Labcoat omics reproducibility

Skill qchiujunhao/labcoat/skills/labcoat-omics-reproducibility

Skills, hooks, and CLI checks for safer biomedical AI coding agents.

Install

npx -y skills add qchiujunhao/labcoat --skill labcoat-omics-reproducibility

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Reproducibility discipline for RNA-seq, scRNA-seq, ATAC-seq, variant, proteomics, imaging, Scanpy, Seurat, clustering, and omics pipeline work. Use when inputs, references, seeds, QC thresholds, layers, versions, or outputs affect scientific correctness.

SKILL.md

1.2 KB, 200 tokens by cl100k_base, as published. Nobody here has run it

Omics Reproducibility

Make omics code rerunnable and biologically interpretable.

Decision Ladder

State input files, sample schema, units, organism, and genome/reference where relevant.
State counts/layer assumptions and normalization.
Set deterministic seeds for stochastic steps.
Record QC thresholds and filtering scope.
Define exact output files, columns, and smoke tests.

Allowed

Conservative checks that ask for missing build/species/layer/QC context.
Minimal pipeline smoke tests on synthetic data.
Version and parameter notes in code or docs.

Disallowed

Do not assume adata.X is raw counts.
Do not assume VCF normalization, FASTQ encoding, or coordinate build.
Do not silently change filtering scope.

Output

Use:

Inputs:
Assumptions:
Determinism:
QC:
Outputs:
Smoke test:

Read the checklist matching the omics domain.