The Agent Skills Directory

[COMMAND_EXECUTION]: The github_project_setup.py script uses subprocess.run to execute the GitHub CLI (gh) for performing GraphQL mutations and API calls. This is a functional requirement for managing GitHub Projects V2 and other features not natively supported by the PyGithub library.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which creates a vulnerability surface.
Ingestion points: The github_project_setup.py and experiment_cleanup.py scripts fetch issue titles, milestone descriptions, and project item metadata from GitHub repositories. The ci_monitor.cjs tool (referenced in SKILL.md) reads workflow execution logs.
Boundary markers: Explicit boundary markers or instructions to ignore embedded commands within the ingested data are absent.
Capability inventory: The skill has the capability to execute shell commands via gh (subprocess), write to the repository (creating labels/issues), and perform network operations via the GitHub API.
Sanitization: Standard string truncation is observed in logging, but no specific sanitization of issue content is performed before processing.
[EXTERNAL_DOWNLOADS]: The skill instructions include fetching live documentation from docs.github.com and checking Node.js LTS versions from nodejs.org. These are well-known and trusted services.
[DYNAMIC_EXECUTION]: The test suite test_github_project_setup.py uses importlib to dynamically load the automation script as a module for unit testing. This is a standard development practice for testing standalone scripts.

github-workflows