Przejdź do treści
Biblioteka skilli
Programowanie · Automatyzacja

babysit

/babysit

Pilnuje otwartego PR: naprawia nieudane CI, obsługuje proste uwagi z przeglądu i doprowadza go do stanu gotowego do scalenia, bez ponownych poleceń.

Repozytorium
pstack ↗
Licencja
MIT
Ostatnia zmiana repozytorium
26.10.2026

Ocena i bezpieczeństwo

100/ 100Klasa: dobry
Format25 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść35 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena15 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
1
Skrypty
0
Komentarze HTML
0
Adresy URL w SKILL.md
0
Przestarzałość

Brak sygnałów. Repozytorium zmienione 26.10.2026, bez odwołań do wycofanych modeli i API.

Licencja

MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.

Co robi i kiedy

Pilnuje otwartego PR: naprawia nieudane CI, obsługuje proste uwagi z przeglądu i doprowadza go do stanu gotowego do scalenia, bez ponownych poleceń.

Oryginalny opis (EN)

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.

Jak działa

  1. When to use
  2. Steps
  3. Hard rules
  4. Cross-refs
  5. Provenance
Sekcje z nagłówków SKILL.md, w oryginale · 63 linii, 761 słów
Podgląd SKILL.md
---
name: babysit
description: 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.
---

# 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`](../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 `/babysit` directly.
- A subagent that opens a PR does NOT babysit — return to the parent and let the parent decide.

## Steps

1. **Fetch PR state.**

   ```bash
   gh pr view <number> --json number,title,state,mergeable,reviewDecision,statusCheckRollup,mergeStateStatus,comments,reviews
   ```

2. **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 (`statusCheckRollup` entries with `conclusion: 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; `gh` is the default and `origin` the fallback when `command -v origin` resolves. 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`](../poteto-mode/references/bugbot-triage.md). Ask by default on security, data, and high-severity findings.

3. **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.

4. **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`).

5. **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-id` of the base..head diff; re-check freshness with `select-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 `FAIL` and `BLOCKED` as 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 ready` only 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 `interrogate` before opening if the diff is contested; once open, babysit takes over.
- Use `unslop` on 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.

Wersje

RepozytoriumWynikLicencja
Ta strona · tommy-ca/pstack100MIT
kirodotdev/kirocrew100Apache-2.0
mintuz/claude-plugins100MIT
lucasnsaraujo/repo-kit100MIT
arjitj2/open-pstack100MIT
chmonitor/chmonitor100GPL-3.0
thedotmack/claude-mem100Apache-2.0
ivy00johns/skill-madness100MIT
michael-denyer/pstack-claude100MIT

Migawka bazy z 13.11.2026 · wersja paczki a6ea3ae474a1 (skrót SHA-256 całej paczki)

Pobrania w ostatnich 30 dniach: 0 · ranking

Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.

Podobne skille

  • 100babysit-pr
    Prowadzi otwarty pull request do stanu gotowego do scalenia: obserwuje CI, ocenia uwagi z przeglądu względem kodu, wypycha poprawki i utrzymuje gałąź aktualną.
  • 100pr-babysit
    Monitoruje pull request przez CI, recenzje i scalenie, by doprowadzić go do stanu zielonego lub gotowego do scalenia.
  • 90sf-ship
    Prowadzi commit, push i pull request, odpowiada na uwagi recenzentów, pilnuje PR do scalenia i pisze notatki wydania.
  • 100babysit-pr
    Pilnuje pull requesta: monitoruje checki i komentarze z przeglądu, obsługuje potwierdzone ustalenia i śledzi gotowość PR do scalenia.
  • 100pr-shepherd
    Przejmuje istniejący otwarty PR i doprowadza go do stanu gotowego do scalenia: zielone CI i wszystkie uwagi recenzentów rozwiązane.
  • 100babysit-pr
    Prowadzi pull request przez rundy przeglądu botów: weryfikuje uwagi, wprowadza poprawki, odpowiada i rozwiązuje wątki.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.