What is the scverse Claude Code skill?

It is a specialized capability that provides Claude with patterns and best practices for single-cell RNA-seq analysis using Python's scverse ecosystem, specifically focusing on AnnData and Scanpy.

Can I use it to visualize gene expression?

Absolutely. The skill provides standardized code for generating UMAP plots, violin plots, heatmaps, and dot plots to visualize both metadata and specific gene expression levels.

Is it compatible with 10x Genomics data?

Yes, it includes I/O patterns for reading various formats including 10x H5 files, MTX matrices, and H5AD files into AnnData objects.

Does this skill help with data quality control?

Yes, it includes patterns for calculating QC metrics, filtering low-quality cells, and identifying mitochondrial or ribosomal gene contamination.

Scverse Single-Cell Analysis

Name: Scverse Single-Cell Analysis
Author: CodingKaiser

byCodingKaiser

Data Science & ML

Streamlines single-cell RNA-seq analysis using standardized AnnData and Scanpy workflows.

About

The scverse skill provides expert patterns for single-cell transcriptomics analysis, focusing on the core Python ecosystem of AnnData and Scanpy. It enables Claude to assist with the entire bioinformatics pipeline, from initial data ingestion and quality control to complex dimensionality reduction and differential expression analysis. By providing domain-specific guidance on data structures and implementation patterns, this skill helps researchers and bioinformaticians maintain best practices while accelerating the exploration and visualization of large-scale cellular datasets.

Key Features

0 GitHub stars
Implementation of PCA, UMAP, and t-SNE dimensionality reduction
Publication-ready visualization patterns for markers and metadata
Comprehensive QC and preprocessing workflows for scRNA-seq
Efficient AnnData object manipulation, creation, and subsetting
Automated clustering using Leiden and Louvain algorithms

Use Cases

Developing end-to-end preprocessing pipelines for raw count matrices
Generating complex genomic visualizations like dot plots and heatmaps
Performing cell-type identification via marker gene analysis and clustering

About

Key Features

0 GitHub stars
Implementation of PCA, UMAP, and t-SNE dimensionality reduction
Publication-ready visualization patterns for markers and metadata
Comprehensive QC and preprocessing workflows for scRNA-seq
Efficient AnnData object manipulation, creation, and subsetting
Automated clustering using Leiden and Louvain algorithms

Use Cases

Developing end-to-end preprocessing pipelines for raw count matrices
Generating complex genomic visualizations like dot plots and heatmaps
Performing cell-type identification via marker gene analysis and clustering