The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional text and operating principles for agentic engineering workflows. It focuses on task decomposition, model routing, and review strategies.
[SAFE]: No scripts, shell commands, or network operations are included in the skill. There is no code execution surface to evaluate for traditional vulnerabilities.
[SAFE]: No external URLs or dependencies are referenced, eliminating risks related to data exfiltration or unverifiable remote code.
[SAFE]: The instructions do not contain prompt injection attempts or efforts to bypass safety guidelines; in fact, the skill explicitly encourages focusing on security and auth assumptions during code review.

agentic-engineering