The Agent Skills Directory

[SAFE]: No security issues were detected. The skill provides a set of guidelines and a persona for the agent to act as an architecture critic.
[NO_CODE]: The skill does not include any scripts, binaries, or automated tools. It operates purely through natural language instructions.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to process external architectural designs (untrusted data), it lacks any high-risk capabilities such as file system writing, network requests, or command execution that could be exploited via injection. The output is limited to text-based architectural findings.

architecture-critic