scanpy

Automate single-cell RNA-seq analysis with Scanpy from QC to marker genes.

Updated Apr 19, 2026
One-click install
npx skills add https://github.com/CHENyiru3/AI-Skills-Collections --skill scanpy-chenyiru3
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: scanpy
Source: https://github.com/CHENyiru3/AI-Skills-Collections/tree/main/skills-market/compbio/single-cell/analysis/scanpy
Command: npx skills add https://github.com/CHENyiru3/AI-Skills-Collections --skill scanpy-chenyiru3

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires scanpy, matplotlib, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

QC, normalization, dimensionality reduction, clustering, and interpretation of single-cell RNA-seq data via a scalable, reproducible Scanpy-based pipeline that turns raw counts into insights and publication-ready visuals.

Core Features & Use Cases

  • End-to-end Scanpy pipeline covering QC metrics, normalization, highly variable gene selection, PCA, UMAP/t-SNE, Leiden clustering, marker gene identification, and basic trajectory analysis.
  • Flexible input formats: supports h5ad, 10X, CSV, and other common single-cell data formats.
  • Reproducible research with bundled references (standard workflow, API reference, plotting guide) and templates (assets) to accelerate analyses.

Quick Start

Load your AnnData object and run the end-to-end Scanpy workflow to generate QC metrics, normalization, HVG selection, dimensionality reduction, clustering, and cell-type annotations.

Frequently Asked Questions about scanpy

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

FAQPage Schema
How do I run an end-to-end single-cell RNA-seq analysis workflow from raw counts to clustering?

Single-cell RNA-seq analysis can be automated end-to-end using Scanpy to deliver QC metrics, normalization, HVG selection, PCA, UMAP, Leiden clustering, and marker gene identification from raw counts.

What input formats are supported for loading scRNA-seq data into a Scanpy pipeline?

The Scanpy pipeline supports loading diverse scRNA-seq data formats including h5ad, 10X, and CSV files to generate a processed AnnData object for downstream analysis.

Does the Scanpy workflow support trajectory inference and cell type annotation?

Yes, the Scanpy workflow supports trajectory inference and cell type annotation, extending beyond standard dimensionality reduction and clustering to interpret cellular development and identify specific cell populations.

How do I generate publication-ready visualizations from an AnnData object after clustering?

You can generate publication-ready visualizations directly from a processed AnnData object using the bundled plotting templates and Scanpy's matplotlib-based plotting guide to visualize UMAP, t-SNE, and marker genes.

What is the best way to ensure reproducible scRNA-seq clustering and dimensionality reduction?

To ensure reproducible scRNA-seq clustering and dimensionality reduction, use a standardized Scanpy pipeline that bundles references, templates, and metadata exports to consistently reproduce QC, normalization, and UMAP results.

Do I need matplotlib to visualize highly variable genes and UMAP plots in Scanpy?

Yes, matplotlib is required as a dependency to render highly variable gene plots, UMAP embeddings, and other publication-ready visualizations within the Scanpy single-cell RNA-seq analysis pipeline.