The Agent Skills Directory

[SAFE]: The skill follows established software development best practices for automating git workflows. It includes clear logic gates to prevent redundant commits or accidental merges into protected branches.
[COMMAND_EXECUTION]: The skill utilizes native command-line interfaces for git management (git) and repository hosting platforms (gh for GitHub, glab for GitLab). These operations are functional requirements for the skill's stated purpose and are performed based on the repository's current state.
[PROMPT_INJECTION]: The skill processes data through placeholders like {pr-body-extra} and {commit-context}. While this represents an ingestion point for external data, the instructions strictly define how this data is used (concatenation into PR bodies and commit messages), posing no significant security risk to the agent's core instructions.
[EXTERNAL_DOWNLOADS]: The skill references a dependency on the git-commit skill and provides instructions for its installation from the author's own repository (FuDesign2008/open-skills). This is a legitimate resource managed by the skill's author.

delivery-discipline