The Agent Skills Directory

[SAFE]: The skill is composed entirely of natural language instructions and communication templates. No executable scripts, binaries, or configuration files are present.- [CREDENTIALS_UNSAFE]: No hardcoded secrets, API keys, or sensitive credentials were found in the skill metadata or body.- [EXTERNAL_DOWNLOADS]: The skill does not perform any network requests, nor does it reference external URLs for downloading code or data.- [PROMPT_INJECTION]: The instructions establish a specific persona and response style for relationship counseling but do not contain patterns designed to bypass safety filters or override core agent constraints.- [COMMAND_EXECUTION]: The skill does not utilize any system commands, shell scripts, or dynamic execution patterns.

taxue-relate