Scanpy cell type annotation starter

Skill ma-compbio-lab/SkillFoundry/skills/transcriptomics/scanpy-cell-type-annotation-starter

A framework for discovering, compiling, and validating reusable skills for scientific agents.

Install

npx -y skills add ma-compbio-lab/SkillFoundry --skill scanpy-cell-type-annotation-starter

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

1.4 KB, 333 tokens by cl100k_base, as published. Nobody here has run it

Scanpy Cell-Type Annotation Starter

Use this skill to score marker-gene programs with Scanpy and assign simple cell-type labels on a deterministic toy single-cell matrix.

What it does

Loads a small count matrix, marker sets, and optional truth labels.
Normalizes counts, log-transforms them, and applies scanpy.tl.score_genes.
Assigns the top-scoring label per cell and reports per-cell scores plus optional accuracy.

When to use it

You need a verified starter for marker-based cell-type annotation.
You want a compact example of scanpy.tl.score_genes before moving to larger reference-mapping workflows.
You need deterministic JSON output for tests or downstream demos.

Example

slurm/envs/scanpy/bin/python skills/transcriptomics/scanpy-cell-type-annotation-starter/scripts/run_scanpy_cell_type_annotation.py \
  --counts skills/transcriptomics/scanpy-cell-type-annotation-starter/examples/toy_counts.tsv \
  --markers skills/transcriptomics/scanpy-cell-type-annotation-starter/examples/toy_markers.json \
  --truth skills/transcriptomics/scanpy-cell-type-annotation-starter/examples/toy_truth.tsv \
  --summary-out scratch/scanpy-cell-annotation/summary.json

Verification