Visualize spatial transcriptomics data using Squidpy and Scanpy. Create tissue plots with gene expression, clusters, and annotations overlaid on histology images.
SkillScore91Maintained
Automatic
◆Research pack
Last verified 8/2/2026
What it changes
Passed 20 of 22 test cases with the skill, and 16 of 22 without it.
Without skill73%
With skill91%
Checks it passed that the model alone missed
Sets vmin=0 to ground the minimum expression level.
Calculates cluster centroid coordinates using .mean(axis=0).
Extracts spatial coordinates for each cluster from adata.obsm['spatial'][mask].
and 4 more in the full report
4 fixed16 passed either way2 still failing0 broke
Pass-rate lift
+18 pp
Tokens
+77%
Agent turns
0%
Response time
-40%
Model gemini-3.6-flashMeasured 8/2/2026v120 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
When displaying single-gene spatial expression heatmaps on Visium tissue slices using Scanpy, I want to set the maximum color threshold at the 99th percentile to prevent extreme outlier spots from washing out the color scale. What argument should I pass to sc.pl.spatial?
What was checked, without and with the skill
Checked
Without skill
With skill
Sets vmax='p99' in sc.pl.spatial.
Passed
Passed
Sets vmin=0 to ground the minimum expression level.
Missed
Passed
case-07 · 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.md259 linessingle file
Spatial Visualization
Create visualizations for spatial transcriptomics data.
Required Imports
import squidpy as sq
import scanpy as sc
import matplotlib.pyplot as plt
Basic Spatial Plot
# Plot spots colored by a variable
sq.pl.spatial_scatter(adata, color='total_counts', size=1.3)
# Multiple variables
sq.pl.spatial_scatter(adata, color=['total_counts', 'n_genes_by_counts'], ncols=2)