The Agent Skills Directory

[SAFE]: The skill is entirely instructional and does not include any executable scripts or binary files. It functions by providing formatting rules for the AI agent to follow when generating text.
[SAFE]: Explicit safety boundaries are defined in the instructions, specifically stating that the skill must not execute commands such as git commit, git stage, or git amend.
[SAFE]: No obfuscated content, hidden URLs, or suspicious network activity patterns were detected in the skill metadata or body.
[SAFE]: The skill does not request or require any specific tool permissions via frontmatter configuration.

caveman-commit