Medicine
v1.0.0Support medical understanding from patient education to clinical practice and research.
⭐ 2· 1.7k·3 current·3 all-time
byIván@ivangdavila
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description ('Medicine') match the SKILL.md content, which provides audience-specific guidance for patients, students, clinicians, researchers, and educators. The skill requests no binaries, env vars, or config paths — all proportional to an instruction-only guidance skill.
Instruction Scope
SKILL.md contains explicit, scoped runtime instructions (ask role, avoid diagnosis, escalate emergencies, cite evidence, adapt language). It does not instruct the agent to read system files, access unrelated env vars, or transmit data to external endpoints. Instructions are focused on content generation and safety.
Install Mechanism
No install spec and no code files — lowest-risk model: nothing is downloaded or written to disk. Runtime behavior will be solely driven by the SKILL.md instructions.
Credentials
No required environment variables, credentials, or config paths are declared. The guidance to 'cite sources' is content-level only and does not imply access to external credentials or APIs.
Persistence & Privilege
always is false and default autonomous invocation is allowed. That is normal, but because this skill generates medical guidance, consider whether you want the agent to invoke it without explicit user confirmation — autonomous medical content can have higher risk if used without oversight.
Assessment
This skill is internally consistent and does what its description says: it provides rules for generating medical explanations without requesting any system access. Before installing, consider: (1) Do you want the agent to be allowed to invoke medical guidance autonomously? If not, disable autonomous invocation or require user confirmation. (2) The skill asks the model to 'cite sources' but does not include a mechanism to fetch or verify them — watch for fabricated or out-of-date citations and verify any clinical claim against trusted guidelines. (3) Never rely on this skill for individual diagnoses, prescriptions, or emergency decisions — maintain human clinician oversight. If you plan to use it in clinical workflows, add auditing, logging, and a human-in-the-loop policy.Like a lobster shell, security has layers — review code before you run it.
latestvk97ayd8dvvcne0pwht5ad1jdhd80wfzx
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
⚕️ Clawdis
OSLinux · macOS · Windows