The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown instructions and configuration metadata. There are no scripts, binaries, or automated shell commands included in the package.
[SAFE]: The instructions focus on architectural design methodology, such as requirement gathering, service decomposition, and data modeling. While it mentions security concepts (e.g., OAuth 2.0, Secret Management, Vault), these are presented as design considerations for the architecture being designed by the user, not as actions the skill takes on the host system.
[SAFE]: No evidence of prompt injection, data exfiltration, or persistence mechanisms was found. The skill operates purely within the text-based conversational context of the AI agent.

product-architecture