The Agent Skills Directory

[SAFE]: The skill consists entirely of a prompt template intended for use in the early stages of product development.
[SAFE]: The disable-model-invocation: true flag in the metadata correctly limits the agent's ability to execute tools, further reducing the risk profile.
[SAFE]: The content focuses on high-level architecture principles such as Role-Based Access Control (RBAC), multi-tenancy isolation, and input validation, promoting secure-by-design implementation practices without introducing any malicious instructions.

write-spec