, transformation, and validation of raw data into high-quality datasets for machine learning and analysis.

AnnData Single-Cell Data Management

Manages annotated data matrices and biological datasets using the AnnData framework in Python.

QuTiP Quantum Simulations

Simulates and analyzes closed and open quantum mechanical systems using the Quantum Toolbox in Python.

OpenAlex Academic Research Database

Queries and analyzes over 240 million scholarly works, authors, and institutions via the OpenAlex API for comprehensive bibliometric research.

Metabolomics Workbench Database

Connects Claude to the NIH Metabolomics Workbench for comprehensive access to metabolite data, study metadata, and mass spectrometry search capabilities.

Senior Prompt Engineering

Optimizes LLM performance through advanced prompt design, agentic system architecture, and rigorous evaluation frameworks.

BioGeoBEARS Biogeographic Analysis

Sets up and executes probabilistic inference of ancestral geographic ranges on phylogenetic trees using BioGeoBEARS in R.

ML Experiment Tracking Setup

Automates the configuration and integration of MLflow and Weights & Biases to streamline machine learning experiment management.

PyTorch Lightning ML Framework

Organizes and scales PyTorch code into modular, high-performance deep learning workflows with minimal boilerplate.

Opentrons Lab Automation

Automates laboratory liquid handling by generating Python Protocol API v2 scripts for Flex and OT-2 robots.

Prompt Optimizer

Optimizes Large Language Model prompts to minimize token usage, reduce operational costs, and enhance response quality.

Excel LBO Modeler

Builds professional-grade Leveraged Buyout (LBO) models in Excel for private equity analysis and transaction screening.

MedChem Molecular Triage

Applies medicinal chemistry rules and structural filters to prioritize and triage molecular libraries for drug discovery.

Pymatgen Materials Science Toolkit

Performs advanced materials analysis, crystal structure manipulation, and Materials Project database integration for computational scientists.

Deep Learning Optimizer

Optimizes deep learning models by refining architectures and training parameters to enhance accuracy and reduce resource consumption.

SymPy Symbolic Math

Performs exact symbolic mathematics in Python, including calculus, algebra, and complex equation solving.

Hyperparameter Tuner

Optimizes machine learning model performance by automatically searching for ideal hyperparameter configurations using advanced search strategies.