The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute git log --oneline -10 locally to analyze project-specific commit history and maintain stylistic consistency.
[SAFE]: It implements a 'Secret File Guard' that proactively identifies sensitive files (such as .env, .pem, .key, and files containing 'secret' or 'password') and instructs the agent to avoid staging them, which is a defensive security practice.
[SAFE]: The skill includes preventative checks for direct commits to the main or master branches, requiring the agent to suggest branch separation to the user, thereby reducing the risk of accidental production regressions.
[SAFE]: No malicious patterns, obfuscation, or unauthorized network activity were detected within the skill instructions.

git-commit