anndata

Organize single-cell expression matrices with annotations in AnnData objects.

1|Updated Mar 4, 2026
One-click install
npx skills add https://github.com/Hung-3008/agusta --skill anndata-hung-3008
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: anndata
Source: https://github.com/Hung-3008/agusta/tree/main/.agents/skills/anndata
Command: npx skills add https://github.com/Hung-3008/agusta --skill anndata-hung-3008

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AnnData provides a compact, flexible data structure to store a gene expression matrix X together with rich annotations (obs, var, layers, obsm, varm, uns) for single-cell experiments, enabling seamless integration and scalable analysis.

Core Features & Use Cases

  • Manage annotated data matrices (X, obs, var, layers) for scRNA-seq workflows.
  • Read/write to common formats (h5ad, zarr); perform concatenation, subsetting, and manipulation.
  • Integrate with Scanpy and the broader scverse ecosystem for preprocessing, clustering, and visualization.

Quick Start

Create and manipulate AnnData objects to organize your single-cell experiments and metadata.

Frequently Asked Questions about anndata

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

FAQPage Schema
How do I store scRNA-seq expression matrices with gene and cell metadata in one object?

AnnData organizes scRNA-seq expression matrices by linking matrix X with obs, var, layers, and embeddings in a unified object, enabling seamless integration and scalable analysis for single-cell experiments.

What is the best way to read and write h5ad files for single-cell data preprocessing pipelines?

Reading and writing h5ad files is handled by AnnData objects, which support common formats including zarr to perform concatenation, subsetting, and manipulation across preprocessing, clustering, and visualization pipelines.

Can I use backed storage for large scRNA-seq datasets to keep memory usage low?

Backed storage is supported for large scRNA-seq datasets, providing memory-efficient storage options that keep memory usage low while maintaining robust metadata management and validation.

Does AnnData integrate with Scanpy and the broader scverse ecosystem for clustering workflows?

AnnData integrates with Scanpy and the broader scverse ecosystem, allowing you to apply annotated data objects directly in preprocessing, clustering, and visualization workflows.

How do I concatenate and subset annotated single-cell data across different formats?

Concatenating and subsetting annotated single-cell data is performed within the AnnData object, supporting manipulation across formats such as h5ad and zarr to merge multiple experiments.

Why use a unified annotated data structure instead of separate matrices for single-cell analysis?

A unified annotated data structure links the expression matrix X with rich annotations like obs, var, layers, and uns, solving the problem of scattered metadata and ensuring robust ecosystem compatibility.