The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes standard development commands, including version control operations via Git and test suite execution using common runners (npm, pytest, cargo, go). These are the primary functions of the skill and are implemented with safety checks.
[PROMPT_INJECTION]: No malicious injection patterns or attempts to override AI safety guidelines were detected. The instructions specifically reinforce safety by preventing the agent from proceeding with failing tests or unconfirmed deletions.
[SAFE]: No obfuscation, credential exposure, or unauthorized network activity was identified. The skill is consistent with its stated purpose of assisting in development workflows.

finishing-a-development-branch