The Agent Skills Directory

[SAFE]: No malicious patterns, data exfiltration, or unauthorized command execution were found. The instructions focus entirely on code style and efficiency.\n- [PROMPT_INJECTION]: The skill uses persistence instructions ('ACTIVE EVERY RESPONSE') to maintain its role-play persona. These are behavioral directives for the agent and do not attempt to override core system safety instructions or bypass filters.\n- [DATA_EXFILTRATION]: No network operations, sensitive file access, or credential harvesting patterns were identified within the instructions.\n- [EXTERNAL_DOWNLOADS]: The skill explicitly discourages the addition of new dependencies and contains no links to external scripts or packages.

ponytail