The Agent Skills Directory

[SAFE]: The skill functions as a prompt-based coach for meditation. It relies on internal markdown templates and examples to generate content and does not use any external tools or network access.
[PROMPT_INJECTION]: There is no evidence of instructions designed to bypass agent safety filters or override core behavioral guidelines.
[DATA_EXFILTRATION]: The skill does not access sensitive local files (e.g., credentials, environment variables) or attempt to transmit data to external servers.
[REMOTE_CODE_EXECUTION]: No scripts or instructions for downloading and executing code from the internet were identified.
[DYNAMIC_CONTEXT_INJECTION]: The skill does not employ the exclamation-backtick syntax for shell execution during initialization.

meditation-coach