The Agent Skills Directory

[SAFE]: The skill provides structural and visual guidelines for multiple design systems (Ant Design, Material You, Carbon, etc.). The instructions are strictly informational and do not contain prompt injection or bypass attempts.
[COMMAND_EXECUTION]: The skill includes a Python script (scripts/apply_ui_rules.py) intended to automate the configuration of AI-specific rules (.cursorrules). Analysis of the script confirms it uses standard libraries (os, argparse) and performs only safe, local file write/append operations using predefined design strings. No network activity, dynamic code evaluation, or privilege escalation patterns are present.
[DATA_EXPOSURE_AND_EXFILTRATION]: No sensitive file paths, hardcoded credentials, or suspicious network operations were detected in the skill instructions or supporting scripts.
[OBFUSCATION]: The skill's content is clear and uses standard Markdown and Python without any hidden characters, Base64 encoding, or other obfuscation techniques.

ui-designer