Cellxgene census atlas query starter
Skill ma-compbio-lab/SkillFoundry/skills/transcriptomics/cellxgene-census-atlas-query-starter
A framework for discovering, compiling, and validating reusable skills for scientific agents.
npx -y skills add ma-compbio-lab/SkillFoundry --skill cellxgene-census-atlas-query-starterAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
1.1 KB, 275 tokens by cl100k_base, as published. Nobody here has run it
CELLxGENE Census Atlas Query Starter
Use this skill to search the public CELLxGENE Census dataset catalog by keyword and summarize the largest matching atlas datasets.
What it does
- Opens the public CELLxGENE Census SOMA catalog.
- Loads the canonical dataset metadata table.
- Filters dataset titles and collection names by a keyword such as
lung,PBMC, orTabula. - Reports top matches, unique collections, and aggregate cell counts.
When to use it
- You need a reproducible atlas-discovery entry point for multi-sample single-cell workflows.
- You want to shortlist large public Census datasets before deeper matrix queries.
Example
slurm/envs/census/bin/python skills/transcriptomics/cellxgene-census-atlas-query-starter/scripts/run_cellxgene_census_atlas_query.py \
--keyword "Tabula Sapiens" \
--limit 5 \
--out scratch/census/tabula_sapiens_query.json
Verification
- Skill-local tests:
python3 -m unittest discover -s skills/transcriptomics/cellxgene-census-atlas-query-starter/tests -p 'test_*.py' - Repository smoke:
python3 -m unittest tests.smoke.test_phase26_frontier_completion_skills -v