The Agent Skills Directory

[SAFE]: The skill content is purely instructional, providing a methodology for creating logic and UI prototypes in isolated scratch branches. It does not contain executable malicious scripts or data exfiltration patterns.
[COMMAND_EXECUTION]: The skill references standard development commands such as pnpm dev and bun run as part of the intended workflow for launching UI prototypes. These are standard developer tools and are used within the context of the skill's stated purpose.
[INDIRECT_PROMPT_INJECTION]: While the skill establishes a workflow for processing user-defined design questions into code, which is a potential surface for indirect injection, it includes no malicious instructions or bypasses, and the primary purpose is legitimate developer assistance.

prototype