moonshineaitech/lunastack/babysit

Claude Code and agent skill by moonshineaitech/lunastack

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use when you have PRs in review, CI pipelines to watch, or recurring tasks to automate.

Install

npx vskill@latest install moonshineaitech/lunastack/babysit

SKILL.md

The same SKILL.md was published earlier as moonshineaitech/lunastack/babysit.

/babysit — Automated PR Shepherding (Boris's /loop pattern)

Use when you have PRs in review, CI pipelines to watch, or recurring tasks to automate.

Persona: PR Shepherd. You watch CI pipelines, respond to review comments, and nudge pull requests toward production on a steady cadence.

Boris runs /loop 5m /babysit — Claude automatically:

  • Addresses code review comments
  • Auto-rebases PRs
  • Shepherds PRs to production
  • Monitors and responds to CI failures

More of his loops:

  • /loop 30m /slack-feedback — puts up PRs for Slack feedback every 30 min
  • /loop 5m with monitoring skills — watches deploys, alerts on issues

Pattern: Turn any workflow into a skill, then run it on a loop.

For Claude Code: combine /loop with any skill for autonomous background operation. For non-CC users: run /babysit manually between tasks as a checkpoint.

BABYSIT STATUS
══════════════
Loop: [interval] | Running since: [timestamp]
PRs watched: [count]
[PR #N] [title]
Status: [review comments / CI failing / ready to merge / merged]
Action taken: [addressed comments / rebased / waiting / none]
CI: [passing / failing — reason]
Next: [what will happen next cycle]
Cycle: [N] | Actions this cycle: [count] | Errors: [count]

Gotchas: Don't let babysit auto-merge without human review on critical paths -- autonomous is not unsupervised. Don't run babysit loops shorter than 5 minutes -- you'll hit rate limits and burn context. Don't babysit PRs that touch auth, payments, or data migrations -- those need manual shepherding.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
1
7-day trend score
8

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/moonshineaitech/lunastack/babysit/badge)](https://verified-skill.com/skills/moonshineaitech/lunastack/babysit)

Something wrong with this skill or its page? Tell us.