anndata

Manage annotated data matrices for single-cell genomics using the AnnData Python package.

1|Updated Mar 12, 2026
One-click install
npx skills add https://github.com/yf8578/clawomics --skill anndata-yf8578
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: anndata
Source: https://github.com/yf8578/clawomics/tree/main/skills/anndata
Command: npx skills add https://github.com/yf8578/clawomics --skill anndata-yf8578

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a standardized and efficient way to handle annotated data matrices, particularly for single-cell genomics, enabling seamless data manipulation and integration within the scverse ecosystem.

Core Features & Use Cases

  • Data Structure: Efficiently store and access experimental measurements (X) alongside observation (obs) and variable (var) metadata.
  • I/O Operations: Read and write data in various formats (h5ad, zarr, CSV, etc.) with support for large datasets and backed mode.
  • Data Manipulation: Subset, filter, concatenate, and transform AnnData objects.
  • Ecosystem Integration: Works seamlessly with tools like Scanpy for downstream analysis.
  • Use Case: Load a large single-cell RNA-seq dataset, filter cells based on quality metrics, normalize counts, identify highly variable genes, and save the processed data.

Quick Start

Load the AnnData object from 'data.h5ad' and print its shape.

Frequently Asked Questions about anndata

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

FAQPage Schema
How do I store single-cell genomics data with observation and variable metadata?

Single-cell genomics data is stored using an annotated data matrix structure that holds experimental measurements in X alongside observation (obs) and variable (var) metadata for integrated analysis.

Can I read and write large h5ad datasets for single-cell analysis?

Yes, you can read and write large single-cell datasets in formats like h5ad and zarr. It supports a backed mode to efficiently handle large-scale experimental data without loading everything into memory.

What is the best way to filter and normalize single-cell RNA-seq data matrices?

The best way to filter and normalize single-cell RNA-seq data is by using annotated data matrices to subset cells based on quality metrics, transform counts, and save processed results.

Does this annotated data matrix format work with Scanpy for downstream scverse workflows?

Yes, this annotated data matrix format integrates seamlessly with the scverse ecosystem, including Scanpy, enabling smooth transitions to downstream analysis workflows like normalization and clustering.

What file formats are supported for importing and exporting annotated data matrices?

Supported file formats for importing and exporting annotated data matrices include h5ad, zarr, and CSV, providing flexible I/O operations for single-cell genomics experimental data.

How do I concatenate multiple single-cell datasets into one matrix?

You can concatenate multiple single-cell datasets by using annotated data matrix manipulation functions to merge observations, variables, and layers across different experimental batches.