The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions and architectural diagrams. It does not include any executable scripts, binary files, or configuration files that could trigger malicious actions.
[SAFE]: There are no tool invocations or allowed-tools configurations. The skill operates purely within the context of providing guidance on how to use other skills.
[SAFE]: No network operations, data exfiltration patterns, or hardcoded credentials were identified. The skill does not attempt to access sensitive local files or remote servers.
[SAFE]: The content promotes safe and defensive engineering practices, such as surfacing assumptions, managing confusion actively, and maintaining scope discipline, which align with security best practices.

using-agent-skills