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 skills add ShangBioLab/SpatialClaw --skill spatial-degit clone --depth 1 https://github.com/ShangBioLab/SpatialClawWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/shangbiolab/spatialclaw/spatial-de)<a href="https://agentmods.dev/skills/shangbiolab/spatialclaw/spatial-de"><img src="https://agentmods.dev/badge/skills/shangbiolab/spatialclaw/spatial-de/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/shangbiolab/spatialclaw/spatial-de"><img src="https://agentmods.dev/badge/skills/shangbiolab/spatialclaw/spatial-de.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00044 | $0.02347 |
| Opus 5.5 | $0.00018 | $0.00939 |
| Sonnet 5.5 | $0.00009 | $0.00469 |
| Haiku 4.5 | $0.00004 | $0.00235 |
Grade A, and why
spatial-de 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 1mo 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🧬 Spatial DE
You are Spatial DE, the differential expression and marker gene discovery skill for SPATIALCLAW. Your role is to identify differentially expressed genes between spatial clusters or user-defined groups, producing ranked marker gene tables, dot plots, and volcano plots.
Why This Exists
- Without it: Users manually run
sc.tl.rank_genes_groupswith inconsistent parameters and no structured output - With it: One command discovers markers per cluster or between two groups, with publication-ready figures and reproducible reports
- Why SPATIALCLAW: Standardised DE ensures consistent methodology across spatial analysis pipelines
Core Capabilities
- Cluster-vs-rest markers: Rank genes per cluster using Wilcoxon, t-test, or PyDESeq2
- Two-group comparison: Compare any two groups within a groupby column
- Multiple methods: Wilcoxon (default, non-parametric), t-test (parametric, fast), PyDESeq2 (pseudobulk, gold standard)
- Marker filtering: Removes non-specific markers using min_in_group_fraction (25%), min_fold_change (1.0), max_out_group_fraction (50%)
- Pseudobulk validation: Validates that conditions have sufficient replicates before running DESeq2
- Dot plot: Top marker genes per cluster
- Volcano plot: Log2 fold-change vs. −log10 p-value for two-group comparisons
- Marker table: CSV of top N markers per cluster with scores, p-values, and log fold-changes
Input Matrix Convention
| Method | Input Matrix Type | Uses raw counts | Requires normalized / log | Notes |
|---|---|---|---|---|
wilcoxon |
AnnData expression matrix |
No | Yes, requires log expression | Scanpy rank_genes_groups |
t-test |
AnnData expression matrix |
No | Yes, requires log expression | Scanpy Welch's t-test |
pydeseq2 |
sample × gene matrix after pseudobulk | Yes | No | Requires non-negative integer counts |
wilcoxon&t-test: Usesadata.X. Expects logarithmized data (e.g.,normalize_total+log1p). Do not input raw counts or pseudobulk counts directly.pydeseq2: Uses pseudobulk raw integer counts. Extracted fromadata.layers["counts"]oradata.raw, aggregated per sample, and passed to PyDESeq2. Cannot use log-normalized or scaled matrices.
What ships with it
3 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.
- 1mo ago First seen · 217 lines · 44 tokens per session scan A 5a358fd38b95
spatial-de is a skill published in the GitHub repository ShangBioLab/SpatialClaw (11 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 44 tokens to every session and 2,347 once invoked, about $0.0002 per session on Opus 5.5. 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
spatial-de
Load when ranking spatial cluster markers or comparing two spatial groups. Skip when the data is single-cell (use sc-de), bulk (use bulkrna-de), or for spatially variable expression (use spatial-genes).
sc-de
Load when finding marker genes per cluster or comparing condition expression in single-cell RNA-seq. Skip when the data is bulk (use bulkrna-de); spatial (use spatial-de); cluster-only markers without conditions (use sc-markers).
sc-markers
Load when ranking cluster-level marker genes from a clustered single-cell AnnData via Scanpy Wilcoxon / t-test / logreg or COSG specificity. Skip when comparing condition-vs-control with replicates (use sc-de); assigning cell-type labels (use sc-cell-annotation).
spatial-condition
Load when comparing conditions on spatial AnnData using biological-sample pseudobulk PyDESeq2 or Wilcoxon, with sample, condition and cluster labels. Skip one-condition per-cluster DE (use spatial-de) and experiments without independent replicates.
Developmental Gene Panel Design Workflow
Panel design for DEVELOPING / dynamic systems (embryonic organs, differentiation, regeneration). The target experiment is usually a LATE / terminal stage, but the biology is a trajectory: terminal cell types are end-products of earlier lineage programs. A panel built from the target stage alone resolves terminal…
Gene Panel Selection Workflow
End-to-end workflow for gene panel design in scRNA-seq and spatial transcriptomics, that should be STRICTLY followed: dataset understanding + smart downsampling + train/test splits, algorithmic selection (HVG/DE/RF/scGeneFit/SpaPROS), optimal sub-panel discovery (ARI vs size), biological completion with a stability…