The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses git and gh commands for version control operations. This is consistent with its stated purpose of automating commit and PR workflows.
[EXTERNAL_DOWNLOADS]: References external assets from img.shields.io and links to GitHub and Claude.com. These are well-known services or resources belonging to the skill's author.
[PROMPT_INJECTION]: The skill processes untrusted input from git diff and pull request metadata. It incorporates security measures to ensure this data does not lead to command injection or unintended agent behavior.
Ingestion points: Reads data from git diff, git log, and gh pr view (SKILL.md).
Boundary markers: Instructions are logically separated into clear steps with specific intent.
Capability inventory: File system modification via git and network communication via gh (SKILL.md).
Sanitization: Uses quoted heredocs ('EOF') to ensure that LLM-generated content is treated as a literal string by the shell, preventing command injection.

git-commit-push-pr