The Agent Skills Directory

[SAFE]: The skill is composed entirely of markdown documentation. No executable scripts, binaries, or system configurations are included, precluding risks associated with code execution or persistence.\n- [SAFE]: A thorough review of the 15 files shows no evidence of obfuscated content, hardcoded credentials, or sensitive data access patterns. All referenced templates are pedagogical in nature and intended for legitimate prompt optimization.\n- [SAFE]: The skill does not perform any network operations or external downloads. All content is stored locally within the skill directory structure.\n- [SAFE]: No prompt injection or jailbreak patterns were identified. The instructions guide the agent on how to better structure its output and reasoning for the user without attempting to override system-level safety protocols.

prompt-engineering