Babysit a PR Agent Skill

Babysits or watches an open GitHub PR until merge-ready, continuously reacting to review comments, CI failures, and routine base movement…

Context cost
32.5k tokensestimated from the bundle, loaded when it triggers
Bundle
3 of 4 fileshanded out here; the rest is at its source
Licence
not declarednone named by its author
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Babysits or watches an open GitHub PR until merge-ready, continuously reacting to review comments, CI failures, and routine base movement throughout the PR's life. Use when asked to 'babysit the PR', 'watch the PR', monitor, or keep an eye on a PR over time — not a one-shot request to resolve review comments or debug one CI failure (those are separate skills). GitHub only, including GitHub Enterprise.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

collaborationgithub

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md88.4 kB · preview
--- name: ce-babysit-pr argument-hint: "[PR number, URL, or blank for current branch's PR] [watch|checkpoint] [duration] [posture:target|stack-ready|stack-land]" ---
7# Babysit a PR
8
9Keep an open PR **continuously moving toward merge** by reacting to three independent event streams — **incoming review comments**, **CI status changes**, and **branch currency** — as each arrives, for as long as the PR stays open. Comment fixes are delegated to ce-resolve-pr-feedback; CI failures are delegated to ce-debug; routine target-local base movement follows the bounded protocol below. This skill owns the watch loop: snapshot, order, dedup, act, and decide when to **keep watching**, move to the next authorized managed-stack layer, or stop.
10
11**Outcome:** leave the requested PR at an honest terminal, looks-ready, blocked, or budget state under the run's **posture** (target | stack-ready | stack-land). For an independent PR or manual dependency chain, the target-local result is done. For a confirmed managed stack, a settled layer is a transition checkpoint governed by posture (below). Never infer stack-wide semantic scope from branch topology alone. **Settled ≠ merged:** a layer can look merge-ready while still OPEN; you do not need to merge to babysit the next layer.
12
13## Posture (one value for the invocation/run)
14
15Hold exactly one posture for the run. Carrier: posture:target|stack-ready|stack-land — distinct from watch / checkpoint / mode:pipeline / duration. Re-state the same posture on every managed-stack layer --continue-invocation transition alongside the existing budget flags.
16
17| Posture | Behavior |
18| --- | --- |
19| target | Only the named PR. Stop at looks-ready. May offer stack-wide once when a confirmed multi-layer managed stack needs work; decline keeps the target-local stop. Never merges. |
20| stack-ready | After the active layer settles, automatically continue to the next open non-draft upstack layer that needs work. Never merges. Persist for the run; do not re-ask each layer. |
21| stack-land | Like stack-ready for traversal. Selecting or handing off posture:stack-land **is** run-level land authorization. After settle, merge the **bottom-most open settled** PR via gh stack merge + gh stack sync, then continue. |
22
23**Selection:** named one PR / no stack language → default target, but if confirmed multi-layer managed stack ask once (only this PR vs whole stack to ready). Intent to own/finish the stack → stack-ready. Intent to land/merge when green → stack-land. Prefer intent over keyword regex. An explicit "babysit the managed stack" request selects stack-ready (or stack-land when land intent is also clear). In mode:pipeline, use only the posture/scope already supplied on the invocation — never ask.
24
25When a confirmed managed stack is in play and you need CLI recipes, load references/stack-commands.md.
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md12,810 words
Files3
Licencenot declared
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈150
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
32,375
on trigger
The instruction body and 2 supporting files, read only when the skill fires.
16.3%
of a 200k window
Ten skills this size would not fit in the window together.
050k100k150k200k context window

32.5k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

The download carries 3 of the 4 files in its source folder; the list here names 3 files, 130.1 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in. The other one is not in the download — listed after these, with why.

  • SKILL.md88.4 kB
  • references/stack-commands.md2.2 kB
  • references/watch-loop.md39.5 kB

Not in the download

Not carried is a type a skill download does not hold. Marked read: its SKILL.md or scripts name the file, so without it the skill works only in part. Take it from its source.

  • scripts/pr-snapshotread · not carried
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the download is 3 files — not the whole of its source: 1 file is left out, and the skill reads it. It is listed under the files, with why.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Babysit a PR · 32.5k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/xiaoquisme-babysit-a-pr/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/babysit-a-pr" ] && { [ ! -e .claude/skills/babysit-a-pr ] || { mv .claude/skills/babysit-a-pr "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/babysit-a-pr" .claude/skills/ && echo "Installed .claude/skills/babysit-a-pr"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add xiaoquisme/babysit-a-pr

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/babysit-a-pr/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/xiaoquisme-babysit-a-pr/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/babysit-a-pr" ] && { [ ! -e ~/.claude/skills/babysit-a-pr ] || { mv ~/.claude/skills/babysit-a-pr "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/babysit-a-pr" ~/.claude/skills/ && echo "Installed ~/.claude/skills/babysit-a-pr" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/babysit-a-pr/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. It appears as ce-babysit-pr in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, babysit-a-pr. Not in this download: 1 file of its source, which its SKILL.md or scripts read (which one, and why). Take it from its source.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referencexiaoquisme/babysit-a-pr

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Publisher
Servers0
Claim this skill