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 bulkrna-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/bulkrna-de)<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/bulkrna-de"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/bulkrna-de.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.01038 |
| Opus 5 | $0.00027 | $0.00519 |
| Sonnet 5 | $0.00011 | $0.00208 |
| Haiku 4.5 | $0.00005 | $0.00104 |
Grade A, and why
bulkrna-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 8d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bulkrna-de
When to use
The user has a bulk RNA-seq count matrix (genes × samples) and wants to know which genes change between two groups (control vs treatment, tumour vs normal, etc.). PyDESeq2 is preferred when ≥2 replicates per condition exist; Welch's t-test is the fallback for the single-replicate / no-PyDESeq2 case.
Inputs & Outputs
Inputs
- File types:
.csv - Accepts artifact
bulkrna.count_matrix(csv) - Tabular structure: at least 3 columns
Outputs
tables/counts.csvtables/de_results.csvtables/de_significant.csvtables/deseq2_results.csvfigures/de_barplot.pngfigures/ma_plot.pngfigures/pvalue_histogram.pngfigures/volcano_plot.pngreport.mdresult.json- Produces artifact
bulkrna.differential_resultsastables/de_results.csv(csv)
Flow
- Load genes × samples raw count matrix.
- Auto-partition columns into control / treatment by name prefix.
- Pre-filter genes with total counts < 10 across all samples.
- Run PyDESeq2 (negative binomial GLM + Wald test) — fall back to Welch's t-test if PyDESeq2 missing or < 2 replicates per condition.
- Apply Benjamini–Hochberg FDR correction.
- Filter DEGs by
--padj-cutoffand--lfc-cutoff. - Render volcano / MA / p-value histogram and emit report.
Gotchas
- PyDESeq2 silently falls back to Welch's t-test when fewer than 2 replicates per condition are detected or
pydeseq2is not importable. Checkresult.json["method_used"]to confirm which engine actually ran — the volcano-plot title alone does not surface the fallback. - LFCs are unshrunk by design. Suitable for hypothesis testing (padj thresholds), but for ranking / visualisation that emphasises high-confidence effects, apply apeglm or ashr shrinkage outside this skill.
- VST / rlog transformations are visualisation-only. Do not feed transformed counts back into this skill — DE testing always wants raw integer counts.
- Sample group detection is prefix-based. Columns must start with
--control-prefix(defaultctrl) or--treat-prefix(defaulttreat); columns matching neither prefix are silently dropped. - Pre-filter removes low-count genes (total < 10). This improves dispersion estimation but means the input gene count is not the testing gene count —
result.json["n_tested"]is authoritative.
What ships with it
7 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.
- 8d ago First seen · 96 lines · 54 tokens per session scan A a603e0e81588
bulkrna-de is a skill published in the GitHub repository TianGzlab/OmicsClaw (160 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,038 once invoked, about $0.0003 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
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…
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…
single-cell-scrna-seq-analysis-scanpy
Complete single-cell RNA-seq analysis workflow built on Scanpy and AnnData. Use this skill when: (1) Loading diverse single-cell data formats (10X, h5ad, CSV), (2) Performing quality control and filtering, (3) Normalization, dimensionality reduction, and clustering, (4) Marker gene identification and cell type…
single-cell-multi-omics-analysis-scvi
Probabilistic deep learning framework for single-cell multi-omics data analysis. Use this skill when: (1) Analyzing single-cell RNA-seq data with batch correction, (2) Integrating multi-modal data (CITE-seq, ATAC-seq, multi-omics), (3) Performing cell type annotation with scANVI, (4) Spatial transcriptomics…
anndata
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
celltypepilot
Single-cell cell-type annotation with evidence, conservative abstention, and reviewable drafts. Use this whenever the user wants to annotate, label, or identify cell types for pre-clustered single-cell or spatial transcriptomics data (.h5ad), or says things like "annotate my clusters", "what cell types are these?"…