The Agent Skills Directory

[SAFE]: The skill provides high-level procedural logic for Pull Request management with a strong emphasis on security controls, including identity verification and multi-stage authorization gates.
[NO_CODE]: The skill consists exclusively of markdown instructions and does not contain any executable scripts, binaries, or command-line sequences for analysis.
[INDIRECT_PROMPT_INJECTION]: Although the skill processes external Pull Request data, it explicitly includes defensive measures such as 'recheck the remote predecessor before every push', 'exact-candidate contracts', and a requirement for explicit owner authorization for every merge group, effectively mitigating risks from untrusted external content.

merge-prs