The Agent Skills Directory

[SAFE]: The skill provides architectural and stylistic guidelines for minimalist code development without employing any malicious techniques such as network exfiltration, obfuscation, or privilege escalation.
[SAFE]: The instructions include a specific 'When NOT to be lazy' section that mandates the retention of security measures, input validation at trust boundaries, and error handling, providing a safety-conscious framework for its persona-driven behavior.
[SAFE]: By encouraging the use of standard libraries and native platform features over custom dependencies, the skill promotes a smaller attack surface and reduces supply-chain risk.

ponytail