Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Spatial Transcriptomics Analysis · FreedomIntelligence | DecimalAI

Spatial Transcriptomics Analysis

SkillScore95Maintained

spatial-transcriptomics-analysis

Automated analysis pipeline for Spatial Transcriptomics (Visium, Xenium) integrating histology and gene expression.

scienceby FreedomIntelligence

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Research pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/spatial-transcriptomics-analysis/SKILL.md

decimalai skills pull spatial-transcriptomics-analysis --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/spatial-transcriptomics-analysis/SKILL.md https://app.decimal.ai/s/spatial-transcriptomics-analysis/SKILL.md

Raw file: /s/spatial-transcriptomics-analysis/SKILL.md ↗ · machine-readable summary at /s/spatial-transcriptomics-analysis.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 51d ago

Yes — +45% lift-31% tokens0% turns95% of whole cases pass with skill (21/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-36%	0%
case-03	✗→✓	▲ Improved	-32%	0%
case-14	✗→✓	▲ Improved	-32%	0%
case-04	✗→✓	▲ Improved	-39%	0%
case-07	✗→✓	▲ Improved	-57%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

FreedomIntelligence / OpenClaw-Medical-Skills

skills/spatial-transcriptomics-analysis/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v2

Skill contents

SKILL.md

<!--

COPYRIGHT NOTICE

This file is part of the "Universal Biomedical Skills" project.

Copyright (c) 2026 MD BABU MIA, PhD <md.babu.mia@mssm.edu>

All Rights Reserved.

#

This code is proprietary and confidential.

Unauthorized copying of this file, via any medium is strictly prohibited.

#

Provenance: Authenticated by MD BABU MIA

-->

Spatial Transcriptomics Skill

Version: 1.0.0 Author: MD BABU MIA, PhD Date: February 2026

Overview

This skill provides automated analysis capabilities for Spatial Transcriptomics data, specifically designed for 10x Visium and Xenium platforms. It enables the integration of histological data with gene expression profiles to uncover spatial organization of cell types.

Capabilities

Data Loading: Supports Spaceranger output (h5, images).
QC & Preprocessing: Spatial QC metrics, normalization.
Spatial Variable Features: Identification of spatially variable genes (SVGs) using Moran's I and Geary's C.
Deconvolution: Interface for cell type deconvolution (mapping scRNA-seq to spatial).
Visualization: Interactive spatial plots overlaying gene expression on tissue images.

Usage

python
from Skills.Genomics.Spatial_Transcriptomics.spatial_analyzer import SpatialAnalyzer

# Initialize
sa = SpatialAnalyzer(data_path="./data/visium_sample1")

# Run Pipeline
sa.load_data()
sa.preprocess()
sa.find_spatial_features()
sa.plot_spatial("INS", save_path="./output/insulin_spatial.png")

Requirements

scanpy
squidpy
anndata
matplotlib

Illustrative Want to see what spatial-transcriptomics-analysis would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/2/2026, 18:03 UTC · 22 cases

Lift

+45%

95% vs 50%

Agent turns

0%

1.0 vs 1.0

Tokens

-31%

1,434.95 vs 2,088.86

fail → pass · 10pass → pass · 11fail → fail · 1

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-01 I have 10x Visium data from SpaceRanger stored in `./data/visium_sample1`. Could you write a Python script using the spatial analyzer class that loads the h5 and image inputs, runs spatial QC and preprocessing, calculates spatially variable features, and outputs a spatial plot overlaying INS gene expression onto the tissue image at `./output/insulin_spatial.png`?	fail→pass	14,860	7,278	-51%	1	1	0%	3,327	2,140	-36%	0	0	—
case-02 Can you provide a Python workflow script to process spatial transcriptomics data from a SpaceRanger directory? I need code that initializes the spatial analyzer, executes the data loading and normalization routines, identifies spatially variable genes, and exports a spatial gene expression map overlaid on top of the histological histology image.	fail→fail	19,337	14,624	-24%	1	1	0%	3,587	3,591	+0%	0	0	—
case-03 Please show me how to write a Python script using the SpatialAnalyzer module to analyze Visium sample data. The code should import the dataset from a specified directory path, handle spatial preprocessing, compute spatial features, and generate an image plot mapping target gene expression over the tissue section.	fail→pass	15,940	11,908	-25%	1	1	0%	3,468	2,361	-32%	0	0	—
case-14 Provide a complete Python script that imports the spatial transcriptomics analyzer, loads data from `./data/visium_sample2`, performs preprocessing, identifies spatial variable features, and plots the `CD8A` gene to `./output/cd8a.png`.	fail→pass	11,692	6,020	-49%	1	1	0%	2,573	1,753	-32%	0	0	—
case-20 I have single-cell RNA-seq count data (without spatial coordinates) in an AnnData object `adata`. How should I perform standard graph-based Leiden clustering using Scanpy? Write a Python script.	pass→pass	12,333	12,304	-0%	1	1	0%	2,551	3,016	+18%	0	0	—
case-21 How do I perform differential gene expression analysis between wild-type and knockout conditions for non-spatial bulk RNA-seq count matrices using PyDESeq2? Provide a Python script.	pass→pass	14,669	13,085	-11%	1	1	0%	3,136	3,165	+1%	0	0	—
case-22 I have ATAC-seq alignment BAM files for a tissue sample. How do I call chromatin accessibility peaks using MACS3 from the command line?	pass→pass	14,930	11,605	-22%	1	1	0%	2,822	2,520	-11%	0	0	—
case-04 Write a Python snippet to initialize a spatial transcriptomics analyzer object for a Visium dataset located at `./data/tissue_section`. Please write valid code using the standard workspace module structure.	fail→pass	7,154	2,868	-60%	1	1	0%	1,454	889	-39%	0	0	—
case-05 After initializing `sa = SpatialAnalyzer(data_path="./data/sample")`, what is the exact method call used to load the SpaceRanger h5 files and tissue images into memory? Provide the Python call.	pass→pass	8,584	2,167	-75%	1	1	0%	1,613	776	-52%	0	0	—
case-06 Write the Python statement to perform spatial quality control and normalization on an initialized `SpatialAnalyzer` instance named `sa`.	pass→pass	6,168	1,961	-68%	1	1	0%	1,001	752	-25%	0	0	—
case-07 Which method on `SpatialAnalyzer` computes spatially variable genes across the tissue spots? Provide a Python snippet demonstrating its usage on instance `sa`.	fail→pass	10,264	2,103	-80%	1	1	0%	1,872	814	-57%	0	0	—
case-08 Write a Python statement using an initialized `SpatialAnalyzer` instance `sa` to generate a spatial gene expression plot for gene `MYH6` and save it to `./output/myh6_expression.png`.	fail→pass	5,487	1,622	-70%	1	1	0%	1,030	729	-29%	0	0	—
case-09 What statistical metrics are employed by the spatial transcriptomics framework to identify spatially variable genes in tissue samples? List the metrics.	pass→pass	12,701	1,900	-85%	1	1	0%	2,404	746	-69%	0	0	—
case-10 Which spatial transcriptomics high-throughput platforms are explicitly supported by this specialized analysis module?	pass→pass	2,849	1,792	-37%	1	1	0%	428	712	+66%	0	0	—
case-11 What Python single-cell and spatial analysis dependencies are required to run the spatial analyzer workflow? List the required packages.	pass→pass	11,298	1,852	-84%	1	1	0%	1,950	716	-63%	0	0	—
case-12 How does the spatial analysis framework support mapping single-cell RNA-seq cell type labels onto spatial transcriptomics spots?	pass→pass	13,699	11,598	-15%	1	1	0%	2,300	2,556	+11%	0	0	—
case-13 Write a Python code snippet to instantiate the spatial analyzer class for a Xenium dataset stored in `./data/xenium_run1`.	fail→pass	5,817	2,202	-62%	1	1	0%	1,122	843	-25%	0	0	—
case-15 Write a Python snippet that calls the spatial visualization method on instance `sa` to map spatial expression of `ERBB2` saving to `./plots/erbb2.png`.	fail→pass	12,251	1,960	-84%	1	1	0%	2,468	823	-67%	0	0	—
case-16 What input file formats from SpaceRanger outputs does the spatial transcriptomics module load during data loading?	pass→pass	9,564	1,563	-84%	1	1	0%	1,941	653	-66%	0	0	—
case-17 What is the full Python import statement required to import the `SpatialAnalyzer` class?	fail→pass	10,669	1,597	-85%	1	1	0%	1,751	620	-65%	0	0	—
case-18 When calling the constructor for `SpatialAnalyzer`, what parameter name is used to pass the directory containing the spatial dataset?	fail→pass	12,759	1,559	-88%	1	1	0%	2,104	629	-70%	0	0	—
case-19 Beyond scanpy and squidpy, what core data structure library is required by the spatial transcriptomics analysis module to hold spatial count matrices?	pass→pass	5,722	2,235	-61%	1	1	0%	1,053	765	-27%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +45 percentage points is the difference between those two pass rates over the 22 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 50%
Pass rate with the skill: 95.5%
Cases attempted: 22
Cases counted toward lift: 22
Cases that regressed: 0
Skill version measured: v2
Run completed: 8/2/2026, 18:03 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-01

Prompt

I have 10x Visium data from SpaceRanger stored in `./data/visium_sample1`. Could you write a Python script using the spatial analyzer class that loads the h5 and image inputs, runs spatial QC and preprocessing, calculates spatially variable features, and outputs a spatial plot overlaying INS gene expression onto the tissue image at `./output/insulin_spatial.png`?

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run95

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns-23% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 51 days ago

Model	Method	Date	Lift
gemini-3.6-flash	verified	7/26/2026	0%

Other measured skills in the registry, with their headline benchmark lift.