The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses dynamic context injection (the !command syntax) to execute date and psql --version when the skill is loaded. These are benign, read-only commands used to provide metadata (timestamp and tool version) for the generated documentation.\n- [SAFE]: The skill scans local source code files to generate documentation and writes the result to a specified directory. No network exfiltration, unauthorized sensitive file access, or remote code execution patterns were detected.

data-model