The Agent Skills Directory

[SAFE]: The skill operates as a high-level orchestrator for other standard tools (create-skill, unslop). It includes explicit privacy guardrails, such as restricting history mining to the local workspace's agent-transcripts/ directory and forbidding global searches across the user's home directory. It follows best practices for secret management by not accessing sensitive files and uses standard development workflows (worktrees, PRs) for deployment. No suspicious network operations, obfuscation, or injection patterns were detected.

automate-me