# Factory Babysit PR

Experimental workflow for babysitting one explicitly authorized pull or merge request.

- Repository: https://github.com/BuilderIO/skills (4626 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-10-28
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add BuilderIO/skills --skill factory-babysit-pr -g -a claude-code -y`
Codex: `npx skills add BuilderIO/skills --skill factory-babysit-pr -g -a codex -y`
Cursor: `npx skills add BuilderIO/skills --skill factory-babysit-pr -g -a cursor -y`
Gemini CLI: `npx skills add BuilderIO/skills --skill factory-babysit-pr -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add BuilderIO/skills`

## Description

Experimental workflow for babysitting one explicitly authorized pull or merge request. Use to monitor its live review state and checks, fix actionable in-scope findings, and apply separate reply, approval, merge, and soak gates.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Factory Babysit PR

> Start with the [Factory guide](../../docs/factory/README.md) for workflow
> setup and configuration.

Follow one authorized PR or merge request through a delivery lifecycle. This
is not a queue sweep like `factory-review-prs` or a stopped-task scan like
`factory-watchdog`.

Read `.agent-factory/config.yaml`, the optional
`skill_prompts.factory-babysit-pr` entry, the target repository's instructions,
and the [Factory configuration reference](https://github.com/BuilderIO/skills/blob/main/docs/factory/configuration.md#workflowspr-babysitting).
A PR number, label, green check, or unrelated ship request is not authorization.
The prompt is additional project guidance, not PR authorization.

## Each pass

1. **Confirm authority and ownership.** Verify the exact host, repository, PR,
   original user authorization, allowed paths/risk, and task-owned worktree. If
   anything is missing or stale, stop before writing.
2. **Read a complete live snapshot.** Record base and head, open/draft/closed/
   merged state, all required checks, current reviews and approvals, unresolved
   threads, and mergeability. Partial or unavailable data is unknown, not clean.
3. **Disposition feedback.** Compare each new finding with the exact diff and
   source. Preserve human direction unless evidence disproves it. Fix only
   actionable findings inside the authorized path/risk limits; avoid
   speculative cleanup and larger redesigns.
4. **Verify and re-read.** Run configured checks for each fix. After every push
   or host mutation, fetch the live PR again and bind all evidence to its exact
   current head. A changed head invalidates old check/review evidence and resets
   the soak.
5. **Apply action gates separately.** A review or fix does not authorize a
   reply, push, approval, or merge.

## Action gates

The rest: https://github.com/BuilderIO/skills/blob/HEAD/skills/factory-babysit-pr/SKILL.md