babysit
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…
Skill by William Duyck
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/fuzzyfox-babysit
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: devops
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/babysit
What's inside
- Skill name
babysit- Description
- 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.
- License
- MIT
- Compatibility
- Requires `gh` authenticated as the operator, and a repo with automated PR reviewers (CodeRabbit, Copilot, or similar).
- Metadata
- author: William Duyck · version: 1.0
- Instructions
- 55 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
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](#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.
From fuzzyfox/skills, MIT.
More from fuzzyfox/skills
- 0.569score
session-usage
fuzzyfox
Headroom left in the Claude subscription windows — percent consumed and time-to-reset.
SkillBFreshness: B★ 4Claude Code +9 - 0.566score
agent-voice
William Duyck
Disclose that a message is agent-written, and keep it plain and concise.
SkillBFreshness: B★ 4Claude Code +9 - 0.524score
mailbox
William Duyck
Inter-agent mailbox for sending a handoff to another agent session and picking up replies.
SkillCFreshness: C★ 4Claude Code +9 - 0.524score
quickchart
William Duyck
Generate chart images for markdown documents using the QuickChart API.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
commit
William Duyck
Commit staged changes as a Gitmoji-prefixed Conventional Commit.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
desert-mode
fuzzyfox
Ruthless token-minimization mode plus a "token police" prompt check.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
dispatch
William Duyck
Dispatch work to another agent through the mailbox to a named existing peer, or to a new agent wired to reply to you.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
changelog
William Duyck
Generate a markdown changelog for the changes between a fixed point and HEAD, enriched with issue-tracker context.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
open-pr
William Duyck
Open, publish, or raise a GitHub pull request.
SkillCFreshness: C★ 4Claude Code +9 - 0.516score
spawn
William Duyck
Spawn a fresh agent session from the current one — hand the conversation off into a new tmux window that continues the work one-way, with no channel back.
SkillCFreshness: C★ 4Claude Code +9 - 0.514score
handback
William Duyck
Return your work to the parent agent that spawned you.
SkillCFreshness: C★ 4Claude Code +9 - 0.494score
review
William Duyck
Review the changes since a fixed point along three independent axes — Standards (does the code follow this repo's documented conventions and avoid known…
SkillCFreshness: C★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 10, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.0
- License
- MIT
- Repository
- github.com/fuzzyfox/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from William Duyck
- 0.566score
agent-voice
William Duyck
Disclose that a message is agent-written, and keep it plain and concise.
SkillBFreshness: B★ 4Claude Code +9 - 0.524score
mailbox
William Duyck
Inter-agent mailbox for sending a handoff to another agent session and picking up replies.
SkillCFreshness: C★ 4Claude Code +9 - 0.524score
quickchart
William Duyck
Generate chart images for markdown documents using the QuickChart API.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
commit
William Duyck
Commit staged changes as a Gitmoji-prefixed Conventional Commit.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
dispatch
William Duyck
Dispatch work to another agent through the mailbox to a named existing peer, or to a new agent wired to reply to you.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
changelog
William Duyck
Generate a markdown changelog for the changes between a fixed point and HEAD, enriched with issue-tracker context.
SkillCFreshness: C★ 4Claude Code +9
Cite this page
babysit skill. Agent Mart. https://agentmart.dev/skills/fuzzyfox-babysit (last updated 2026-10-24)