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-enrichmentgit 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-enrichment)<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/bulkrna-enrichment"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/bulkrna-enrichment/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/bulkrna-enrichment"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/bulkrna-enrichment.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 | $0.00059 | $0.01165 |
| Opus 5 | $0.00030 | $0.00583 |
| Sonnet 5 | $0.00012 | $0.00233 |
| Haiku 4.5 | $0.00006 | $0.00117 |
Grade A, and why
bulkrna-enrichment 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 11d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bulkrna-enrichment
When to use
Run after bulkrna-de to ask "which biological pathways are enriched
in the DEG list?". Two modes: ORA (over-representation analysis on a
significance-filtered gene list) and pre-ranked GSEA (full ranked
list, no threshold needed). Backed by GSEApy with R clusterProfiler
and a built-in hypergeometric implementation as fallbacks.
Inputs & Outputs
Inputs
- File types:
.csv - Accepts artifact
bulkrna.differential_results(csv)
Outputs
tables/enrichment_results.csvtables/enrichment_significant.csvfigures/enrichment_barplot.pngfigures/enrichment_dotplot.pngreport.mdresult.json
Flow
- Load DE table; pick a ranking metric (log2FoldChange, signed -log10 padj, etc.). Falls back to
log2FoldChangewith a warning atbulkrna_enrichment.py:67if the heuristic finds no preferred metric. - Resolve
--method: ORA, GSEA, or auto. Hard-fails at:370for unknown methods. - Try R clusterProfiler first; on import failure, fall back to GSEApy (
:379). - On GSEApy failure, fall back to the built-in hypergeometric implementation (
:436ORA path,:479GSEA path). - Render barplot + dotplot; emit enrichment table + report.
Gotchas
- Three-tier silent fallback chain. R clusterProfiler → GSEApy → built-in. Each fall is
logger.warning-only (bulkrna_enrichment.py:379, :436, :479); the chosen backend is inresult.json["method_used"]. Built-in is the least feature-rich (no permutation-based GSEA p-values) — verify which engine actually ran before claiming a particular method. - Ranking-metric auto-pick is heuristic and not surfaced in
result.json.:67warns when it falls back tolog2FoldChange, but if your DE table uses a non-standard column name (e.g.lfcinstead oflog2FoldChange), the heuristic may pick the wrong column without complaint. The chosen metric is logged at INFO (:450) but does NOT make it into the summary dict (which carries onlyn_input_genes,n_significant,method_used,n_terms_tested,n_enriched_terms,enrichment_df). Grep the run's stderr for "Using gseapy for pre-ranked GSEA (metric: ...)" to confirm. --padj-cutoffand--lfc-cutoffonly apply to ORA. Pre-ranked GSEA uses the full ranked list and ignores both flags — passing them on a GSEA run silently does nothing. This is correct GSEA behaviour, but easy to mistake for a bug.- No DEGs above thresholds → silent empty plots.
:516and:525warn ("No enrichment results to plot" / "No terms with valid padj") and skip plotting; the run still exits 0 with empty figures and an emptytables/enrichment_results.csv. Loosen thresholds or pre-filter the input if your DE list is sparse.
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.
- 11d ago First seen · 89 lines · 59 tokens per session scan A 9b53ed45e862
bulkrna-enrichment is a skill published in the GitHub repository TianGzlab/OmicsClaw (160 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,165 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
enrichment
Functional enrichment and pathway analysis including GSEA, ORA, ssGSEA, GSVA, and decoupler-based activity inference.
spatial-enrichment
Pathway and gene set enrichment analysis for spatial transcriptomics data.
kegg-query
Query KEGG database for drug information, pathway analysis, and disease-drug-target discovery. Use this skill when: (1) Looking up drug information including efficacy, targets, metabolism, and interactions, (2) Analyzing metabolic or signaling pathways to retrieve genes, compounds, and modules, (3) Discovering…
onekgpd
Query the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants. Use when a question is about individuals or variants in the 1000 Genomes Project cohort: which individuals carry variants matching specific criteria in a gene or region, which individuals…
pkpd-modeling
Pharmacokinetic and pharmacodynamic modelling and simulation - non-compartmental analysis, compartmental and population PK, PK/PD and exposure-response, TMDD, PBPK orientation, bioequivalence, allometric scaling and first-in-human dose, drug interaction prediction, and Bayesian therapeutic drug monitoring. Use when…
clinical-decision-support
Prepare and validate research-only clinical decision-support evaluation, evidence-profile, cohort, survival, biomarker/model, privacy, and governance artifacts. Use for aggregate or synthetic research documentation and traceability—not patient care or live clinical operation.