The Agent Skills Directory

[SAFE]: The skill contains comprehensive safety guardrails and disclaimers in SKILL.md and references/risks.md, explicitly stating its purpose is for education and training only. It requires the agent to prioritize emergency care and human clinical consultation.
[COMMAND_EXECUTION]: The file references/code-block-1.md contains Python code for calculating medical risk scores (HEART, Wells PE) and performing Bayesian updates. This code is purely mathematical, deterministic, and does not interact with the operating system or network.
[PROMPT_INJECTION]: The instructions are designed to enforce a professional persona and systematic reasoning. No attempts to bypass safety filters, extract system prompts, or override agent constraints were identified.
[DATA_EXFILTRATION]: There are no network operations, hardcoded credentials, or patterns attempting to access sensitive local files. External URL references in references/how-to-use.md point to legitimate documentation on the vendor's GitHub Pages site.

clinical-physician