babysit
Watch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user wants the agent to shepherd it without re-prompting.
- License 许可
- MIT
- 最近更新
- 2026-11-04
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- babysit
- description
- Watch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user wants the agent to shepherd it without re-prompting.
03 SKILL.md 正文
Babysit a PR
Claude Code analog of Cursor's built-in /babysit. The implementation is a loop over gh CLI plus the Claude Code loop skill for pacing.
Platform note. On Codex or another non-Claude runtime, the Claude tool names and Claude built-in skills named below (loop, AskUserQuestion) are Claude defaults. Resolve them via codex-tools.md.
Inside engineering-mode, the Babysit playbook (../engineering-mode/playbooks/babysit.md) supersedes this skill: it owns mode declaration, the merge frontier, stack safety, and the watch-pr watcher. This skill stays the standalone /babysit entry point for a single PR outside a engineering-mode run.
When to use
- There's an open PR and the user explicitly wants it kept green, and you are not already inside a engineering-mode run (the playbook owns that case).
- The user invokes
/babysitdirectly. - A subagent that opens a PR does NOT babysit — return to the parent and let the parent decide.
Steps
-
Fetch PR state.
gh pr view <number> --json number,title,state,mergeable,reviewDecision,statusCheckRollup,mergeStateStatus,comments,reviews -
Triage in priority order.
- Merge conflicts (
mergeStateStatus == DIRTY): rebase or mergemain; resolve; force-push only if the branch is yours and not shared. - Failing checks (
statusCheckRollupentries withconclusion: FAILURE): pull logs withgh run view <run-id> --log-failed. Root-cause the failure; fix the underlying code or test; commit; push. - Review comments from human reviewers (
gh pr view --json comments,reviews): act only on feedback you actually agree with. When a comment has a single mechanical answer — a rename, a guard clause, a formatting nit — make the edit and quote the comment in the commit message. When it hinges on a judgement call, or you can't tell what's being asked, don't guess: leave it and reply with what you would have done. - Review-bot comments (Bugbot and similar automation): classify as fix, dismiss, or ask before acting, per
../engineering-mode/references/bugbot-triage.md. Follow the rubric's Ask by default categories, including security, data, and high-severity findings.
- Merge conflicts (
-
Loop. Use the Claude Code
loopskill to pace re-checks. Pick the interval from what you're watching:- Active CI run: poll
gh pr checks --watch(it blocks until checks finish, so no separate loop interval needed). - Awaiting reviewer: 20–30 min heartbeat.
- Idle but want to catch new comments: hourly.
- Active CI run: poll
-
When to stop.
- Build is green, every comment resolved, branch merges cleanly → call it ready.
- You've run three rounds of fix → push → recheck and it still isn't fully green → stop, summarise what's still broken, and hand control back.
- The next fix would force a design choice → pause and put it to the user with
AskUserQuestion.
-
Report. Summarize fixes applied, comments addressed, comments deferred (with reason), current PR status. Cite each commit by SHA.
Hard rules
- Don't rewrite history on a branch others may have pulled. If a rebase or force-push looks necessary, clear it with the user first.
- Don't tweak a test's expected values just to get a pass. Only change an assertion when the behaviour genuinely changed and the assertion was pinned to the old behaviour.
- Never skip hooks (
--no-verify). - Never bypass a failing check by marking it as not required.
gh pr readyonly when all checks are green and no unresolved review comments remain.
Cross-refs
engineering-modeopens here after a PR is opened.- Use
interrogatebefore opening if the diff is contested; once open, babysit takes over. - Use
unslopon any prose you write here (PR comments, commit messages, status reports).
Provenance
This is a Claude Code analog of Cursor's /babysit, not a port — Cursor's implementation is closed source. The skill is independently authored, with its own prose and structure; the workflow is informed by Cursor's public /babysit behavior. The only overlap with other PR tools is the gh CLI commands it runs, which are functional invocations rather than copied text.
04 同仓库更多 Skills
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, stacked PRs, or keeping tests and docs with code.
why
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
what-did-i-get-done
Summarize authored commits over a user-specified time period into a concise update
unslop
Cut AI tells from any writing.
typescript-best-practices
TypeScript best practices. Use when reading or editing any .ts or .tsx file.
thermo-nuclear-code-quality-review
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.