用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/JeremyDwayne/dotfiles --skill babysit-pr命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
All the repos we work in have various AI review bots. They're helpful, even if they're not always right.
If your harness offers tools to monitor a PR, use them so you can respond when comments arrive. Otherwise, poll the PR for new comments and checks.
Only act on checks and comments newer than the latest push. Verify every bot finding against the source before changing code. Fix real findings and CI failures, distinguish repository failures from infrastructure flakes, and reply with a written response when dismissing false positives.
Keep an eye on changes to main and rebase when needed. If an overlapping PR makes this one obsolete, stop monitoring, report it to the user, and ask before closing the PR unless closure was explicitly authorized.
Put poll loops in a script file and run it, so worktree-isolated sessions don't trip the command guard.
If a review bot leaves feedback you believe is not worth addressing, reply and resolve the comment. Format comments left on Jeremy's behalf as:
[MODEL-SLUG] RESPONDING ON BEHALF OF JEREMY
-----
[actual reply]
Do not let review feedback expand the PR beyond the user's original goal. Address real shortcomings, but avoid scope creep.
If nothing has changed, stay quiet rather than posting filler comments. Stop when the review bots and required checks are green on the latest commit. Merge only when the user explicitly requested it; otherwise report that the PR is ready.