agentleFS
christofferbergjchristofferbergj/agent-skills/skills/agents/babysit-and-ship/SKILL.md

babysit-and-ship

Skill1 starsChanged 25 days agoMITView on GitHub

Takes a PR or stack through to merged, with Pstack's independent verifier before each merge. Use when the user asks to merge a PR once it's good to go and CI is green, to see a PR through to merge, or picks the babysit-and-ship option.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Babysit: Run Babysit in drive mode, whatever the PR's size.

    line 13
  2. Distinctive:

    Ship: Run Shipping for the frontier.

    line 14
  3. Distinctive:

    Complete when: every PR reads merged into trunk, every watch or loop you started is stopped, and the reply is Shipping's.

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Babysit and ship

The user's request is their go to mark the PR ready and merge it. The work runs through two playbooks of the installed /pstack-mode skill: read its playbooks/babysit.md and playbooks/shipping.md from the path the host's skill index gives, and follow them except where a step below says otherwise. In a coordinator thread, the coordinator's merge step owns this go instead.

Work one frontier, the lowest unmerged PR, at a time through steps 1 to 3, then repeat them for the next frontier until every PR has merged.

  1. Mark the frontier ready. Mark it ready for review, through the run's built-in PR tool or gh pr ready <pr>, so its full CI runs. This replaces both playbooks' rule that a draft stays a draft until its own merge, so pass Babysit's watcher no --allow-draft. Complete when gh pr view <pr> --json isDraft reads false for the frontier.
  2. Babysit. Run Babysit in drive mode, whatever the PR's size. Complete when Babysit's drive stop condition holds for the frontier.
  3. Ship. Run Shipping for the frontier. Complete when it reads merged into trunk.
  4. Loop back on a failed verdict. Fix a FAIL on the PR's own branch and return to step 2 for that PR. When two fixes for the same verifier finding have failed, apply /principle-attack-the-premise before the next one.
  5. Stop where only the user can act. Stop the watch or loop and bring the user each item with its link: a required human approval; a check that waits on a person, such as a Chromatic baseline; a bot finding Babysit's triage classes as ask; a rebase Babysit reports instead of making; a push to a branch someone else owns, or one that would dismiss an approval; and a check that still fails after the root-cause fix. When the user answers, resume at step 2.

Complete when every PR reads merged into trunk, every watch or loop you started is stopped, and the reply is Shipping's.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.