Data Science & ML Agent Skills

Excel & Data Analysis Toolkit

Creates, edits, and analyzes Excel spreadsheets with production-grade formulas, formatting, and scientific visualizations.

KEGG Database Connector

Facilitates direct REST API access to the Kyoto Encyclopedia of Genes and Genomes for biological pathway analysis and molecular mapping.

NCBI Gene Database

Queries and retrieves comprehensive genomic data from NCBI Gene using E-utilities and Datasets APIs for scientific analysis.

OMERO Microscopy Integration

Integrates OMERO microscopy data management with Python for advanced image analysis, metadata handling, and automated screening workflows.

LabArchives Integration

Automates electronic lab notebook management through the LabArchives REST API for research documentation, data backups, and tool integration.

PyTorch Lightning

Streamlines deep learning development by organizing PyTorch code into scalable, modular structures for automated training and multi-GPU orchestration.

PyTorch Geometric (PyG) Graph Learning

Develop and train Graph Neural Networks using PyTorch Geometric for node classification, link prediction, and molecular modeling.

ZINC Chemical Database

Accesses the ZINC database of 230M+ purchasable compounds for virtual screening, drug discovery, and molecular docking studies.

Ensembl Genome Database Access

Facilitates automated queries to the Ensembl REST API for gene annotation, sequence retrieval, and comparative genomic analysis across 250+ species.

UniProt Protein Database

Provides direct REST API access to UniProt for protein sequence retrieval, identifier mapping, and comprehensive functional annotation searches.

Open Targets Database

Queries the Open Targets Platform to identify therapeutic drug targets and analyze disease-target associations using human genetics and omics data.

NCBI GEO Genomics Assistant

Accesses and processes NCBI Gene Expression Omnibus (GEO) data for transcriptomics and functional genomics research.

STRING Database Analysis

Accesses and analyzes protein-protein interaction networks and functional enrichment data using the STRING API.

Scientific Research Lookup

Conducts real-time academic research, literature reviews, and technical documentation lookups with automated model selection and proper citations.

Scientific Visualization

Generates publication-quality scientific figures and multi-panel layouts using Python libraries while adhering to journal-specific standards.

LatchBio Bioinformatics Integration

Builds and deploys serverless bioinformatics workflows using the Latch SDK and Registry.

DNAnexus Integration

Streamlines genomics pipeline development and data management on the DNAnexus cloud platform using the dxpy Python SDK.

Market Research Reports

Generates 50+ page, consulting-grade market research reports with professional LaTeX formatting and data-driven strategic frameworks.

Pysam Genomic Toolkit

Reads, manipulates, and writes genomic datasets including BAM, VCF, and FASTA files using a Pythonic interface to htslib.

PubChem Database Explorer

Queries the PubChem database to retrieve chemical properties, perform structure searches, and access bioactivity data for over 110 million compounds.

Scientific Hypothesis Generator

Formulates testable, evidence-based scientific hypotheses and experimental designs from observations and literature.

Scikit-bio (Biological Data Analysis)

Performs comprehensive biological data analysis including sequence manipulation, phylogenetics, and microbial ecology statistics.

BRENDA Enzyme Database

Accesses the comprehensive BRENDA enzyme database to retrieve kinetic parameters, biochemical reactions, and metabolic pathway data.

Zarr Python Scientific Computing

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

Metabolomics Workbench Database

Accesses the NIH Metabolomics Workbench API to retrieve metabolite structures, study metadata, and standardized chemical nomenclature for biomarker discovery.

Statsmodels Statistical Modeling

Performs rigorous statistical modeling, econometric analysis, and time series forecasting using the Statsmodels library.

HMDB Scientific Database

Accesses the Human Metabolome Database to retrieve chemical, clinical, and spectroscopic data for over 220,000 metabolites.

AlphaFold Database Tools

Accesses and analyzes over 200 million AI-predicted protein structures for bioinformatics and structural biology research.

ChEMBL Database & Drug Discovery

Queries the ChEMBL database to retrieve bioactive molecule data, drug targets, and bioactivity measurements for medicinal chemistry.

Qiskit Quantum Computing

Develops, optimizes, and executes quantum circuits and algorithms across various hardware backends using the Qiskit framework.