The Agent Skills Directory

[SAFE]: The skill provides stylistic and structural guidelines for AI-generated text, intended to improve readability in terminal and desktop environments. It does not introduce any new technical capabilities or tools.
[SAFE]: No external scripts, packages, or remote code patterns are defined or requested. The examples provided (e.g., npm test, psql) are standard development commands used for illustrative purposes in prose.
[SAFE]: The instructions explicitly state that the rules apply to the 'what is left' after complying with the system harness, ensuring that safety filters and platform requirements take precedence.
[SAFE]: References to sensitive file patterns like .env.staging and DATABASE_URL appear strictly within hypothetical error-reporting templates to demonstrate good communication practices, not as instructions to access or exfiltrate credentials.
[SAFE]: The 'Persistence' section refers to maintaining a consistent communication style throughout a chat session, rather than attempting to gain technical persistence on the underlying operating system.

lucid