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 TianGzlab/OmicsClaw --skill spatial-degit clone --depth 1 https://github.com/TianGzlab/OmicsClawWrote 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/tiangzlab/omicsclaw/spatial-de)<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/spatial-de"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/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/tiangzlab/omicsclaw/spatial-de"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/spatial-de.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 3 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00048 | $0.01155 |
| Opus 5.5 | $0.00019 | $0.00462 |
| Sonnet 5.5 | $0.00010 | $0.00231 |
| Haiku 4.5 | $0.00005 | $0.00115 |
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 14d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spatial-de
When to use
Rank spatial group markers with Wilcoxon or t-test, or compare conditions with sample-aware PyDESeq2 pseudobulk. Biological sample labels are required; spatial spots do not supply independent replicates.
Use from a step
from skills._sdk.notebook import load_skill, read_input, write_output
library = load_skill("spatial-de")
adata = read_input("processed.h5ad")
library.differential_expression(adata, groupby="leiden")
write_output(library.results(adata), "tables/de_full.csv")
The executable example checks known markers in simulated spatial domains.
API
differential_expression(adata, *, method='wilcoxon', groupby='leiden', group1=None, group2=None, n_top_genes=10, fdr_threshold=0.05, log2fc_threshold=1.0, **parameters)
Test groups and return the same AnnData, with results in its diagnostics.
Scanpy uses raw when present, otherwise log-normalized X. PyDESeq2 uses counts, then raw, then X; provide integer counts and biological samples.
:param adata: Expression and group labels; modified in place. :param method: CLI default wilcoxon; t-test or pydeseq2 for other tests. :param groupby: CLI default leiden; obs column defining comparisons. :param group1: Tested group, or None for each group versus rest. :param group2: Reference group; supply together with group1. :param n_top_genes: CLI default 10 marker genes per group. :param fdr_threshold: CLI default 0.05 adjusted-p-value threshold. :param log2fc_threshold: CLI default 1.0 effect-size threshold. :param parameters: Method-specific CLI parameters from references/parameters.md. :returns: The same AnnData; results returns the full result table. :raises ValueError: Groups, method or sample replication are invalid. :raises ImportError: PyDESeq2 is unavailable; use install_skill_deps.
results(adata, *, markers_only=False)
Return the full or selected marker table without changing expression.
What ships with it
13 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.
- _api.py 5.3 KB runs code
- examples/example_step.py 861 B runs code
- r_visualization/de_publication_template.R 7.2 KB
- r_visualization/README.md 1.6 KB
- references/methodology.md 7.6 KB
- references/output_contract.md 1.9 KB
- references/parameters.md 4.8 KB
- references/r_visualization.md 808 B
- spatial_de.py 66 KB runs code
- tests/__init__.py 0 B runs code
- tests/test_api.py 2.2 KB runs code
- tests/test_examples_replay.py 1.8 KB runs code
- tests/test_spatial_de.py 7.2 KB runs code
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.
- 14d ago Changed · +1 lines · -3 tokens per session 0ba13a8cbaa7
- 1mo ago First seen · 126 lines · 51 tokens per session scan A 5c579d367198
spatial-de is a skill published in the GitHub repository TianGzlab/OmicsClaw (161 stars, last pushed 14d ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,155 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 2026-09-03.
Other skills, from other repositories
spatial-de
Differential expression analysis — find marker genes for clusters or compare two groups. Supports Wilcoxon rank-sum, t-test, and PyDESeq2 methods with publication-ready figures and CSV tables.
spatial-condition-comparison
Experimental condition comparison using pseudobulk differential expression with proper multi-sample statistics.
bulk-transcriptomics
Bulk RNA-seq and microarray differential expression analysis including method selection, batch correction, and complex experimental designs.
spatial-omics
Spatial transcriptomics and spatial proteomics analysis covering technology-specific workflows, spatial statistics, deconvolution, and niche analysis.
spatial-omics-integrate
Integrate two aligned spatial omics modalities on the same cells using SpatialGlue or SpaDDM. Standard input contract: --input --omics2 . Supports demo mode and validated modality pairs such as RNA+Protein and RNA+ATAC.
pseudobulk_design_helper
Recommend a replicate-aware pseudobulk strategy for single-cell differential expression and explain the design choices.