scverse-compact

Run a compact Scanpy single-cell RNA-seq workflow on an AnnData object.

6|1|Updated Nov 26, 2025

Search Tags:#UMAP #PCA #single-cell #clustering #QC #AnnData #Scanpy

Ready to run

npx skills add https://github.com/CodingKaiser/kaiser-skills --skill scverse-compact

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: scverse-compact
Source: https://github.com/CodingKaiser/kaiser-skills/tree/main/scverse-compact
Command: npx skills add https://github.com/CodingKaiser/kaiser-skills --skill scverse-compact

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a compact, end-to-end single-cell RNA-seq analysis workflow using Scanpy on an AnnData object.

Core Features & Use Cases

QC metrics computation and filtering for cells and genes
Normalization, log transformation, and highly-variable gene (HVG) selection
Dimensionality reduction (PCA, UMAP) and neighborhood graph construction
Clustering (Leiden) and marker gene ranking for identified clusters
Use Case: Quickly analyze a new scRNA-seq dataset to obtain a ready-to-interpret UMAP map with clusters and marker lists

Quick Start

Use the scverse-compact skill to run a compact single-cell workflow on a given AnnData object, performing QC, filtering, normalization, HVG selection, PCA, neighbors, UMAP, Leiden clustering, and marker gene ranking.

Frequently Asked Questions about scverse-compact

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I run a complete single-cell RNA-seq analysis workflow using Scanpy?▼

To run single-cell RNA-seq analysis using Scanpy, you need an AnnData object to execute a compact workflow covering QC, normalization, HVG selection, PCA, UMAP, Leiden clustering, and marker gene ranking.

What is the best way to generate UMAP and Leiden clusters from an AnnData object?▼

Generating UMAP and Leiden clusters from an AnnData object requires computing a neighborhood graph after PCA, which then enables UMAP dimensionality reduction and Leiden clustering for identifying distinct cell populations.

Can I use this Scanpy workflow for quality control and filtering of scRNA-seq data?▼

Yes, this Scanpy workflow handles quality control by computing QC metrics and performing filtering for both cells and genes, ensuring your scRNA-seq dataset is properly cleaned before normalization and downstream analysis.

Do I need a specific Python environment to perform dimensionality reduction and clustering on my single-cell data?▼

Yes, you need a Python environment with Scanpy and AnnData installed to perform dimensionality reduction, neighborhood graph construction, and Leiden clustering on your single-cell data for reproducible results.

How does marker gene ranking work after Leiden clustering in single-cell analysis?▼

Marker gene ranking in single-cell analysis identifies genes that distinguish each Leiden cluster, providing biological interpretation for the cell populations defined by the UMAP visualization and clustering steps.