The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/fetch_issue_context.py and the documentation in the reference files utilize the gh and glab CLI tools. The Python implementation uses subprocess.run with a list of arguments and no shell invocation, which is the recommended secure method for executing external processes.
[SAFE]: The skill is explicitly designed to be read-only. It processes external data (issue descriptions and comments) into a structured JSON format and constructs write commands as payloads for user approval rather than executing them directly, mitigating risks associated with unintended modifications or indirect prompt injection.

rhdh-forge