The Agent Skills Directory

[SAFE]: The skill's primary logic in SKILL.md focuses on logical reasoning and adversarial debate without requesting any special permissions or tools. It includes robust guardrails that explicitly forbid the use of role-play to bypass safety filters or advocate for harm.
[SAFE]: The validation scripts (scripts/validate.py and scripts/test_skill.py) perform standard software quality checks, such as verifying required headings and Python syntax, using only local file system access in a controlled environment.
[SAFE]: No evidence of data exfiltration, credential exposure, or remote code execution was found. The skill does not define any external dependencies or network operations.

devils-advocate