The Agent Skills Directory

[SAFE]: The skill is a collection of instructions and templates for a UX Architect agent. It provides boilerplate CSS, JavaScript for theme management, and Markdown templates for technical handoffs.
[COMMAND_EXECUTION]: The suggested workflow includes using cat and grep to read project context from local files (e.g., ai/memory-bank/site-setup.md). These commands are intended for the agent to use locally to gather information and do not represent a security risk in this context.
[INDIRECT_PROMPT_INJECTION]: The agent is designed to process external project specifications and task lists. While this represents an ingestion point for untrusted data, the agent's capabilities are limited to producing text-based documentation and code templates, and it does not possess high-risk capabilities such as network exfiltration or direct command execution based on untrusted input.

UX Architect