The Agent Skills Directory

[SAFE]: The skill consists of instructional markdown files providing guidance on software architecture and project management. No executable scripts, dangerous commands, or unauthorized network operations were found.
[SAFE]: Mentions of external tools and frameworks such as claude-flow, agentdb, and ruvector are presented within the context of architectural evaluation and technology discovery. These resources align with the vendor's own ecosystem and do not represent a security risk.
[SAFE]: No prompt injection or obfuscation patterns were detected. The documentation explicitly reinforces safety by stating that AI assistants will not and should not bypass safety constraints.
[SAFE]: The proposed 'Spec Driven Development' framework encourages best practices such as machine-enforceable rules, automated testing, and human verification checkpoints, which improve the security posture of the software being built.

human-architect-mindset