Quality control, filtering, normalization, and feature selection for spatial transcriptomics data. Calculate QC metrics, filter spots/cells, normalize counts, and identify highly variable genes.
SkillScore86Maintained
Automatic
◆Research pack
Last verified 8/2/2026
What it changes
Passed 19 of 22 test cases with the skill, and 17 of 22 without it.
Without skill77%
With skill86%
Checks it passed that the model alone missed
Uses min_genes=200 in sc.pp.filter_cells
Uses min_counts=500 in sc.pp.filter_cells
Uses sq.read.visium to load the spatial dataset
and 6 more in the full report
4 fixed15 passed either way1 still failing2 broke
Pass-rate lift
+9 pp
Tokens
+41%
Agent turns
0%
Response time
-41%
Model gemini-3.6-flashMeasured 8/2/2026v119 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 4
Prompt
I have computed highly variable genes and Moran's I spatial autocorrelation in my AnnData object. Write Python code to create a union set of all HVGs and the top 500 spatial genes, then subset the dataset.
What was checked, without and with the skill
Checked
Without skill
With skill
Retrieves top 500 spatial genes from adata.uns['moranI'] using head(500)
Missed
Passed
Combines HVG set and top SVG set using set union operation
Passed
Passed
Subsets AnnData object using the combined gene list
Passed
Passed
case-13 · gemini-3.6-flash · 8/2/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md221 linessingle file
Spatial Preprocessing
QC, filtering, normalization, and feature selection for spatial data.
Required Imports
import squidpy as sq
import scanpy as sc
import numpy as np
import matplotlib.pyplot as plt