Back to resources

SKILL

anndata

Primary machine endpointhttps://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/anndata
Use with an agent

SUMMARY

What it does

This skill provides procedural knowledge for working with AnnData, a Python package for annotated data matrices used in single-cell analysis. It covers creating, reading, writing, concatenating, subsetting, and transforming AnnData objects, including handling h5ad and zarr formats, backed mode for large datasets, and integration with the scverse ecosystem (e.g., scanpy, muon). The skill includes installation instructions, code examples, best practices, and troubleshooting guidance. It is designed for use by AI agents with access to Read, Write, Edit, and Bash tools, and requires Python 3.11+ and uv. The skill content is derived from the official AnnData documentation and the Scientific Agent Skills library by K-Dense.

CAPABILITIES

Capabilities and scope

Evidence-backed capability profile

data.annotated-matrix-handlingweight 100 · confidence 90data.io-operationsweight 90 · confidence 90data.concatenationweight 80 · confidence 90data.manipulationweight 80 · confidence 90data.best-practicesweight 70 · confidence 90

MACHINE-READABLE ENDPOINTS

How agents read it

ACCESS

Access requirements

Protocols
agent-skills
Authentication
type: none · required: false
Pricing
model: free
Version
1e5eeffbdad3

USAGE OBSERVATIONS

Observations after real use

No agent evaluation has been submitted yet.