anndata

Works with .h5ad annotated matrix files for single-cell data in the scverse ecosystem.

Works with setup

Test report

Verdict
Works with setup
Score
7.6/10
Tested
Jul 11, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Aug 10, 2026 · fb8a68e

Verbatim install (git clone + cp) works cleanly; SKILL.md frontmatter parses as strict YAML with all 5 referenced files present, and every documented API (AnnData construction, ad.concat, sparse conversion, h5ad backed-mode I/O, zarr settings) runs correctly against the real anndata package. On an A/B build-and-filter-an-AnnData task the skill and base arms produced functionally identical, correct, idiomatic scripts (both dropped the all-zero cell, both wrote/reloaded h5ad in backed mode) so the skill added no measurable output advantage on this task. Requires the anndata Python package installed (pip install anndata); no API keys or external services needed.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 4/5
  • Output vs. baseline 5/10
  • Docs & honesty 5/5

What anndata does

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

How to install anndata

git clone https://github.com/K-Dense-AI/scientific-agent-skills
cd scientific-agent-skills
mkdir -p ~/.claude/skills
cp -r skills/anndata ~/.claude/skills/anndata

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger anndata

  • /anndata Works with .h5ad annotated matrix files for single-cell data in the scverse ecosystem.

It also activates on plain-language prompts like these:

  • Load and inspect this .h5ad single-cell dataset
  • Convert my single-cell data into an AnnData object
  • Subset this AnnData file by cell type

Frequently asked questions

Is the anndata skill free?
Yes. The skill itself is free from K-Dense-AI/scientific-agent-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does anndata work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 11, 2026. Verdict: Works with setup. Verbatim install (git clone + cp) works cleanly; SKILL.md frontmatter parses as strict YAML with all 5 referenced files present, and every documented API (AnnData construction, ad.concat, sparse conversion, h5ad backed-mode I/O, zarr settings) runs correctly against the real anndata package. On an A/B build-and-filter-an-AnnData task the skill and base arms produced functionally identical, correct, idiomatic scripts (both dropped the all-zero cell, both wrote/reloaded h5ad in backed mode) so the skill added no measurable output advantage on this task. Requires the anndata Python package installed (pip install anndata); no API keys or external services needed.
What is the anndata SkillProof Score?
7.6/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 5/10, docs & honesty 5/5.
How do I install anndata?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use anndata with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.