Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

CELLxGENE Census Data Query

Query and analyze 200M+ cells of public single-cell and spatial transcriptomics data from the CZ CELLxGENE Census without downloading full datasets.

Data & AnalyticsAdvanced★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

The CZ CELLxGENE Census is a versioned, standardized collection of public single-cell and spatial transcriptomics data. This skill teaches Claude to use the cellxgene-census Python API correctly so you pull only the slice you need instead of whole datasets.

  • Filter on standardized metadata: cell type, tissue, disease, assay, donor
  • Fetch raw expression matrices into AnnData, or stream large slices out-of-core
  • List datasets, summary counts, and source H5AD download URIs
  • Access pre-computed embeddings and spatial Census data
  • Integrate with Scanpy and train PyTorch models via TileDB-SOMA-ML
  • Reproducibility best practices (pin census_version, filter is_primary_data == True) plus a troubleshooting section

Who it's for

  • Bioinformaticians and grad students working with scRNA-seq
  • Anyone building reference atlases by comparing many public datasets
  • ML engineers training cell-type classifiers at million-cell scale
  • Users who need public reference data (for your own local data, use scanpy/scvi-tools instead)

Examples

  1. "Show me the cell type composition of lung tissue" → metadata-only get_obs query followed by value_counts().
  2. "Compare CD4/CD8A expression in T cells from COVID-19 donors" → explore metadata first, then load a narrow AnnData slice and analyze with Scanpy.
  3. "How do macrophages differ across lung, liver, and brain?" → cross-tissue query plus rank_genes_groups for tissue-specific markers.

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/cellxgene-census folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/cellxgene-census/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

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

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and confirm you have Python 3.10–3.12 (python --version).
  2. Clone the repo: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r scientific-agent-skills/skills/cellxgene-census ~/.claude/skills/
  5. Install the library: uv pip install "cellxgene-census==1.17.*" (for spatial work: uv pip install "cellxgene-census[spatial]==1.17.*" "spatialdata[extra]>=0.2.5").
  6. Restart Claude Code and try a prompt like "Query lung cell types from the CELLxGENE Census".
  7. No authentication is needed for public Census data, but you do need network access and enough RAM for larger queries.
View source on GitHub ↗License: MIT