The Agent Skills Directory

[SAFE]: The skill serves as an advisory classifier for agent workflows. It does not perform any sensitive operations, network requests, or file modifications.
[NO_CODE]: The skill consists entirely of Markdown instructions, YAML configuration, and JSON evaluation cases. No executable scripts (Python, JavaScript, or shell) are included in the package.
[SAFE]: The logic includes explicit safety-first rules for 'destructive' operations, ensuring that high-risk actions (such as database deletions or schema breaks) are routed to a 'Discuss' step to prevent accidental or malicious under-escalation.

workflow-gate