Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This skill library transposes the Bioconductor ecosystem into agent-readable tools, covering annotation with biomaRt, enrichment with clusterProfiler, epigenomics with ChIPseeker and minfi, and genomic infrastructure with GenomicRanges and Biostrings. It gives bioinformaticians, core facility staff, and computational biologists a way to run multi-omics analyses—from peak calling to pathway enrichment—without leaving the agent.
WHO IT'S FOR
Bioinformatics Core Facility Staff
supporting multi-omics analysis workflows
Computational Epigenomics Researchers
analyzing ChIP-seq, ATAC-seq, and methylation data
Functional Genomics and Pathway Analysts
performing gene set enrichment and pathway analysis
Genomic Data Scientists and Bioinformaticians
manipulating and visualizing genomic ranges and sequences
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Follow the documented setup, then try a first task.
Claude Code global — all skills
Installs: Global installation of the complete 200-package Bioconductor skill bundle. skillPaths is a bounded selection emphasizing the starter tasks; the documented command installs all skills found in the bundle. · Claude Code
Before you start
An existing local copy of the repository containing the skills/ directory
An existing ~/.claude/skills/ destination directory
Run from: Repository root
In a terminal, from the repository root, run the complete loop to copy every SKILL.md into Claude Code's global skills directory.
# Install all skills into Claude Code (global)
find skills -name "SKILL.md" | while read f; do
pkg=$(dirname "$f" | xargs basename)
cp "$f" ~/.claude/skills/bioconductor-${pkg}.md
done
A short character vector of lipid shorthand names, such as c("PC 32:1", "LPC 34:1")
Optional supported grammar name, such as "Goslin" or "LipidMaps"
Use the bioconductor-rgoslin skill to inspect the supported grammars, validate my supplied lipid shorthand names, and draft a small R example that parses the valid names into normalized names, monoisotopic masses, sum formulas, and LIPID MAPS classifications. Explicitly report any names that cannot be parsed. Use a specific grammar when I provide one; otherwise explain that the available parsers will be tried sequentially.
Either one local .cool, .mcool, or .hic file path, or both the .matrix and .bed file paths required for HiC-Pro input; /path/to/contact.cool is a placeholder
For focused .cool, .mcool, or .hic import, a target genomic locus such as I:20001-80000
File format and, for multiresolution files, optional requested resolution
Use the bioconductor-hicexperiment skill to draft a minimal R example that imports my local Hi-C contact matrix and inspects its resolution. For a .cool, .mcool, or .hic file, replace /path/to/contact.cool with my actual file path and replace I:20001-80000 with my target locus for focused import. If I provide HiC-Pro input instead, use both its .matrix and .bed files and fully import the matrix without the focus argument.
Read a multimodal H5MU file without loading it fully
Uses bioconductor-mudata
Path to a multimodal .h5mu file; /path/to/dataset.h5mu is a placeholder
Enough disk access to keep the backed matrices available
Use the bioconductor-mudata skill to draft a minimal R example that reads my multimodal .h5mu file into a MultiAssayExperiment with backed = TRUE, then briefly identifies the modalities available. Replace /path/to/dataset.h5mu with my actual file path. Do not perform downstream clustering or differential-expression analysis.
Claude
Goose