The Agent Skills Directory

[SAFE]: The skill serves as a technical reference guide for building and publishing Claude Code hooks, focusing on standard development workflows.
[SAFE]: The documentation includes explicit security-focused instructions, such as blocking access to sensitive files (e.g., .env, .pem, .key) and implementing path sanitization to prevent directory traversal.
[SAFE]: References to external resources, such as the hook schema, point to the official repository of the skill author (pr-pm), which is a legitimate vendor resource in this context.
[SAFE]: Recommended commands such as chmod +x and prpm publish are appropriate for the skill's stated purpose of creating and distributing executable scripts.

creating-claude-hooks