agentleFS
fuzzyfoxfuzzyfox/skills/skills/babysit/SKILL.md

babysit

Skill4 starsChanged 2 months agoMITView on GitHub

Babysit a pull request to approval: watch CI and the automated reviewers, action or push back on each comment, push fixes, keep watching until the bots have nothing left to say. Use when the user asks to babysit, monitor, or watch a PR, or to take one through review until it is mergeable.

47 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use oh-my-issues, what-the and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • tuliosalustiano27Skill

    oh-my-issues

    Cluster a GitHub issue backlog by root cause into a small set of plan-master issues, redirect children with a standardized comment, and bundle architectural-fix PRs that close clusters atomically. Use when an issue tracker has accumulated dozens of reports that share underlying defects, when asked to triage / consolidate / cluster / dedupe issues, when asked to build a plan series or roadmap from open issues, or when routing a new incoming bug into an existing plan.

    Also in 3 projects that use this

  • tuliosalustiano27Skill

    what-the

    What the? Use when the user wants a plain-English breakdown of something technical — the who, what, where, why, and when.

    Also in 3 projects that use this

  • Tsumugii24Skill

    split-to-prs

    Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.

    Also in 4 projects that use this

  • mukcoSkill

    principles

    General software engineering principles — DRY, SOLID, YAGNI, KISS, naming, code smells, and refactoring. Language-agnostic. Use alongside language-specific skills.

    Also in 5 projects that use this

  • PandelisZSkill

    update-cli-config

    View and modify Cursor CLI configuration settings in ~/.cursor/cli-config.json. Use when the user wants to change CLI settings, configure permissions, switch approval mode, enable vim mode, toggle display options, configure sandbox, or manage any CLI preferences.

    Also in 3 projects that use this

  • 32103210Skill

    migrate-to-skills

    Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent Skills format (.cursor/skills/). Use when you want to migrate rules or commands to skills, convert .mdc rules to SKILL.md format, or consolidate commands into the skills directory.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 45 edited versions we read keep these.

  • 5

    Distinctive

    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:

    If there is no PR yet, open one with open-pr.

    line 22
  2. Distinctive:

    Triage: every new comment (below).

    line 30
  3. Distinctive:

    Every comment gets a decision, and the decision is yours — a bot's comment is an argument, not an instruction.

    line 42
  4. Distinctive:

    Action it: when it names a real defect, a repo convention the change misses, or a case the tests do not cover.

    line 45
  5. Distinctive:

    When a comment turns on a judgement the operator owns — a product decision, a deliberate trade-off, an architectural direction — stop and …

    line 51
  6. Distinctive:

    Stop early and say so when the loop stops converging: the same comment surviving two rounds of fixes, CI failing for a reason outside the …

    line 64

“Common” is measured: kept by at least 6 in 10 of the 45 edited versions of this file we could read. “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

Babysitting is a loop, not a single pass — each push provokes another round of CI and reviewer comments.

The loop

Resolve the PR first: a number or URL the operator gave, otherwise the PR for the current branch (gh pr view --json number,url,state,statusCheckRollup,reviews). If there is no PR yet, open one with open-pr.

Then, until done:

  1. Wait for the PR to change — CI settling, a reviewer posting. gh pr checks --watch blocks on CI; read the review threads between rounds rather than spinning tightly. Bots are slow, and a quiet PR is usually a pending one, not a finished one.
  2. Triage every new comment (below). Red CI is a comment too — read the failing log and treat the cause as an action item.
  3. Fix what you agreed with, through tdd: the failing test first, then the change.
  4. Reply to what you disagreed with, on the review comment itself, with the reasoning that changed your mind about it.
  5. Push, and go back to 1. A push restarts CI and re-triggers the reviewers; expect another round, and expect the round after that to be smaller.

Triage

Every comment gets a decision, and the decision is yours — a bot's comment is an argument, not an instruction.

Action it when it names a real defect, a repo convention the change misses, or a case the tests do not cover. Push back when the bot has missed context the diff does not carry, is restating a choice made deliberately, or is asking for scope the issue did not ask for; say which, in a reply, so the thread carries the reasoning rather than silence.

When a comment turns on a judgement the operator owns — a product decision, a deliberate trade-off, an architectural direction — stop and ask them. Guessing on their behalf is how a babysat PR drifts away from what they wanted.

Done

Done is all three at once: CI green, every comment either fixed or answered, and every automated reviewer approving.

Then stop and hand the PR back — its URL, what you changed in response to review, and what you pushed back on. Merging is the operator's, in that moment or a later prompt; babysitting ends at approved.

Stop early and say so when the loop stops converging: the same comment surviving two rounds of fixes, CI failing for a reason outside the diff, or a reviewer that never posts. A stalled loop reported is worth more than a loop still running.

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.