The Agent Skills Directory

[SAFE]: No security threats were detected. The skill consists of markdown instructions and research data designed to guide an AI's personality and reasoning style without involving executable logic.\n- [PROMPT_INJECTION]: The character persona instructions are standard and do not attempt to bypass safety filters, extract system prompts, or manipulate agent behavior outside of the intended role-play.\n- [DATA_EXFILTRATION]: No network operations or sensitive data access patterns were identified. The skill does not request access to credentials or private file paths.\n- [COMMAND_EXECUTION]: There are no shell commands, scripts, or subprocess instructions present in the skill files.

mayun-perspective