The Agent Skills Directory

[SAFE]: The skill operates entirely through natural language instructions for the AI agent. It does not contain any scripts, executables, or network-enabled tools.
[SAFE]: File access is limited to reading project-level configuration files (specifically CLAUDE.md or AGENTS.md) to determine persona preferences. This is standard behavior for project-aware agents and does not involve writing to the file system or accessing sensitive system paths.
[SAFE]: The instructions include clear boundaries, explicitly stating that persona narration must not apply to deliverables like code, PR descriptions, or technical reports. This prevents the persona from interfering with technical accuracy or user-facing work products.

dispel