The Agent Skills Directory

[SAFE]: The skill consists of natural language instructions for the agent to follow during a design phase. It does not include any scripts, executable binaries, or remote code dependencies.\n- [COMMAND_EXECUTION]: The skill instructs the agent to create a 'designs' directory and write markdown files to it. These actions are within the normal scope of an assistant's file management capabilities and are directed toward a specific, non-sensitive path.\n- [DATA_EXPOSURE]: The skill involves processing user input to generate design documentation. It does not attempt to read sensitive files (e.g., SSH keys, AWS credentials) or exfiltrate data to external domains.

discovery