Data Science & ML Agent Skills

MarkItDown Converter

Converts diverse file formats including PDFs, Office documents, and media into LLM-optimized Markdown for AI processing.

PufferLib High-Performance RL

Accelerates reinforcement learning development with high-speed parallel environment simulation and optimized PPO training.

Zarr Python Array Management

Manages large-scale N-dimensional arrays with efficient chunking, compression, and cloud-native storage integration.

Statsmodels Statistical Analysis

Performs rigorous statistical modeling, econometric analysis, and hypothesis testing using Python's premier inference toolkit.

Bioinformatics Query Toolkit (gget)

Provides unified, high-speed access to 20+ genomic databases and protein structure prediction tools directly from the command line.

scvi-tools for Single-Cell Analysis

Analyzes single-cell omics data using deep generative models and probabilistic frameworks for batch correction and multimodal integration.

Transformers Model Integration

Implements and fine-tunes state-of-the-art machine learning models for natural language processing, computer vision, and audio tasks.

ESM Protein Language Models

Powers protein engineering workflows with state-of-the-art generative design, structure prediction, and high-quality sequence embeddings.

ENA Bioinformatics Database

Accesses and retrieves nucleotide sequence data, raw reads, and genome assemblies from the European Nucleotide Archive.

HMDB Database Access

Accesses the Human Metabolome Database (HMDB) to retrieve detailed information on over 220,000 human metabolites, including chemical properties, clinical biomarkers, and spectral data.

NCBI Gene Database Connector

Queries and retrieves comprehensive genetic data from NCBI using E-utilities and Datasets APIs for biological research and gene annotation.

SymPy Symbolic Math

Performs exact symbolic mathematics, calculus, and algebraic computations in Python to provide precise mathematical results.

ZINC Chemical Database

Accesses the ZINC repository of 230M+ purchasable compounds for virtual screening, drug discovery, and molecular property analysis.

STRING Database & Protein Analysis

Queries the STRING API to analyze protein-protein interaction networks and perform functional enrichment for systems biology.

PubMed Database Access

Facilitates advanced biomedical literature research and programmatic access to the National Library of Medicine's PubMed database via E-utilities.

SimPy Discrete-Event Simulation

Builds and manages process-based discrete-event simulations in Python to model complex systems like manufacturing, logistics, and network traffic.

ChEMBL Bioactivity Database

Accesses ChEMBL's vast repository of bioactive molecules and drug discovery data for medicinal chemistry and pharmacology research.

ClinPGx Database

Provides programmatic access to comprehensive pharmacogenomics data for precision medicine, clinical guidelines, and gene-drug interaction analysis.

PyTorch Geometric (PyG)

Develops and trains Graph Neural Networks (GNNs) for complex data structures like social networks, molecules, and 3D point clouds.

CELLxGENE Census Genomics

Provides programmatic access to standardized single-cell genomics data for large-scale analysis and machine learning.

LabArchives Integration

Automates electronic lab notebook workflows by managing entries, attachments, and backups through the LabArchives REST API.

PubChem Database Explorer

Accesses and queries the world's largest chemical database for compound information, molecular properties, and bioactivity data.

Seaborn Statistical Visualization

Generates publication-quality statistical graphics and exploratory data visualizations using the Seaborn Python library.

Aeon Time Series ML

Simplifies complex time series machine learning tasks including forecasting, classification, and anomaly detection using a scikit-learn compatible toolkit.

BioRxiv Research Database

Searches and retrieves metadata and full-text PDFs from the bioRxiv preprint server for life sciences research discovery.

Gtars Genomic Data Analysis

Analyzes and processes high-performance genomic interval data for computational biology and machine learning workflows.

Pydicom Medical Imaging

Processes medical imaging data in the DICOM standard format for healthcare applications and radiology workflows.

PyMC Bayesian Modeling

Builds, fits, and validates Bayesian statistical models using PyMC and ArviZ for probabilistic programming.

AlphaFold Database Access

Accesses and analyzes over 200 million AI-predicted protein structures from the AlphaFold DB for drug discovery and structural biology research.

Ensembl Genomic Database Integration

Accesses and analyzes comprehensive vertebrate genomic data from the Ensembl REST API for over 250 species.