The Agent Skills Directory

[SAFE]: The skill primarily defines linguistic constraints to minimize token usage by stripping filler words, pleasantries, and articles. It does not include any commands for file access, network operations, or tool execution.
[SAFE]: The 'Auto-Clarity Exception' rule specifically requires the agent to drop the persona for security warnings, irreversible action confirmations, and sequences where clarity is paramount, maintaining safety and user awareness.
[SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found. The skill operates entirely within the scope of text formatting and persona management.

caveman