Analyzes spatial proteomics data from CODEX, IMC, and MIBI platforms including cell segmentation and protein colocalization.
SkillScore100Maintained
Automatic
◆Research pack
Last verified 8/2/2026
What it changes
Passed 22 of 22 test cases with the skill, and 10 of 22 without it.
Without skill45%
With skill100%
Checks it passed that the model alone missed
Uses sm.tl.cluster with method='leiden'
Calls sm.pp.combat with batch_key='fov'
Calls sm.pp.log1p on the AnnData object
and 12 more in the full report
12 fixed10 passed either way0 still failing0 broke
Pass-rate lift
+55 pp
Tokens
-9%
Agent turns
0%
Response time
-49%
Model gemini-3.6-flashMeasured 8/2/2026v122 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 12
Prompt
Before rescale normalization of raw signal intensities in an AnnData spatial proteomics object, log-transformation is required. What function computes log1p on the intensity matrix?
What was checked, without and with the skill
Checked
Without skill
With skill
Calls sm.pp.log1p on the AnnData object
Missed
Passed
case-16 · 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.md116 linessingle file
Spatial Proteomics Analysis
Data Loading
import scimap as sm
import anndata as ad
# Load CODEX/IMC data (cell x marker matrix with spatial coordinates)
adata = ad.read_h5ad('spatial_proteomics.h5ad')
# Required: spatial coordinates in adata.obsm['spatial']
# Required: protein intensities in adata.X