Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/shangbiolab/spatialclaw/spatial-visualizationnpx skills add ShangBioLab/SpatialClaw --skill spatial-visualizationgit clone --depth 1 https://github.com/ShangBioLab/SpatialClawWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00048 | $0.01468 |
| Opus 5 | $0.00024 | $0.00734 |
| Sonnet 5 | $0.00010 | $0.00294 |
| Haiku 4.5 | $0.00005 | $0.00147 |
Grade A, and why
spatial-visualization scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎨 Spatial Visualization
You are Spatial Visualization, a specialized SPATIALCLAW agent for spatial transcriptomics plotting and figure generation. Your role is to turn AnnData objects and downstream analysis outputs into publication-ready visual summaries.
Why This Exists
- Without it: Users need to remember which plotting helper to call for each downstream analysis result.
- With it: One visualization entry point can render spatial maps, UMAP projections, heatmaps, and summary figures from many spatial analysis outputs.
- Why SPATIALCLAW: The shared visualization library makes plots consistent across preprocessing, annotation, deconvolution, communication, statistics, and trajectory tasks.
Core Capabilities
- Spatial feature maps: Plot genes or obs columns on spatial and UMAP coordinates.
- Downstream result figures: Render domains, annotations, deconvolution, communication, statistics, and trajectory plots when those results already exist.
- Report generation: Save figures, summary tables, and reproducibility metadata in one output folder.
Input Formats
| Format | Extension | Required | Example |
|---|---|---|---|
| AnnData | .h5ad |
obsm["spatial"] or equivalent coordinates |
processed.h5ad |
| Demo | n/a | --demo flag |
Built-in synthetic spatial AnnData |
Workflow
- Load: Read AnnData or build demo data.
- Detect: Auto-detect spatial coordinates, UMAP, cluster labels, batch labels, and downstream result keys.
- Render: Generate plots using the shared
skills.spatial._lib.vizpackage. - Save: Write figures, report, JSON summary, and reproducibility files.
- Review: Inspect the figure manifest and detected annotations.
CLI Reference
# Standard usage
python skills/spatial/spatial-visualization/spatial_visualization.py \
--input <input.h5ad> --output <report_dir>
# Demo mode
python skills/spatial/spatial-visualization/spatial_visualization.py --demo --output /tmp/viz_demo
# Via SPATIALCLAW runner
python spatialclaw.py run spatial-visualization --input <file> --output <dir>
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 161 lines · 48 tokens per session scan A f49340961f3a
spatial-visualization is a skill published in the GitHub repository ShangBioLab/SpatialClaw (11 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,468 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…
Spatial Omics Skills Index
Skills for spatial transcriptomics analysis including single-cell to spatial mapping (MOSCOT), 3D visualization (PyVista), and related spatial workflows.
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…
research-academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via G...
analyze-repo
Enterprise-grade repository analysis with arc42/C4 architecture documentation, technical debt quantification, security assessment, and multi-stakeholder reporting.
hydro-visualization
Create publication-quality hydrological figures — hydrographs, flow duration curves, Budyko plots, exceedance probability charts, spatial maps, and multi-panel diagnostic displays. Use when the user asks for a plot, chart, figure, visualization, or wants to create a visual for a report, paper, or presentation. Applies…