Agent skill · research science · aiskillstore

openclaw-medical-skills

Codex adaptation of the OpenClaw Medical Skills library. Use for biomedical, clinical, healthcare AI, genomics, bioinformatics, drug discovery, pharmacovigilance, clinical trials, medical imaging, public health, medical device, regulatory, scientific data analysis, lab automation, and medical research workflows; also use when the user mentions OpenClaw Medical Skills, medical skill library, or any named capability preserved in the OpenClaw capability index.

Why this skill is useful

Adds a comprehensive execution framework for OpenClaw Medical Skills, enabling advanced biomedical and clinical workflows that are not covered in standard AI training.

What it needs

About 4k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.

What this skill does

OpenClaw Medical Skills for Codex Purpose Use this skill as a Codex-native router and execution guide for the OpenClaw Medical Skills capability library. Preserve the original capability set: do not rename, remove, merge, narrow, or reinterpret a listed OpenClaw capability. Adapt only the execution layer from OpenClaw/NanoClaw assumptions to Codex tools, local files, installed skills, web access, Python/R, MCP connectors, and user-provided data. The canonical capability inventory is references/capability-index.md. The complete source text is preserved in references/source-openclaw-medical-skills.md for provenance. Treat OpenClaw/NanoClaw installation instructions in the source as historical context; this folder is the Codex skill. Safety Boundary Use clinical and biomedical outputs for education, research, drafting, triage support, or decision support only. Do not present the output as a definitive diagnosis, prescription, treatment order, device approval, regulatory clearance, or substitute for a qualified clinician, pharmacist, genetic counsellor, institutional reviewer, or regulatory professional. For emergencies, self-harm risk, severe acute symptoms, poisoning, overdose, stroke/MI signs, anaphylaxis, sepsis concern, suicidal intent, or threats to others, tell the user to contact local emergency services immediately; in the United States, mention 911 for emergencies and 988 for suicide or mental health crisis support when relevant. Keep crisis responses short, practical, and supportive. For patient-specific medical advice, ask for missing critical context when needed, state uncertainty, identify red flags, recommend professional evaluation, and separate evidence from interpretation. Do not invent patient data, lab values, guideline recommendations, regulatory status, trial availability, or database results. Reference Navigation Before executing a substantive task, locate the relevant OpenClaw capability: 1. …

How to use it

Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:

@skills aiskillstore/openclaw-medical-skills

View the source on GitHub

Browse the @skills marketplace