Labcoat entity discipline
Gene, variant, disease, drug, protein, cell type, tissue, marker, ortholog, HGVS, rsID, transcript, species, and genome-build ambiguity discipline. Use when biomedical entity interpretation could change by organism, identifier system, reference, or provenance.From its SKILL.md
npx -y skills add qchiujunhao/labcoat --skill labcoat-entity-disciplineAssembled 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
1.4 KB, 235 tokens by cl100k_base, as published. Nobody here has run it
Entity Discipline
Biomedical names are not universal. Require enough context before interpreting them.
Decision Ladder
- Identify entity type: gene, variant, disease, drug, protein, tissue, cell type, pathway, sample, coordinate.
- Require organism/species for gene symbols and markers.
- Require genome build for genomic coordinates and VCF/BED/BAM/GTF/GFF/liftOver work.
- Require transcript/reference sequence for HGVS or protein-change claims.
- Use stable identifiers where possible; preserve user-provided uncertainty.
Allowed
- Ask for missing species, build, transcript, or identifier source.
- Flag ambiguous marker panels and aliases.
- Use
scripts/detect_bio_entities.pyfor a quick deterministic entity scan.
Disallowed
- Do not infer human because symbols are uppercase.
- Do not infer GRCh38/hg38 because coordinates look modern.
- Do not invent clinical significance, citation, or variant interpretation.
Output
Use:
- Entity:
- Missing context:
- Risk:
- Minimal safe next step:
Read references/entity-ambiguity.md for common ambiguity patterns.
What ships with it: 2 files
1.3 KB alongside SKILL.md, 1 of them executable
references/
- entity-ambiguity.md479 B
scripts/
- detect_bio_entities.pyruns844 B