Tooluniverse Single Cell

This handles scanpy/anndata workflows for single-cell RNA-seq, from h5ad loading through clustering and differential expression. The skill emphasizes checking for pre-computed results first (executed notebooks, existing CSVs) before rerunning analysis, which matters because reanalysis from raw data produces different numbers and burns through turns. It includes statistical rigor reminders (normalization, multiple testing correction), a decision tree for when to use scanpy DE versus pseudo-bulk DESeq2, and integration with ToolUniverse for searching datasets in CELLxGENE, GEO, and SRA. The workflow coverage is comprehensive: QC, PCA, UMAP, Leiden clustering, marker identification, batch correction with Harmony, and correlation analysis. Good for anyone doing routine scRNA-seq work who wants structured guidance without reinventing the wheel.

skills.sh installs: 342
GitHub stars: 1.8K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add mims-harvard/tooluniverse --skill tooluniverse-single-cell --agent claude-code

Installs into .claude/skills of the current project.

Files

Single-Cell Genomics and Expression Matrix Analysis

RULE ZERO — Check for pre-computed results FIRST

Before following any instruction below, scan the data folder for:

*_executed.ipynb → read with tu run read_executed_notebook '{"data_folder":"<path>","search":"<keyword>"}' and cite its cell outputs as the authoritative answer
Pre-computed result files (CSV/TSV with names like *results*, *deseq*, *enrich*, *stats*, *_simplified.csv) → read directly and report the requested value
Canonical analysis scripts (analysis.R, run_*.py, find_*.R, *.Rmd) → execute as-is and read the output

Only follow this skill's re-analysis recipe below if none of the above exist. Re-running from raw data produces different numbers than the published answer and is much slower (often 5-10× turn count).

Comprehensive single-cell RNA-seq analysis and expression matrix processing using scanpy, anndata, scipy, and ToolUniverse.

LOOK UP, DON'T GUESS

When uncertain about any scientific fact, SEARCH databases first (PubMed, UniProt, ChEMBL, ClinVar, etc.) rather than reasoning from memory. A database-verified answer is always more reliable than a guess.

SKILL.md on GitHub