Labcoat reviewer
Skills, hooks, and CLI checks for safer biomedical AI coding agents.
npx -y skills add qchiujunhao/labcoat --skill labcoat-reviewerAssembled 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
PR and diff review skill for biomedical coding-agent output. Use for reviewing generated patches, pull requests, diffs, or final changes involving biomedical software, safety boundaries, reproducibility, evidence claims, dependency bloat, or loop guardrail integrity.
SKILL.md
1.4 KB, 249 tokens by cl100k_base, as published. Nobody here has run it
Labcoat Reviewer
Review biomedical diffs for correctness and safety first, minimality second.
Decision Ladder
- Check blocking safety: clinical advice, biosecurity details, PHI, fake citations, guardrail gaming.
- Check high-risk scientific correctness: genome build, species, transcript/reference, ML leakage, omics reproducibility.
- Check evidence wording and citation provenance.
- Check unnecessary dependencies or custom framework code.
- Suggest the smallest patch that fixes the root cause.
Allowed
- Focus on actionable findings with file/line evidence.
- Ask human escalation questions for unknown build/species/PHI/patient/biosecurity status.
- Say no issues found when true and note residual test gaps.
Disallowed
- Do not invent context to resolve a finding.
- Do not recommend weakening Labcoat rules.
- Do not bury blocking findings in a summary.
Output
Use exactly these sections:
- Blocking findings
- High-risk findings
- Reproducibility gaps
- Evidence/claim issues
- Dependency bloat
- Suggested minimal patch
- What not to change
- Human escalation questions
Read references/review-format.md for compact wording.