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 sc-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/sc-de)<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/sc-de"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/sc-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/sc-de"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/sc-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 | $0.00051 | $0.02467 |
| Opus 5.5 | $0.00020 | $0.00987 |
| Sonnet 5.5 | $0.00010 | $0.00493 |
| Haiku 4.5 | $0.00005 | $0.00247 |
Grade A, and why
sc-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 17d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sc-de
When to use
The user has a preprocessed scRNA-seq AnnData and wants to know either
(a) which genes mark each cluster (Wilcoxon / t-test / logreg ranking) or
(b) which genes change between conditions in a replicate-aware way
(pseudobulk_de, DESeq2 in R). Mixing normalized expression and raw
counts across these paths is the most common silent-wrong-answer failure
mode, so each path reads the matrix it needs.
Use from a step
de = load_skill("sc-de")
adata = read_input("results/04_annotation/intermediate/adata_annotated.h5ad")
table = de.rank_genes(adata, groupby="cell_type", method="wilcoxon")
write_output(table, "tables/de_full.csv")
write_output(de.top_genes(table, n_top=10), "tables/markers_top.csv")
write_output(de.volcano_figure(table, group="B cell"), "figures/volcano_b_cell.png")
A complete step that runs on demo data: examples/example_step.py.
API
rank_genes(adata, *, groupby: str='leiden', method: str='wilcoxon', group1: str | None=None, group2: str | None=None, logreg_solver: str='lbfgs') -> pd.DataFrame
Rank genes per group of cells: every group against the rest, or group1 against group2.
wilcoxon, t-test and logreg run scanpy's rank_genes_groups on
X (use_raw=False, with the fraction of expressing cells) and also leave
its result in uns['rank_genes_groups']; mast runs the MAST hurdle model
in R. Cells are the units here, so p-values overstate the evidence for a
difference between conditions; use :func:pseudobulk_de for that.
:param groupby: The obs column defining the groups. Default "leiden"; when it
is missing and louvain exists, louvain is used and recorded.
:param method: "wilcoxon" (default; scanpy's recommended test), "t-test",
"logreg" or "mast".
:param group1: Compare only this group ...
:param group2: ... against this one. Default: each group against the rest.
:param logreg_solver: The scikit-learn solver for logreg. Default "lbfgs".
:returns: One row per gene and group. scanpy methods: names, scores,
logfoldchanges, pvals, pvals_adj, pct_nz_group,
pct_nz_reference, group; mast: gene, group, pvalue,
padj and effect columns.
:raises ValueError: an unknown method, or the group column is missing.
:raises RuntimeError: mast and R or MAST is missing.
What ships with it
10 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 14 KB runs code
- examples/example_step.py 821 B runs code
- references/methodology.md 4.6 KB
- references/output_contract.md 3.0 KB
- references/parameters.md 2.9 KB
- references/r_visualization.md 1.1 KB
- sc_de.py 29 KB runs code
- tests/__init__.py 0 B runs code
- tests/test_mast_exchange.py 2.3 KB runs code
- tests/test_sc_de.py 2.8 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.
- 17d ago Changed · +47 lines e8921e11742a
- 1mo ago First seen · 123 lines · 51 tokens per session scan A 4443e57bc72c
sc-de is a skill published in the GitHub repository TianGzlab/OmicsClaw (161 stars, last pushed 17d ago), licensed Apache-2.0. It adds 51 tokens to every session and 2,467 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
bulk-transcriptomics
Bulk RNA-seq and microarray differential expression analysis including method selection, batch correction, and complex experimental designs.
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.
scanpy
Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use…
Virtual Embryo — atlas data + knowledge graph
Query the Virtual Embryo knowledge graph (mouse/human developmental biology: genes, anatomy, Theiler/Carnegie stages, gene expression, diseases, papers) and its 3D atlas catalog (anatomical OPT/light-sheet volumes + 3D spatial- transcriptomics datasets), and visualise those datasets in 3D with the volume3d / spatial3d…
Single-Cell Analysis Skills Index
Core skills for single-cell RNA-seq analysis: quality control, cell type annotation, and trajectory inference. These are high-priority actionable workflows — load them first for common single-cell tasks.
cellxgene-census-query
Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, and integrate with scanpy/PyTorch for population-scale single-cell analysis. Use this skill when: (1) Querying single-cell expression data by cell type, tissue, or disease, (2) Exploring available single-cell datasets…