The Agent Skills Directory

[COMMAND_EXECUTION]: The github_project_setup.py script utilizes subprocess.run to execute the GitHub CLI (gh) for performing GraphQL queries against the GitHub API.
[DYNAMIC_EXECUTION]: The test suite test_github_project_setup.py employs importlib.util to dynamically load the setup script, which is a standard pattern for testing standalone Python scripts.
[EXTERNAL_DOWNLOADS]: The skill fetches workflow syntax and triggers from GitHub's official documentation at docs.github.com and retrieves Node.js version information from nodejs.org. These are well-known and trusted sources.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to monitor and process GitHub Action workflow logs and external documentation.
Ingestion points: Ingests workflow run logs for debugging (log-failed) and searches through logs via regex (grep). It also fetches Markdown files from external GitHub documentation.
Boundary markers: The instructions do not specify explicit delimiters or warnings for the agent when processing log content.
Capability inventory: The skill is capable of creating, editing, and closing issues, labels, milestones, and project items using the repository's credentials.
Sanitization: No explicit sanitization or filtering logic was observed in the log processing command descriptions.

github-workflows