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-coexpressiongit 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-coexpression)<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/bulkrna-coexpression"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/bulkrna-coexpression/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-coexpression"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/bulkrna-coexpression.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 | $0.00060 | $0.01211 |
| Opus 5.5 | $0.00024 | $0.00484 |
| Sonnet 5.5 | $0.00012 | $0.00242 |
| Haiku 4.5 | $0.00006 | $0.00121 |
Grade A, and why
bulkrna-coexpression 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bulkrna-coexpression
When to use
Load when discovering bulk gene co-expression modules and hub genes with R WGCNA. Skip direct expression contrasts (use bulkrna-de), existing-gene-list PPI lookup (use bulkrna-ppi-network), or single-cell networks (use sc-grn).
Use from a step
from skills._sdk.notebook import load_skill, write_output
library = load_skill("bulkrna-coexpression")
result = library.analyze(data, power=6, min_module_size=10)
write_output(result, "tables/result.csv")
write_output(library.module_sizes_figure(result), "figures/result.png")
Read expression and metadata with read_input before calling the library.
examples/example_step.py constructs a small synthetic dataset and checks
its results through the step runner and fresh-kernel replay.
API
analyze(data: pd.DataFrame, *, power: int | None=None, min_module_size: int=10, random_state: int=54321) -> pd.DataFrame
Return R WGCNA gene-module assignments, leaving expression unchanged.
:param data: Nonnegative feature-by-sample expression; provide normalized data on the intended correlation scale. :param power: CLI default None selects the soft threshold; set a positive integer to override it. :param min_module_size: CLI default 10 genes per module. :param random_state: WGCNA blockwiseModules default seed 54321; fixes its preclustering. :returns: Gene/module DataFrame with diagnostics, hub genes and threshold fit in attrs. :raises ValueError: Input, sample count, power or module size is invalid. :raises ImportError: R WGCNA or Matrix is unavailable. :raises RuntimeError: R analysis fails.
run_info(data: pd.DataFrame, *, keep: bool=True) -> dict
Return WGCNA method diagnostics and summary.
:param data: Result from analyze. :param keep: Keep diagnostics by default; the CLI passes False. :returns: Independent diagnostics dictionary. :raises ValueError: No WGCNA diagnostics are present.
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 5.5 KB runs code
- bulkrna_coexpression.py 13 KB runs code
- examples/example_step.py 990 B runs code
- references/methodology.md 1.1 KB
- references/output_contract.md 619 B
- references/parameters.md 240 B
- rscripts/wgcna.R 5.2 KB
- tests/__init__.py 0 B runs code
- tests/test_api.py 1.2 KB runs code
- tests/test_bulkrna_coexpression.py 2.5 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 · +42 lines · -13 tokens per session bc6e42311cb5
- 1mo ago First seen · 92 lines · 73 tokens per session scan A 96394e8417ec
bulkrna-coexpression is a skill published in the GitHub repository TianGzlab/OmicsClaw (161 stars, last pushed 14d ago), licensed Apache-2.0. It adds 60 tokens to every session and 1,211 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
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-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…
genomic-intelligence
Predicts regulatory features, gene structure, and expression directly from DNA sequence using Genomic Intelligence's hosted transformer DNA language models — no local GPU or model weights. Six tasks over a REST API and a hosted MCP server (keyless public demo): promoter regions, splice donor/acceptor sites, enhancer…
torch-geometric
Supports PyTorch Geometric (PyG) graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when working with torchgeometric, not for general NetworkX analytics or non-graph PyTorch models.
bids
Organizes, queries, validates, and converts Brain Imaging Data Structure (BIDS) datasets. Supports organizing neuroscience and biomedical data (MRI, EEG, MEG, iEEG, PET, microscopy, NIRS, motion capture, EMG, MR spectroscopy, behavioral), querying BIDS layouts, validating compliance, converting DICOM to BIDS, writing…
bulk-rnaseq
Prepares bulk RNA-seq FASTQ, Salmon, STAR or featureCounts output for gene-level differential expression. Covers nf-core/rnaseq and standalone quantification, biological replication, strandedness, reference provenance, validated count assembly and a PyDESeq2 handoff. Use for FASTQ-to-counts analysis, nf-core/rnaseq…