The Agent Skills Directory

[SAFE]: The skill is entirely descriptive and instructional, providing a framework for legal research triage. It does not perform any file writes, network requests, or system modifications.
[SAFE]: The allowed-tools list is restricted to Read, significantly limiting the agent's attack surface.
[SAFE]: No sensitive data exposure, obfuscation, or remote code execution patterns were detected. The skill includes a 'human-in-the-loop' requirement for legal conclusions, which is a safety best practice for the legal domain.

hierarchia-zrodel-pl