The Agent Skills Directory

[SAFE]: The skill is entirely declarative, containing only markdown instructions without any associated scripts, binaries, or executable code.
[SAFE]: No network operations (such as curl, wget, or fetch) or external URL downloads were detected.
[SAFE]: The skill explicitly promotes security and reliability best practices, such as implementing human confirmation gates for side-effecting actions and treating external tool outputs as untrusted data to prevent injection attacks.
[SAFE]: No sensitive file paths, hardcoded credentials, or persistence mechanisms were found.

agent-design-review