The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) to interact with the repository. It performs read operations via gh issue list and write operations via gh issue create as part of its core functionality.- [PROMPT_INJECTION]: The skill processes untrusted user input and codebase content to generate issue drafts, presenting an indirect prompt injection surface.
Ingestion points: User-supplied feature or bug descriptions and codebase files accessed via read_file or grep_search.
Boundary markers: The skill implements a mandatory human-in-the-loop checkpoint, stating "Do not submit until the user explicitly approves."
Capability inventory: Includes the ability to write files to the .qwen/ directory and execute shell commands via gh.
Sanitization: The skill relies on manual user verification of the drafted content rather than automated sanitization.

create-issue