The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes standard git commands (including status, diff, log, branch, rev-parse, fetch, checkout, stash, and push) and GitHub CLI commands (gh pr list, gh pr view, gh pr create, gh pr edit) to perform its primary function of managing repository state and pull requests.
[DYNAMIC_CONTEXT_INJECTION]: Employs the !command syntax in SKILL.md to dynamically fetch the repository's default branch and check for existing pull requests at the time the skill is loaded.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the local repository to generate PR descriptions, creating an indirect prompt injection surface.
Ingestion points: The skill reads output from git diff and git log to provide context for the description generation logic.
Capability inventory: The skill has the ability to execute shell commands (git, gh) and write to temporary files for PR body management.
Boundary markers: No explicit delimiters or guardrails are defined for the interpolation of diff content into the agent's prompt.
Sanitization: The instructions provide a logical filter by asking the agent to interpret the purpose of the changes rather than repeating the diff verbatim.
[EXTERNAL_DOWNLOADS]: Includes a branding badge hosted on img.shields.io and a reference to the project's repository on github.com/raptoravis/tunan. These are well-known services and vendor-related resources.
[SAFE]: The skill implements protective measures by explicitly warning the agent against using git add . or git add -A to prevent the accidental inclusion of sensitive files like .env, build artifacts, or generated files in commits.

commit-push-pr