The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized network operations were detected. The skill acts as a process coordinator for local design tasks.
[COMMAND_EXECUTION]: The skill directs the agent to use external tools such as Playwright MCP or the Cursor IDE Browser to capture screenshots during the review phase. These are legitimate tools used for the stated purpose of validating frontend designs.
[DATA_EXFILTRATION]: The skill manages project data locally in a structured .design/ directory. There is no evidence of sensitive data being harvested or sent to external servers.
[PROMPT_INJECTION]: The skill uses natural instructional language to guide the agent's behavior through sequential phases. It does not contain instructions that attempt to bypass safety filters or override core agent guidelines.

design-flow