The Agent Skills Directory

[COMMAND_EXECUTION]: The skill automates standard development operations using git, npm, pip, poetry, cargo, and go. These commands are only executed after detecting relevant project files (e.g., package.json, requirements.txt), which is expected behavior for a development-focused agent skill.
[SAFE]: Implements mandatory safety verification using git check-ignore to ensure worktree contents are not accidentally committed to the repository. It also includes logic to automatically fix missing .gitignore entries.
[SAFE]: No instances of obfuscation, remote code execution from untrusted sources, or data exfiltration were found. The skill's access to local configuration directories is consistent with its stated purpose of workspace management.

worktrees