The Agent Skills Directory

[SAFE]: The skill's primary function is to enforce a specific communication format (brevity/token reduction). It does not perform any sensitive file operations, network requests, or code execution.
[PROMPT_INJECTION]: The skill uses instructional language to maintain a persona ('Once triggered, every reply is active', 'Do not drift back to nonsense'). However, these instructions are focused on formatting and do not attempt to override the underlying AI safety guidelines or bypass security filters.
[SAFE]: The skill demonstrates good security practices by including an 'Auto-Clarity Exception', which directs the agent to revert to standard, clear language when delivering security warnings or confirming irreversible operations.

caveman