The Agent Skills Directory

[SAFE]: No security issues were detected. The skill is limited to providing design feedback based on user-provided UI evidence and does not request any dangerous tool permissions.
[SAFE]: The skill explicitly forbids code modification during the initial analysis phase, which aligns with security best practices for minimizing unintended side effects during diagnostic tasks.
[SAFE]: Reference files and handoff paths are handled through local markdown files and internal skill routing, with no evidence of external downloads or remote script execution.

redesign