The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes git and gh (GitHub CLI) commands to interact with the local repository and the remote GitHub instance. These operations are standard for the skill's stated purpose of pushing branches and creating pull requests.
[EXTERNAL_DOWNLOADS]: The skill performs remote calls using gh api to fetch Pull Request templates from GitHub repositories. This behavior targets a well-known service and is used to retrieve configuration content.
[PROMPT_INJECTION]: The skill processes data from git commit messages, diffs, and remote PR templates to generate pull request content, presenting a surface for indirect prompt injection.
Ingestion points: Commit messages (subjects and bodies) and diff content from the local git history, as well as template files retrieved from GitHub via API.
Boundary markers: No explicit delimiters are specified in the instructions for separating processed data from the system prompt.
Capability inventory: The skill can execute shell commands for git pushing and PR creation, and can write to local configuration files.
Sanitization: The skill employs an AI-driven 'synthesis' step to describe changes in the agent's own words rather than raw copying. It also requires the output to pass a formatting validation script (validate.sh) and mandates explicit user review and confirmation before calling the final gh pr create command.

pull-request