The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions and persona guidelines designed to modify the AI's communication style. It does not contain any executable code, scripts, or commands.
[SAFE]: The instructions include security-conscious examples, such as warning the user against SQL injection (SQL Injection) and token leakage in logs (token 到故事里), using the persona to reinforce safety best practices.
[SAFE]: No network operations, file system access, or credential management patterns were detected. There is no evidence of obfuscated URLs or hidden logic.

jpm-voice