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-qcgit 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-qc)<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/bulkrna-qc"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/bulkrna-qc/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-qc"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/bulkrna-qc.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 | $0.00071 | $0.00962 |
| Opus 5 | $0.00036 | $0.00481 |
| Sonnet 5 | $0.00014 | $0.00192 |
| Haiku 4.5 | $0.00007 | $0.00096 |
Grade A, and why
bulkrna-qc 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 9d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bulkrna-qc
When to use
Run as the first step on a bulk RNA-seq count matrix (genes × samples) before differential expression. Surfaces the four failure modes that silently bias DE results: a sample with a tiny library, a sample with suspiciously few detected genes, a low-correlation outlier vs the rest, and CPM-vs-raw comparison artefacts.
Inputs & Outputs
Inputs
- File types:
.csv
Outputs
tables/cpm_normalized.csvtables/sample_stats.csvfigures/expression_density.pngfigures/gene_detection.pngfigures/library_sizes.pngfigures/sample_correlation.pngreport.mdresult.json
Flow
- Load the count matrix (raise on missing
--inputor non-existent file perbulkrna_qc.py:428,431). - Compute per-sample library sizes and detected-gene counts.
- Compute sample × sample correlation matrix; flag samples below the median-of-medians threshold as outliers.
- Compute CPM normalisation as a side artifact (write
tables/cpm_normalized.csv). - Render four figures and emit
report.md+result.json.
Gotchas
- Hard-fails on missing input.
bulkrna_qc.py:428raisesValueError("--input is required when not using --demo");:431raisesFileNotFoundErrorif the path doesn't exist. No silent demo fallback when--inputis given but invalid — fix the path or use--demo. - CPM is for visualisation only.
tables/cpm_normalized.csvis emitted as a downstream-friendly artefact, but DE testing must always use raw counts (PyDESeq2's negative-binomial GLM expects integer counts; feeding CPM produces meaningless dispersion estimates). Do not pipecpm_normalized.csvintobulkrna-de. - Outlier flagging is correlation-based, not biology-aware. If two biological conditions differ strongly (e.g. tumour vs normal), the cross-condition correlations are expected to be lower — the outlier flag may fire on legitimate biology. Cross-check
result.json["outlier_samples"]against the experimental design before excluding samples. - First column is treated as the gene-id column unconditionally. If the CSV has a header row but no leading id column (samples-only), the first sample column will be silently parsed as gene names and omitted from QC. Inspect
report.md's "samples seen" count vs your design before trusting the output.
What ships with it
5 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.
- 9d ago First seen · 84 lines · 71 tokens per session scan A 46b849a3ee34
bulkrna-qc is a skill published in the GitHub repository TianGzlab/OmicsClaw (160 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 71 tokens to every session and 962 once invoked, about $0.0004 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
protein-design-qc
Protein design quality control, filtering thresholds, and ranking guidance. Use this skill when: (1) Evaluating design quality for binding, expression, or structure, (2) Setting filtering thresholds for pLDDT, ipTM, PAE, (3) Checking sequence liabilities (cysteines, deamidation, polybasic clusters), (4) Creating…
protein-qc
Quality control metrics and filtering thresholds for protein design. Use this skill when: (1) Evaluating design quality for binding, expression, or structure, (2) Setting filtering thresholds for pLDDT, ipTM, PAE, (3) Checking sequence liabilities (cysteines, deamidation, polybasic clusters), (4) Creating multi-stage…
protein-design-qc
Protein design quality control, filtering thresholds, and ranking guidance. Use this skill when: (1) Evaluating design quality for binding, expression, or structure, (2) Setting filtering thresholds for pLDDT, ipTM, PAE, (3) Checking sequence liabilities (cysteines, deamidation, polybasic clusters), (4) Creating…
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…
neuropixels-analysis
Analyze Neuropixels extracellular recordings end-to-end with SpikeInterface. Covers loading SpikeGLX/Open Ephys/NWB data, preprocessing, drift/motion correction, Kilosort4 (and CPU) spike sorting, quality metrics, and unit curation (threshold-based, model-based UnitRefine, and AI-assisted visual review). Use when…
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…