The Agent Skills Directory

[SAFE]: No malicious behavior, obfuscation, or unauthorized access patterns were detected. The skill's operations are confined to standard development workflows within a repository.
[COMMAND_EXECUTION]: The skill uses git and gh CLI tools for repository management. All commands are subject to individual user confirmation, and the skill includes explicit prohibitions against destructive actions like force-pushing or rebasing.
[PROMPT_INJECTION]: The instructions incorporate 'anti-sycophancy' guidelines that encourage the agent to notify the user of potential issues (e.g., merging work while files are still in the inbox) before proceeding. This is an operational safety feature and not an attempt to circumvent system-level safety guardrails.

finish