Browse Tools

SimBiology workflows in MATLAB for quantitative systems pharmacology (QSP), physiologically based pharmacokinetic (PBPK), and PK/PD modeling. Use this skill for SimBiology model construction, SBML imp

Use this skill for Slurm workload manager operations across HPC and cloud clusters, including sbatch job submission, srun interactive execution, squeue and sacct monitoring, resource request tuning, d

Smoldyn is a particle-based biochemical simulator for stochastic reaction-diffusion systems with explicit surfaces and compartments. Use this skill when users need spatial single-molecule simulation,

Tools for processing, parsing, and querying SNOMED CT RF2 release files and terminologies. Use for clinical coding, ontology mapping, RF2 extraction, and Snowstorm API interactions.

SoilGrids tools are a suite of tools for accessing and processing global soil information, providing data on soil properties, texture, and other characteristics for soil science and terrestrial ecolog

Use this skill for legacy and interoperability geospatial work in R using the `sp` package: constructing `Spatial*` classes, assigning coordinates with `coordinates()`, setting CRS metadata with `CRS(

Use when building or debugging Apache Spark and PySpark data pipelines on local, YARN, Kubernetes, or standalone clusters. Covers SparkSession, DataFrame and SQL transformations, partitioning, caching

SpatiaLite extends SQLite with OGC-style spatial SQL, geometry metadata tables, RTree spatial indexing, and import/export helpers for formats such as Shapefile, DBF, and GeoJSON. Use this skill when u

Use when working with spatstat (R) for spatial point pattern analysis, exploratory diagnostics, simulation, and point process model fitting. Routes tasks for ppp/owin data preparation, Kest/Gest/Fest/

Turn a SpatioTemporal Asset Catalog (STAC) into a dask-backed xarray DataArray. Use for Earth observation, remote sensing, geospatial data analysis, spatial ecology, and loading satellite imagery (Sen

Use this skill for R geospatial data-cube work with the stars package, including raster/NetCDF ingestion (`read_stars`, `read_ncdf`), lazy proxy workflows (`stars_proxy`), reprojection and warping (`s

svglib is a Python library and CLI for converting SVG and SVGZ graphics into ReportLab Drawing objects and PDF output. Use this skill when users ask to render SVG assets into PDFs for papers, convert

SWAT (Soil and Water Assessment Tool) — river basin-scale hydrological model for simulating water quantity and quality, sediment transport, nutrient cycling, and land management impacts. Covers waters

Use when working with tibble — the core tidyverse R package providing a modern reimagination of data.frame. Handles tidy data creation with tibble() and tribble(), type-safe subsetting, lazy column ev

timereg — flexible regression models for survival data in R. Additive hazards via aalen(), semiparametric Cox-Aalen models via cox.aalen(), competing risks regression via comp.risk() with Fine-Gray an

Use this skill when creating, configuring, and maintaining R packages with the usethis package. Routes tasks like package scaffolding, git/GitHub setup, testthat and CI configuration, DESCRIPTION/NAME

Route workflow linting and syntax checks for Nextflow DSL2, Snakemake, WDL, and CWL. Trigger phrases: validate-workflow-syntax, workflow validation, nextflow syntax, snakemake lint, wdl validate, cwl

ViennaRNA is a C/Python library and CLI suite for RNA secondary structure prediction, thermodynamic analysis, and non-coding RNA design. Core use cases: minimum free energy (MFE) folding with RNAfold,

Whitebox (WhiteboxTools) — geospatial-gis-tools for hydrological modeling, terrain derivatives, LiDAR processing, raster/vector analysis, and remote sensing workflows. Use this skill when users ask fo

Look up and manage taxonomic data from the World Register of Marine Species (WoRMS). This skill allows you to validate species names, retrieve taxonomic hierarchies, find synonyms, and query distribut

>

Dorado — Oxford Nanopore's official high-performance open-source basecaller that converts raw nanopore signal (POD5/FAST5) into nucleotide sequences. Replaces Guppy as the primary ONT basecaller. Supp

Ensembl Compara — comparative genomics database and API from EMBL-EBI providing pairwise and multiple whole-genome alignments, gene trees, protein families, orthologues, paralogues, and synteny region

Horvath clock — the foundational multi-tissue epigenetic age predictor using 353 CpG dinucleotide methylation sites and elastic net regression. Predict biological age from DNA methylation arrays (27K,

HostDB routing skill for host-pathogen genomics queries, gene expression analysis, ortholog searches, and comparative genomics on parasitic and tropical disease organisms. Use this skill when users me

Illumina sequencing operations routing skill for BCL Convert, DRAGEN, BaseSpace Sequence Hub, and Illumina Connected Analytics (ICA). Use when a user needs to inspect an Illumina run folder, fix or va

Use when working with LaminDB, the open-source data framework for biology that provides lineage-native data management, traceability, and validation for datasets and models. Covers LaminDB CLI and Pyt

Use this skill when working with Illumina PrimateAI-3D to score human missense variants, run the public PyTorch training/evaluation pipeline, and validate run outputs. Covers the current `primateAI-3D

PubAnnotation is a platform for storing, sharing, and querying biomedical text annotations on PubMed abstracts and PMC full-text articles. Retrieve named entity annotations (genes, diseases, chemicals

pyranges is a Python library for fast, intuitive manipulation of genomic intervals (BED, GTF, GFF3, BAM). Use when users need to compute overlaps, intersections, nearest features, or coverage from gen

SALEM — specialized Python library for geoscientific data processing and geolocalized operations. Extends xarray with masking, subsetting, and map plotting capabilities. Essential for climatology, met

Use when working with Severus for long-read structural variant calling, including tumor-only and tumor/normal somatic workflows, multi-sample tumor analysis, breakpoint-graph interpretation, and haplo

Terra — Broad Institute cloud platform for biomedical and genomics research on Google Cloud Platform. Supports WDL/Cromwell workflow execution, Jupyter notebook environments, Google Cloud Storage data

TRAPD — Toolkit for Rare variant Association from Population Data. Tests gene-level rare-variant burden in case-control studies using population databases (gnomAD, TOPMed) as controls. Implements adap

tskit is the tree-sequence toolkit for population genetics: it stores, analyzes, and converts genealogical data in the efficient .trees format used by msprime, SLiM, tsinfer, and other simulators. Use

VectorBase — NIAID Bioinformatics Resource Center for invertebrate vectors of human pathogens (mosquitoes, ticks, sandflies, tsetse flies, kissing bugs, and related arthropods). Provides genome assemb

BioContainers — community-driven registry of Docker and Singularity container images for bioinformatics tools. Provides reproducible, pre-built containers from Bioconda recipes via automated multi-bui

Use this skill when users need AWS Batch for containerized high-throughput compute jobs on AWS. Covers compute environments, job queues, job definitions, submit-job orchestration, array jobs, multi-no

ADMIXTURE for maximum likelihood estimation of individual ancestries from SNP genotype data. Use when working with admixture, ancestry estimation, population structure analysis, K selection via cross-

BEAGLE for genotype phasing and imputation from VCF files. Performs haplotype phase inference for genotyped variants, imputes ungenotyped markers using a reference panel, and estimates identity-by-des

Centrifuge is a rapid and memory-efficient metagenomic classifier for DNA sequences. Uses FM-index compression to classify reads against large reference databases including bacteria, archaea, viruses,

DPYD tools for pharmacogenomics analysis of dihydropyrimidine dehydrogenase variants. Supports star allele calling, diplotype-to-phenotype translation, and fluoropyrimidine (5-FU, capecitabine, tegafu

fastSTRUCTURE for variational Bayesian inference of population structure from SNP genotype data. Use when working with faststructure, fast structure, population structure analysis, variational Bayes a

Google Life Sciences (hpc-cloud) skill for routing genomic and bioinformatics workload execution through the Cloud Life Sciences API and adjacent Google Cloud services. Use this skill when users menti

inferCNV — R/Bioconductor package for inferring copy number variations (CNVs) from single-cell RNA-seq data by comparing tumor cell expression against a reference set of normal cells. Generates chromo

>

LDpred2 — Bayesian polygenic risk score (PRS) method implemented in R via the bigsnpr package. Computes polygenic scores from GWAS summary statistics using four models: LDpred2-inf (infinitesimal), LD

Use when performing Mendelian randomization (MR) analyses to estimate causal effects of exposures on outcomes using genetic variants as instrumental variables. Covers two-sample MR, IVW, MR-Egger, wei

METAL for genome-wide meta-analysis of genetic association studies. Combines GWAS summary statistics across cohorts using inverse-variance-weighted or sample-size-weighted fixed-effects schemes. Use w

Use when working with microfluidics, droplet microfluidics, lab-on-chip design, microfluidic flow control, digital PCR analysis, droplet-based single-cell encapsulation, chip layout generation, Fluige