The Agent Skills Directory

[SAFE]: The skill operates as a purely instructional guide for system triage. It does not perform any network operations, access sensitive credentials, or attempt to persist on a system.
[NO_CODE]: There are no executable scripts or third-party dependencies included. The skill relies on natural language instructions to guide the agent's existing capabilities.
[PROMPT_INJECTION]: The skill is designed to process external, untrusted data (logs, metrics, and traces) as part of its triage process. Ingestion points: External system logs and metrics (referenced in SKILL.md). Boundary markers: Explicitly instructs the agent to restate 'no-touch boundaries' before action. Capability inventory: Uses the agent's existing tools to perform treatments. Sanitization: Relies on procedural separation of facts and assumptions rather than technical filtering.

medicine