2,000+ deep skill bundles for AI bioinformatics agents

Poetry is the Python dependency management and packaging tool for creating reproducible projects with pyproject.toml and poetry.lock. Use this skill for dependency resolution, virtual environment isol

Direct REST API access to UniProt (250M+ protein sequences, 570K+ reviewed Swiss-Prot entries). Protein search, FASTA/JSON retrieval, ID mapping across 200+ databases, batch retrieval, streaming, fiel

Use when working with CVXPY — a Python-embedded domain-specific language for convex optimization problems. Covers problem construction with the DCP (Disciplined Convex Programming) ruleset, all built-

xorca (eXtensible ORCA Grid Adapter) preprocesses NEMO ocean model NetCDF outputs into XGCM-compatible Xarray datasets for grid-aware operations on curvilinear ORCA grids. Use when working with NEMO s

DBSCAN (Density-Based Spatial Clustering of Applications with Noise) — fast C++ implementation of density-based clustering algorithms in R. Includes DBSCAN, HDBSCAN, OPTICS/OPTICSXi, LOF outlier detec

wateRmelon v2.16.0 — Bioconductor R package for Illumina 450K and EPIC DNA methylation array normalization and performance metrics. Provides 15 normalization methods (dasen, nasen, naten, danes, swan,

HDMT — High-Dimensional Mediation Testing for joint significance of exposure-mediator and mediator-outcome associations. Controls FWER and FDR for mediation hypotheses in high-dimensional settings (ep

Use when working with aurora — a machine learning GWAS R package for identifying microbial habitat adaptation genes and autochthonous strain provenance. Implements a Random Forest + random-walk (AUtoc

SeSAMe (SEnsible Step-wise Analysis of DNA MEthylation BeadChips) — R/Bioconductor package for processing Illumina Infinium DNA methylation arrays. Supports EPIC, EPICv2, HM450, HM27, MM285, and Mamma

xESMF — Regrid geospatial and climate datasets between structured grids using ESMF (Earth System Modeling Framework). Use when working with climate model output (CMIP6, ERA5, CESM), satellite data, or

fdrtool — estimation of tail area-based false discovery rates (Fdr/q-values) and density-based local false discovery rates (fdr) from observed test statistics. Supports four null models: normal (z-sco

Zarr — chunked, compressed N-dimensional arrays for Python with cloud-native storage. Provides hierarchical groups, pluggable compression codecs (Blosc, Zstd, Gzip), sharding for large-scale datasets,

JM / JMbayes2 — Joint models for longitudinal and time-to-event data under the Bayesian framework. Fits shared-parameter joint models via jm() linking mixed-effects longitudinal submodels (lme, mixed_

qvalue — Q-value estimation for false discovery rate control in multiple hypothesis testing. Estimates q-values, the proportion of true null hypotheses (pi0), and local false discovery rates from vect

Stan — probabilistic programming language for Bayesian statistical modeling and high-performance inference. Full Bayesian inference via No-U-Turn Sampler (NUTS/HMC), approximate inference via Automati

Uni-Mol universal 3D molecular representation learning framework for molecular property prediction, protein-ligand docking, drug-target interaction, and binding affinity scoring. Covers unimol_tools P

PubMed Database — NCBI's comprehensive biomedical literature database providing free access to over 37 million citations from MEDLINE, life science journals, and online books. Query via E-utilities RE

GEO Database — NCBI Gene Expression Omnibus public repository for high-throughput gene expression and functional genomics data. Contains 264,000+ series (GSE), 8M+ samples (GSM), 27,000+ platforms (GP

PyStan — Python interface to Stan for Bayesian statistical modeling and high-performance inference. Compile Stan programs (stan.build), draw posterior samples via HMC-NUTS (model.sample), extract draw