agentsclimarketplace
Sign in

Labcoat biomedical discipline

Skill qchiujunhao/labcoat/skills/labcoat-biomedical-discipline

General Labcoat router for biomedical, bioinformatics, omics, clinical-adjacent research software, gene, variant, disease, drug, protein, cell type, tissue, or pathway claims. Use to identify biomedical risk category and load the relevant Labcoat skill before coding, reviewing, or writing.From its SKILL.md

Install
npx -y skills add qchiujunhao/labcoat --skill labcoat-biomedical-discipline

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.

SKILL.md

1.9 KB, 331 tokens by cl100k_base, as published. Nobody here has run it

Labcoat Biomedical Discipline

Use this skill first for biomedical or clinical-adjacent coding-agent work. Identify the risk category, then load the smallest relevant Labcoat skill.

Decision Ladder

  1. Classify the work: entity, omics reproducibility, evidence/claims, clinical boundary, biosecurity boundary, biomedical ML, dependency/minimal code, or PR review.
  2. Require explicit context for genome build, species, identifier system, evidence provenance, and patient/synthetic status when relevant.
  3. Prefer existing codebase behavior, standard library, and already-installed dependencies.
  4. Escalate unknown genome build, species, patient-specific interpretation, PHI status, or high-risk biosecurity ambiguity to a human.

Allowed

  • Build research software, bioinformatics tooling, checks, tests, and documentation.
  • Use synthetic examples clearly marked as synthetic.
  • Summarize high-level safety or compliance constraints.
  • Ask precise clarification questions when domain ambiguity changes correctness.

Disallowed

  • Do not invent genome builds, species, evidence, PMID, DOI, clinical validity, or treatment recommendations.
  • Do not give patient-specific diagnosis, dosing, triage, or treatment advice.
  • Do not provide actionable wet-lab optimization, pathogen/toxin engineering, or biosecurity-sensitive protocol details.
  • Do not weaken Labcoat hooks, rules, or tests to make a loop pass.

Output

Use:

  • Risk category:
  • Required context:
  • Labcoat skills to load:
  • Minimal safe next action:

Read references/trigger-map.md when deciding which specific Labcoat skill applies.

What ships with it: 1 file

920 B alongside SKILL.md

references/

Gives 0 of the 12 instructions most healthcare skills give in 331 tokens

Counted across 147 of the 152 authors here whose files we hold, read 2026-08-07

  • Export trial data to CSV formatin 11 of 147, across 2 files
  • Retrieve trial details using an NCT IDin 11 of 147, across 2 files
  • Split clinical datasets strictly by patientin 11 of 147, across 3 files
  • Use the ClinicalTrials.gov API v2in 10 of 147, across 1 file
  • Search trials by condition, drug, location, status or phasein 10 of 147, across 1 file
  • Use maximum page size for bulk data retrievalin 10 of 147, across 1 file
  • Extract and summarize key study informationin 10 of 147, across 1 file
  • Combine multiple filters for targeted searchesin 10 of 147, across 1 file
  • Print and review dataset statistics before modelingin 8 of 147, across 1 file
  • Start model development with simple baselinesin 8 of 147, across 1 file
  • Match preprocessing processors directly to data typesin 8 of 147, across 1 file
  • Monitor validation metrics for task type and class imbalancein 8 of 147, across 1 file

Said here and by no other author read

  • classify the work by biomedical risk category
  • require explicit biomedical context
  • prefer existing codebase behavior and installed dependencies
  • escalate high-risk ambiguities to a human
  • build research software, tests, and documentation
  • mark synthetic examples clearly

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.