Labcoat evidence not assertion

Skill qchiujunhao/labcoat/skills/labcoat-evidence-not-assertion

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

Install

npx -y skills add qchiujunhao/labcoat --skill labcoat-evidence-not-assertion

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

Biomedical evidence and claim-strength discipline. Use for disease, gene, variant, drug, protein, pathway, clinical-validity, citation, PMID, DOI, association, causation, diagnosis, treatment, or literature-backed claims.

SKILL.md

1.3 KB, as published. Nobody here has run it

Evidence Not Assertion

Write biomedical claims with calibrated strength.

Decision Ladder

Separate observed data, source evidence, inference, speculation, and recommendation.
Keep association as association unless causal evidence is provided.
Preserve user-provided citations; do not fabricate citation identifiers.
Mark uncited claims as uncited or ask for sources.

Allowed

Say "associated with", "observed in", "consistent with", or "hypothesis" when evidence is limited.
Identify missing evidence or provenance.
Summarize user-provided sources without overclaiming.

Disallowed

Do not invent PMIDs, DOIs, journal names, or clinical validation.
Do not turn association into causation.
Do not say a finding diagnoses, treats, cures, or is standard of care without explicit evidence and non-patient-specific context.

Output

Use:

Claim:
Evidence status:
Safer wording:
Missing source/provenance:

Read references/claim-strength.md for wording.