The Agent Skills Directory

[SAFE]: The skill is composed exclusively of natural language instructions and markdown documentation. No scripts, binaries, or other executable files are included.
[SAFE]: There are no signs of prompt injection, obfuscation, or data exfiltration. The instructions for 'relentless' interviewing and codebase exploration are consistent with the skill's primary purpose of plan review and design stress-testing.
[NO_CODE]: As a no-code skill, it does not introduce technical vulnerabilities like remote code execution, privilege escalation, or unsafe dependency management.

grill-me