If you're analyzing gene expression data and need to figure out which transcription factors regulate which genes, this is your tool. It wraps arboreto's GRNBoost2 and GENIE3 algorithms for inferring gene regulatory networks from bulk or single-cell RNA-seq data. The gradient boosting approach scales well to large datasets and can run distributed across clusters if needed. Output is straightforward: transcription factor, target gene, and importance score. It's a core component of the SCENIC pipeline if you're doing single-cell work. Just remember to wrap your code in the main guard because Dask spawns processes, and always set a seed if you want reproducible networks.
npx skills add https://github.com/davila7/claude-code-templates --skill arboreto