Watch an open PR/MR until it's green or merged — poll checks, kick stalled CI, rerun flakes, catch late review threads.

MITAuto-check passed

Install Babysit

skills CLI
$ npx skills add OutThisLife/brooklyn-skills --skill babysit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install OutThisLife/brooklyn-skills babysit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/OutThisLife/brooklyn-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/babysit .claude/skills/babysit && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
babysit
GitHub stars
199
Token cost
~699 tokens
SKILL.md length
379 words
Files
1
Skills in repo
22
Repo updated
First seen
Licence
MIT

At a glance

Watch an open PR/MR until it's green or merged — poll checks, kick stalled CI, rerun flakes, catch late review threads.

  • Works in 4 steps: Snapshot: `gh pr view --json → Poll inside bounded shell loops (a… → React by cause → …
  • Babysit it to green
  • SKILL.md covers Loop, Merging, CI quirks and Done when, plus 1 more section
  • Calls gh and git

What it does

Babysit is an agent skill from OutThisLife/brooklyn-skills. Watch an open PR/MR until it's green or merged — poll checks, kick stalled CI, rerun flakes, catch late review threads. Use for /babysit, "babysit it to green", "watch it", "keep an eye on CI", or any stay-on-it ask after a PR handoff.

Its SKILL.md is about 700 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Skills that drive best-in-class engineering. The licence is MIT.

When your agent uses it

  • Babysit it to green
  • Keep an eye on CI
  • Any stay-on-it ask after a PR handoff

Example prompts

  • “babysit it to green”
  • “watch it”
  • “keep an eye on CI”
  • “/babysit”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Snapshot: `gh pr view --json
  2. Poll inside bounded shell loops (a single for with sleep 30–60
  3. React by cause
  4. Repeat until done. A push or rerun is progress, not an exit.

What it can do on your machine

Read from SKILL.md and the folder at commit 8a97904. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh and git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Babysit loads about 699 tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 379 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~61
When it runs · the whole SKILL.md, loaded when a task matches
~699

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from OutThisLife/brooklyn-skills at commit 8a97904, republished under its MIT licence (© OutThisLife). 379 words, ~699 tokens.

Download SKILL.mdSave it as .claude/skills/babysit/SKILL.md (or your agent's skills folder).
name
babysit
description
Watch an open PR/MR until it's green or merged — poll checks, kick stalled CI, rerun flakes, catch late review threads. Use for /babysit, "babysit it to green", "watch it", "keep an eye on CI", or any stay-on-it ask after a PR handoff.

Babysit

Stay on the PR after handoff until it's actually done. Being asked to babysit IS the ask to poll — but report state changes only, no heartbeats, no per-poll narration.

Loop

  1. Snapshot: gh pr view <N> --json state,mergeable,mergeStateStatus,reviewDecision,statusCheckRollup,autoMergeRequest plus gh pr checks <N>.
  2. Poll inside bounded shell loops (a single for with sleep 30–60 between iterations), not one message per check. Keep watcher scripts, logs, and state outside disposable worktrees, and use a stable working directory; other sessions may remove a merged PR's worktree while its watcher is running. If a watcher fails, recheck the service directly and resume only the remainder of the original deadline. A failed monitor is not a failed deployment.
  3. React by cause:
    • CI never started → kick it: git commit --allow-empty -m "chore: kick CI" && git push.
    • Red caused by this branch → fix it (the pr-ready loop), push, resume watching on the new SHA.
    • Flake / infra red → rerun the failed jobs; repeat until green. Note the flake in one line with the run link.
    • New review threads → handle per pr-ready (fix or reply, verify resolved via the forge API), resume.
  4. Repeat until done. A push or rerun is progress, not an exit.

Merging

Arm automerge only when the user explicitly asks to merge or enable automerge. "Make CI green", "babysit", and "watch it" authorize checks and repairs, not merging. End at green with threads resolved unless merge authorization is explicit.

Show full SKILL.md (141 more words)Show less

CI quirks

  • gh run rerun refusing with "already running" → cancel the run first, then rerun.
  • A cancelled run showing "no checks reported" is pending, not red — wait for it to re-report before calling it either way.
  • Rollup gates ("All required checks pass") go red because a leaf did — diagnose the leaf failure, never the gate.

Done when

Re-query the forge — don't trust that a push went green or a rerun stuck. Merged, or every check green with no unresolved threads. Fail closed: any red or open thread means keep watching. Wrap up with the PR/MR link and what the watch consumed — reruns used, kicks, fixes pushed.

Scope

  • In: watching an open PR, kicking stalled CI, rerunning flakes, small branch-caused fixes, late review threads.
  • Out: opening or refreshing the PR (pr-update, cpr), full rebase/red-CI overhauls (pr-ready), other people's PRs (pr-triage), merging unasked.

© OutThisLife, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/babysit of OutThisLife/brooklyn-skills.

Open the folder on GitHubat commit 8a97904

Compare with similar skills

Babysit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Babysit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Babysit this skillOutThisLife/brooklyn-skills199—~699Automated safety check: PassMIT
Babysitsimstudioai/sim30k—~2.9kAutomated safety check: PassApache-2.0
Canary Watchaffaan-m/ECC276k1 repos~770Automated safety check: PassMIT
Canary Watchaffaan-m/ECC276k—~405Automated safety check: PassMIT
Canary Watchaffaan-m/ECC276k—~414Automated safety check: PassMIT
Babysitnubjs/nub4.4k—~1.9kAutomated safety check: PassMIT

Similar skills

  • Babysit

    simstudioai/sim

    Drive a PR to a clean review (Greptile 5/5, zero open threads) — ships if needed, keeps it mergeable against staging, re-triggers both Greptile and cubic, fixes real findings, replies to and…

    30k GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Canary Watch

    affaan-m/ECC

    A skill your agent uses to monitor and verify a deployed URL after releases — checks HTTP endpoints, SSE streams, static assets, console errors, and performance regressions after deploys, merges, or…

    276k GitHub starsUsed in 1 repo~770 tokens
    DevOps & CloudAuto-check passed
  • Canary Watch

    affaan-m/ECC

    このスキルを使用して、デプロイメント、マージ、または依存関係アップグレード後にデプロイされたURLの回帰を監視します. An agent skill from affaan-m/ECC.

    276k GitHub stars~405 tokensUpdated 4 days ago
    DevOps & CloudAuto-check passed
  • Canary Watch

    affaan-m/ECC

    使用此技能在部署、合并或依赖升级后监控已部署的URL是否存在回归问题。

    276k GitHub stars~414 tokensUpdated 4 days ago
    DevOps & CloudAuto-check passed
  • Babysit

    nubjs/nub

    Bring one nubjs/nub pull request to merge-readiness — pull the inline reviews, verify each finding against the code, re-verify every fix round locally, fix CI, and loop.

    4.4k GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Watch

    taoufik123-collab/claude-watch

    Watch a video (URL or local path) like an editor. An agent skill from taoufik123-collab/claude-watch.

    942 GitHub stars~5.8k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check: warnings

More from OutThisLife/brooklyn-skills

All 22 skills in this repo
  • Draft Tweet

    OutThisLife/brooklyn-skills

    Draft X/Twitter posts about shipped work. An agent skill from OutThisLife/brooklyn-skills.

    199 GitHub stars~456 tokensUpdated 3 days ago
    Auto-check passed
  • Free Disk Space

    OutThisLife/brooklyn-skills

    Safely reclaim disk space on macOS without touching personal or agent data.

    199 GitHub stars~433 tokensUpdated 3 days ago
    Auto-check passed
  • List Open Work

    OutThisLife/brooklyn-skills

    List my open MRs/PRs in the current repo/worktree, each with its tracker ticket.

    199 GitHub stars~1.5k tokensUpdated 3 days ago
    Auto-check passed
  • PR Ready

    OutThisLife/brooklyn-skills

    Clear everything blocking an existing PR/MR from merging — rebase onto the default branch, get CI green, and resolve review threads (Copilot and human).

    199 GitHub stars~2.5k tokensUpdated 3 days ago
    Auto-check passed
  • PR Triage

    OutThisLife/brooklyn-skills

    Maintainer triage on OTHER people's PRs/MRs — verdict of approve, supersede, or close, salvage with credit, close the cluster.

    199 GitHub stars~4.7k tokensUpdated 3 days ago
    Auto-check passed
  • PR Update

    OutThisLife/brooklyn-skills

    Open a PR/MR if missing, or refresh an existing one's title and description so they match the current diff.

    199 GitHub stars~1.3k tokensUpdated 3 days ago
    Auto-check: notes

Questions about Babysit

What does Babysit do?

Watch an open PR/MR until it's green or merged — poll checks, kick stalled CI, rerun flakes, catch late review threads. Babysit is an agent skill from OutThisLife/brooklyn-skills. Watch an open PR/MR until it's green or merged — poll checks, kick stalled CI, rerun flakes, catch late review threads.

When should I use Babysit?

Babysit fits situations like: babysit it to green; keep an eye on CI; any stay-on-it ask after a PR handoff.

How do I install Babysit in Claude Code?

Run `npx skills add OutThisLife/brooklyn-skills --skill babysit -a claude-code`. Or copy the skill folder (skills/babysit in OutThisLife/brooklyn-skills) into .claude/skills/babysit in your project. Claude Code loads it when a task matches its description.

How do I install Babysit in Codex?

Run `npx skills add OutThisLife/brooklyn-skills --skill babysit -a codex`. Or copy the skill folder (skills/babysit in OutThisLife/brooklyn-skills) into .agents/skills/babysit in your project. Codex loads it when a task matches its description.

Can I use Babysit in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OutThisLife/brooklyn-skills --skill babysit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/babysit, .gemini/skills/babysit, .github/skills/babysit and .opencode/skills/babysit in your project.

What does Babysit need to run?

Going by SKILL.md and its folder, Babysit needs the command-line tools its instructions call (gh and git).

Does Babysit access the network?

SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Babysit safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Babysit use?

Babysit is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Babysit use?

About 699 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Babysit?

Skills that share tags, products or a category with Babysit: Babysit (simstudioai/sim, 30k stars), Canary Watch (affaan-m/ECC, 276k stars), Canary Watch (affaan-m/ECC, 276k stars) and Canary Watch (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Babysit?

OutThisLife (a GitHub user) maintains it in OutThisLife/brooklyn-skills, which has 199 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on October 5, 2026.

Source: OutThisLife/brooklyn-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.