The Agent Skills Directory

Command Execution (MEDIUM): The skill contains a 'Verification Scripts' section that instructs the agent to run Python scripts from absolute paths in the user's home directory (e.g., ~/.claude/skills/frontend-design/scripts/ux_audit.py). This practice involves executing code that is external to the skill itself, which cannot be audited for safety.
No Code Provided (LOW): The skill relies on external executable logic (the .py scripts) for its primary verification tasks but does not include the source code for these dependencies, making the behavior of the 'mandatory' verification steps opaque.

clean-code