Data Science & ML Agent Skills

Dask Parallel Computing

Scales Python, pandas, and NumPy workflows across multiple cores or clusters for larger-than-memory datasets.

Data Commons Client

Accesses and queries global statistical data from Data Commons to provide programmatic insights into demographics, economics, and environmental indicators.

DrugBank Database Explorer

Accesses and analyzes comprehensive pharmaceutical data from DrugBank for drug discovery, pharmacology research, and safety analysis.

Datamol Cheminformatics

Simplifies molecular cheminformatics workflows by providing a Pythonic wrapper around RDKit with sensible defaults and parallel processing.

Plotly Interactive Data Visualization

Generates interactive, publication-quality scientific and statistical charts using Plotly Express and Graph Objects.

Pysam Genomic Toolkit

Processes and analyzes genomic datasets including SAM, BAM, VCF, and FASTA files using a Pythonic interface to htslib.

DeepChem Molecular ML

Facilitates molecular machine learning and drug discovery workflows using the DeepChem toolkit.

PennyLane Quantum Computing

Enables building, training, and optimizing quantum circuits and hybrid quantum-classical machine learning models with automatic differentiation.

STRING Protein Database Integration

Retrieves and analyzes protein-protein interaction networks and functional enrichment data directly from the STRING database.

DNAnexus Integration

Integrates Claude with the DNAnexus cloud genomics platform to develop bioinformatics pipelines, manage data, and orchestrate workflows.

Matchms Spectrometry Analysis

Processes and analyzes mass spectrometry data using Python for metabolomics and chemical identification.

Pydicom Medical Imaging

Processes, modifies, and analyzes DICOM medical imaging files using the pydicom library.

Ensembl Genome Database

Queries the Ensembl REST API to retrieve gene annotations, sequences, variants, and comparative genomic data for over 250 species.

ETE Toolkit Phylogenetic Analysis

Manipulates, analyzes, and visualizes phylogenetic trees with advanced support for evolutionary event detection and NCBI taxonomy integration.

GEO Database Access

Integrates with the NCBI Gene Expression Omnibus (GEO) to search, download, and analyze high-throughput functional genomics datasets.

LatchBio Integration

Builds and deploys bioinformatics workflows using the Latch SDK and serverless cloud infrastructure.

Scientific Exploratory Data Analysis

Performs comprehensive exploratory data analysis on over 200 scientific file formats to generate detailed quality reports and statistical summaries.

FDA Regulatory Data Access

Queries and analyzes openFDA data for drugs, medical devices, food safety, and adverse events using a standardized Python interface.

PyDESeq2 Differential Expression

Performs robust differential gene expression analysis for bulk RNA-seq data using the Python implementation of DESeq2.

FluidSim CFD Framework

Simulates complex fluid dynamics using high-performance Python pseudospectral methods and solvers for Navier-Stokes and geophysical flows.

Gene Database

Queries the NCBI Gene database to retrieve comprehensive genomic information, including sequences, annotations, and functional data.

GeoPandas Geospatial Analysis

Extends pandas with geometric operations and spatial data structures for advanced geospatial analysis and mapping.

Scientific Compute Resource Analyzer

Detects and analyzes system hardware to provide optimized strategic recommendations for scientific computing and data processing tasks.

gget Bioinformatics Toolkit

Enables rapid bioinformatics queries and sequence analysis across 20+ genomic databases directly from your terminal or Python scripts.

Genomic Tools and Analysis in Rust (Gtars)

Provides high-performance tools for genomic interval analysis, interval overlap detection, and machine learning tokenization using Rust.

Histolab Digital Pathology

Processes whole slide images (WSI) for digital pathology by automating tissue detection and tile extraction for machine learning pipelines.

Hypogenic Scientific Hypothesis Generator

Automates scientific hypothesis generation and testing by combining observational data with literature-based insights using large language models.

LaminDB Biological Data Management

Manage, validate, and trace biological datasets using a FAIR-compliant data framework and standardized biological ontologies.

PyHealth AI Toolkit

Develops, tests, and deploys healthcare-specific machine learning models using clinical data and electronic health records.

UMAP-Learn

Simplifies high-dimensional data visualization and preprocessing using the Uniform Manifold Approximation and Projection (UMAP) algorithm.