The Agent Skills Directory

[SAFE]: No malicious patterns or prompt injection attempts were found. The skill maintains its role as an information architecture expert without attempting to bypass safety filters or override system constraints.\n- [SAFE]: The skill's instruction to check for and read .agents/product-marketing-context.md is a safe, documented behavior for context-aware agents and does not target sensitive system credentials or private user files.\n- [SAFE]: No obfuscation, remote code execution, or suspicious network activities are present. The skill relies entirely on its own instructions and local reference files.\n- [SAFE]: All external references within the skill point to other skills in the same environment or provided documentation, representing a safe and contained ecosystem.

site-architecture