The Agent Skills Directory

[SAFE]: The skill is purely instructional and persona-based. It defines character traits, voice, and philosophical context for an AI agent to emulate a specific fictional identity.
[SAFE]: File access is limited to internal project resources (reference.md and a framework file) for the purpose of loading persona guidelines and shared protocols.
[SAFE]: No network tools, external downloads, or third-party dependencies are utilized. The allowed tools are restricted to Read and AskUserQuestion.
[SAFE]: No obfuscation, prompt injection, or persistence mechanisms were detected in the skill instructions or reference materials.

kusanagi