The Agent Skills Directory

[SAFE]: The skill is purely instructional and governs interaction logic for clarifying ambiguous tasks. It focuses on communication strategy rather than execution.
[SAFE]: No malicious patterns such as prompt injection, obfuscation, or unauthorized data access were found in the instructions or metadata.
[SAFE]: The skill limits its execution environment to read-only tools (Read, Glob, Grep) and explicitly instructs the agent to avoid running mutating commands or committing to plans until user requirements are clarified, which is a security best practice.

clarify-underspecified