The Agent Skills Directory

[SAFE]: The skill is composed entirely of natural language instructions and metadata. It does not include any scripts, executables, or automated commands.
[SAFE]: No network-based exfiltration or external data fetching patterns were detected. The skill operates purely within the text-generation context of the agent.
[SAFE]: There are no requests for elevated privileges, persistent access, or exposure of credentials. The instructions explicitly include guardrails against bullying or inventing false consequences.

intimidation