The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses several Python scripts that execute commands via subprocess.run to interact with the GitHub CLI (gh).
In scripts/fetch_pr_checks.py, it executes gh pr view, gh pr checks, gh run list, and gh run view to retrieve CI status and logs.
In scripts/fetch_pr_feedback.py, it uses gh repo view, gh pr view, and gh api (including GraphQL) to fetch and prioritize review comments.
In scripts/monitor_pr_checks.py, it repeatedly calls gh pr view and gh pr checks to poll for completion of CI runs.
In scripts/reply_to_thread.py, it uses gh api graphql to post replies back to the pull request threads.
[SAFE]: All command executions are restricted to the official GitHub CLI tool and target legitimate repository metadata. The logic for priority categorization (LOGAF scale) and log snippet extraction is implemented as local Python logic and does not involve remote code execution or data exfiltration to non-vendor domains.

iterate-pr