The Agent Skills Directory

[SAFE]: The skill's primary function is to enforce a 'minimalist' coding philosophy, prioritizing the standard library and existing code over new dependencies. It does not perform network operations, access sensitive files, or execute external scripts.
[SAFE]: The instructions include specific safeguards in the 'When NOT to be lazy' section, explicitly stating that security measures, input validation, and error handling must never be simplified or removed.
[PROMPT_INJECTION]: The skill uses strong instructional language such as 'ACTIVE EVERY RESPONSE' and 'No drift back to over-building' to maintain a specific persona. These are stylistic constraints and do not attempt to override the underlying AI safety filters or exfiltrate data.

ponytail