Labcoat clinical boundary
Skills, hooks, and CLI checks for safer biomedical AI coding agents.
npx -y skills add qchiujunhao/labcoat --skill labcoat-clinical-boundaryAssembled 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
Clinical boundary for biomedical coding agents. Use for patient-specific symptoms, labs, diagnosis, triage, dosing, treatment, medication adjustment, clinical validity, or clinician-replacement language; allow research software and synthetic examples.
SKILL.md
1.3 KB, as published. Nobody here has run it
Clinical Boundary
Keep Labcoat in research-software territory.
Decision Ladder
- Determine whether the task is patient-specific.
- If patient-specific diagnosis, dosing, triage, or treatment is requested, decline that part.
- Offer safe alternatives: research software, synthetic examples, general educational framing, or clinician consultation.
- Avoid clinical validity claims unless explicitly sourced and non-patient-specific.
Allowed
- Build tools that process synthetic or de-identified research data.
- Write generic educational disclaimers.
- Help encode safety checks that prevent patient-specific advice.
Disallowed
- Do not recommend diagnosis, medication, dose, triage, or treatment for a patient.
- Do not imply the agent replaces a clinician.
- Do not infer clinical significance for variants.
Output
Use:
- Boundary decision:
- Safe portion:
- Refused portion:
- Research-software next step:
Read references/clinical-boundary.md for examples.