tommy-ca/pstack/babysit
Claude Code and agent skill by tommy-ca/pstack
- community
Checking that the SKILL.md file is still in the repository.
Watch an open PR — fix failing CI, handle straightforward review comments, and drive it to a mergeable state. Use after opening a PR when the user wants the agent to shepherd it without re-prompting.
Install
npx vskill@latest install tommy-ca/pstack/babysitSKILL.md
Babysit a PR
On Codex, Grok, Antigravity, OMP, or OpenCode, consult the respective host mapping under skills/poteto-mode/references/ before following this skill.
Portable agent workflow for shepherd-to-green pull requests across agent harnesses. The implementation is a loop over gh CLI plus host-native pacing.
Inside poteto-mode, the Babysit playbook (`../poteto-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 poteto-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 poteto-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.
``bash gh pr view <number> --json number,title,state,mergeable,reviewDecision,statusCheckRollup,mergeStateStatus,comments,reviews ``
- Triage in priority order.
- Merge conflicts (
mergeStateStatus == DIRTY): run the fix-merge-conflicts skill. Force-push only if the branch is yours and not shared. - Failing checks (
statusCheckRollupentries withconclusion: FAILURE): run the fix-ci skill. Root-cause the failure; fix the underlying code or test; commit; push. - Before you trust any failing or passing check, scope the gate to the patch instead of the whole matrix:
python scripts/verify_portable.py select-checks --base <base-ref> [--head <sha>]names the minimal checks that can fail for the changed paths (docs-only changes do not select the runtime matrix). The PR's forge commands still own the overall check state;ghis the default andoriginthe fallback whencommand -v originresolves. Do not assume a universal forge CLI or package manager. - Review comments: run the get-pr-comments skill for the summary, then 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 fix/dismiss/ask before acting, per `bugbot-triage.md`. Ask by default on security, data, and high-severity findings.
- Loop. Use the host's native pacing capability (
schedule,monitor, or background loop) 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.
- 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 the host's question or confirmation capability (
human.ask).
- 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 quote an old result as current CI. A verdict is bound to the head SHA and the
git patch-idof the base..head diff; re-check freshness withselect-checks --base <base-ref> --receipt <path>after any rebase, retarget, or new commit. A changed patch-id invalidates it; a pure rebase with an identical patch-id keeps it. - Report
FAILandBLOCKEDas they are. A skip is not a pass. - 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
- Opening a PR does not start a babysit; inside poteto-mode the Babysit playbook owns the request and starts only when asked.
- 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
Standalone host-portable entry point for shepherd-to-green pull requests across all 5 harnesses. The workflow is driven via standard gh CLI commands and host-native scheduler integrations.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/babysit/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/tommy-ca/pstack/babysit)