The Agent Skills Directory

[SAFE]: The skill functions as a communication style guide and does not contain instructions to execute unauthorized commands or access sensitive files.
[SAFE]: No hardcoded credentials, API keys, or secrets were identified in the skill content.
[SAFE]: The skill does not perform any network operations or external downloads. All referenced paths are local to the expected project environment.
[SAFE]: The 'Persistence' instruction is limited to the AI agent's internal conversational state and does not involve system-level persistence mechanisms like cron jobs or shell configuration modifications.
[SAFE]: No obfuscation techniques, such as Base64 encoding or hidden Unicode characters, were detected.
[SAFE]: The skill explicitly defines exceptions for security warnings and irreversible actions, ensuring safety guidelines remain prioritized even when the compression mode is active.

caveman