The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use the subagent tool with actions such as create, get, and update. These operations are used to manage baseline test agents with specific configurations (e.g., setting inheritSkills to false) to ensure a clean testing environment for new instructions.
[DATA_EXPOSURE]: The instructions involve reading and writing project-level documentation and configuration files, such as AGENTS.md, CLAUDE.md, and system prompts. This access is consistent with the skill's stated purpose of refining agent behavior through text development.
[SAFE]: No network operations, credential harvesting, or execution of untrusted code from remote sources were detected. The skill relies on local project structure and internal platform tools.

write-skill