The Agent Skills Directory

[SAFE]: The skill is entirely instructional and focused on formatting the agent's output into specific labels (e.g., 'Do this first', 'Next action') to reduce cognitive load for the user.
[SAFE]: No network access, credential handling, or file system operations were detected. The skill operates solely within the text conversation context.
[SAFE]: Includes explicit safety boundaries prohibiting the diagnosis of mental health conditions and providing guidance for emergency situations.
[SAFE]: References are from well-known and reputable sources including the World Health Organization (WHO) and major book publishers.
[PROMPT_INJECTION]: While the skill uses strict output constraints and instructs the agent to omit intros/outros, these are design choices for 'Overloaded Mode' to minimize user stress and do not constitute malicious concealment of agent activity.

overloaded-mode