Browse Tools

IRanges — core Bioconductor infrastructure for integer range and interval data manipulation in R. Create, manipulate, and query IRanges and GRanges objects for genomic interval arithmetic. Use for fin

JAGS (Just Another Gibbs Sampler) — program for Bayesian hierarchical model analysis via Markov Chain Monte Carlo (MCMC) simulation using the BUGS language dialect. Supports Gibbs sampling, slice samp

KIN — kinship inference for ancient DNA genomes using the DReichLab/EIG toolkit (EIGENSOFT). Estimates biological relatedness between ancient individuals from pseudo-haploid or diploid genotype data i

Use this skill when building interactive web maps in R with the leaflet package. Covers core map construction with leaflet(), addTiles(), addProviderTiles(), addMarkers(), addCircleMarkers(), addPolyg

Leafmap is a Python package for interactive mapping and geospatial analysis in Jupyter environments with minimal code. Use this skill when users ask for `leafmap.Map`, backend selection (`leafmap`, `l

Use when working with libRoadRunner (Python module: roadrunner) for SBML model simulation and analysis, including deterministic ODE integration (CVODE, rk4, rk45), stochastic simulation (gillespie), s

linearmodels — panel data models, instrumental variable (IV) estimators, system estimators (SUR, 3SLS), and linear factor models for econometrics and quantitative research in Python. Provides fixed ef

LitVar — biomedical literature mining for genetic variants. Search PubMed and PMC full-text articles for mentions of SNPs, indels, and other genetic variants by rsID, gene name, or HGVS notation. Retr

lme4 — R package for fitting linear, generalized linear, and nonlinear mixed-effects models using Eigen-based sparse matrix methods. Core functions: lmer() for linear mixed models (LMMs), glmer() for

Longshot is a diploid long-read SNV caller for aligned PacBio/ONT BAM or CRAM input, with optional genotyping/phasing from an input VCF and optional haplotype-tagged BAM output. Use this skill when us

The Matrix package for R provides a rich hierarchy of S4 classes for dense and sparse matrices. It enables efficient numerical linear algebra operations and is a foundational component of the R ecosys

mclust — R package for Gaussian finite mixture models fitted via EM algorithm providing model-based clustering (automatic cluster number and covariance structure selection via BIC/ICL across 14 parame

Use this skill for MEMOTE workflows on genome-scale metabolic models (GEMs), including SBML model preflight checks, ad hoc benchmark runs, HTML snapshot report generation, diff/history report routing,

MetaboLights is the EMBL-EBI open-access repository for metabolomics studies and reference spectra. Browse and download public metabolomics datasets (MTBLS accessions) via REST API or metabolights-uti

Use this skill for meteorological analysis with MetPy in Python: unit-aware calculations (`metpy.calc`), CF-aware xarray workflows (`.metpy.parse_cf()`), weather file I/O (`metpy.io`), and synoptic pl

Micromamba — fast, standalone conda-compatible package and environment manager built on libmamba (C++). Creates, activates, and manages isolated conda environments from conda-forge, bioconda, and cust

Use this skill for Minerva Story workflows in multiplexed tissue imaging, including exhibit.json validation, story/waypoint routing, channel-group consistency checks, local static preview with npx htt

MLflow — open-source platform for managing the full ML lifecycle: experiment tracking (parameters, metrics, artifacts), model registry (versioning, staging, production promotion), model serving (REST

MNE-BIDS — Python package for converting EEG, MEG, and iEEG (intracranial) electrophysiology data to the Brain Imaging Data Structure (BIDS) standard. Handles write_raw_bids() conversion, BIDSPath con

mofapy2 is a Python package implementing Multi-Omics Factor Analysis v2 (MOFA+) for unsupervised integration of multi-omics datasets. It identifies latent factors that capture sources of variation sha

MoleculeNet in DeepChem provides curated molecular machine learning dataset loaders for ADME, toxicity, quantum chemistry, materials, and reaction benchmarks through `deepchem.molnet.load_*` functions

MrBayes — Bayesian phylogenetic inference using MCMC. Accepts sequence alignments (NEXUS format) and performs Bayesian inference on evolutionary trees with posterior probability estimates. Supports DN

mzR routing skill for metabolomics and lipidomics raw mass spectrometry data parsing. Use this skill when users mention mzR, openMSfile, mzML parsing, mzXML reading, mzData, netCDF mass spec, ProteoWi

Noise2Void (N2V) is a self-supervised deep learning method for fluorescence microscopy image denoising that requires only noisy images — no clean ground truth needed. Uses a blind-spot convolutional n

Use when working with napari-spatialdata, the scverse napari plugin for interactive exploration and annotation of SpatialData .zarr datasets in spatial omics workflows. Covers CLI usage (`python -m na

NEB Tools is a suite of free online tools from New England Biolabs (NEB) for primer design, restriction enzyme selection, cloning strategy planning, and molecular biology workflow design. Key tools in

NEST (Neural Simulation Tool) — high-performance spiking neural network simulator for large-scale networks of point neurons and conductance-based models. Supports iaf_psc_alpha, hh_psc_alpha, aeif_con

Use when working with NeuroDSP for neural digital signal processing on EEG, LFP, or other electrophysiology time series. NeuroDSP provides filtering, burst detection, spectral analysis, aperiodic sign

NEURON — biophysically detailed multi-compartment neural simulation environment for modeling neurons and neural networks. Builds and runs Hodgkin-Huxley style conductance-based neuron models, morpholo

NewHybrids + hybriddetective — Bayesian hybrid detection and genotypic class assignment for population genomics. Classifies individuals as pure parental, F1 hybrids, F2 hybrids, or backcrosses using m

Use when working with nf-core/ampliseq — a reproducible Nextflow pipeline for amplicon sequencing analysis targeting 16S rRNA, ITS, 18S rRNA, and other custom amplicon regions. Takes paired-end or sin

nf-core/fetchngs — Nextflow pipeline for downloading and standardizing sequencing data from public repositories (SRA, ENA, DDBJ, GEO, Synapse). Fetches FASTQ files from accession IDs and generates nf-

Use when working with NGSadmix — admixture estimation from genotype likelihoods. Part of the ANGSD ecosystem; estimates individual ancestry proportions (Q-matrix) from BEAGLE GL files without calling

niffler — transparent compressed file I/O for Rust bioinformatics pipelines. Sniffs compression format from magic bytes using get_reader and from_path. Supports gzip, bzip2, xz/lzma, zstd, and BGZF (b

Numba — open-source JIT compiler for numerical Python using LLVM. Compiles Python functions to optimized machine code at runtime via @jit/@njit decorators. Supports automatic parallelization (parallel

Use when working with NumPy, ndarray-based numerical computing, array creation, vectorization, broadcasting, linear algebra, random sampling, or scientific file I/O in Python. NumPy provides the n-dim

Use when working with OBITools3 for DNA metabarcoding, environmental DNA, primer/tag demultiplexing, paired-end read assembly, dereplication, denoising, taxonomic assignment, or export from the OBIToo

OGER (OntoGene Entity Recogniser) — dictionary-based biomedical named entity recognition (NER) tool that annotates text using ontology resources including UniProt, MeSH, CTD, CRAFT, and ChEBI. Accepts

OGGM (Open Global Glacier Model) — modular open-source framework for simulating past and future glacier mass balance, volume, and geometry worldwide. Automates glacier-specific workflows from RGI outl

OHDSI Atlas — open-source web platform for observational health data analysis on OMOP Common Data Model (CDM) databases. Define cohorts using standardized vocabularies, run characterization studies, i

OMOP CDM (Observational Medical Outcomes Partnership Common Data Model) — standardized relational schema for observational health data (EHR, claims, registries). Enables federated network studies acro

OpenSlide for digital pathology whole-slide imaging (WSI): inspect vendor formats, read tiles/regions, generate thumbnails, and build Deep Zoom outputs from SVS/NDPI/SCN/MRXS/DICOM slides. Use when us

Use this skill when working with openslide-python for digital pathology and whole-slide imaging (WSI). Covers reading SVS/NDPI/MRXS/SCN/DICOM and other OpenSlide-supported formats, slide pyramids, met

OpenWetWare is an open wiki platform for sharing biological research protocols, lab notebooks, standard operating procedures (SOPs), and experimental methods. Use to discover and retrieve community-cu

Use this skill for base R numerical optimization with `stats::optim()` and `optimHess()`: unconstrained optimization (Nelder-Mead, BFGS, CG), box-constrained optimization (L-BFGS-B), simulated anneali

overlapSelect — UCSC Kent utilities command-line tool for filtering genomic records based on coordinate overlap. Selects (or excludes) records from a BED, PSL, genePred, or tab-delimited input file wh

PacBio (Pacific Biosciences) is a company that develops and manufactures systems for gene sequencing. This skill provides tools to work with PacBio data.

Use when building interactive dashboards, data apps, or reactive tools with Panel in Python. Covers notebook and script workflows, widget binding with pn.bind, template-based app layouts, and deployme

Pangu-Weather — AI-based global weather forecasting with 3D neural networks. Predicts atmospheric conditions at 0.25° resolution (~28 km) for lead times of 1, 3, 6, and 24 hours using Earth-Specific T

Compose multiple ggplot2 plots into multi-panel figures using patchwork. Use this skill for side-by-side, stacked, nested, or annotated figure layouts in R. Trigger when users ask about combining ggpl