AutomationResearch InfrastructureFreedomIntelligence/OpenClaw-Medical-SkillsData & Reproduction

STAgent

Maintainer FreedomIntelligence · Last updated April 1, 2026

STAgent.

OpenClawNanoClawAnalysisReproductionstagentopenclaw medical skillsadditional scientific toolsstagent

Original source

FreedomIntelligence/OpenClaw-Medical-Skills

https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills/tree/main/skills/STAgent

Skill Snapshot

2 min

Run STAgent to align histology images with expression matrices, perform clustering/SVG detection, and generate literature-backed spatial reports.
Analysis of Visium/Xenium or similar ST datasets.
Visual reasoning over spatial plots, H&E images, or cluster maps.
Automatically generating Scanpy/Squidpy code for new ST workflows.
Hypothesis generation about spatial gene expression patterns.

Source Doc

Dynamic code generation: Create/execute Python scripts for QC, clustering, SVG detection.
Visual reasoning: Interpret spatial plots to identify tissue domains and cell neighborhoods.
Literature retrieval: Pull references that contextualize findings.
Report generation: Deliver publication-style writeups with plots and SVG tables.

Env setup: conda env create -f environment.yml && conda activate STAgent.
Data prep: Supply expression_path (.h5ad/Spaceranger) + image_path (H&E/IF) and metadata.
Task selection: Choose tasks such as cluster, find_svg, annotate_domains, or composite instructions; run python repo/src/main.py --data_path ... --task "...".
Execute & interpret: Let STAgent generate scripts, run analyses, and interpret results with literature references.
Package outputs: Save UMAP/spatial plots, SVG tables, QC details, and summary markdown.

Document coordinate systems and any scaling between imaging and expression coordinates.
Avoid definitive cell-type labels without supporting markers.
Capture QC parameters for reproducibility.