babysit-pr

Monitor GitHub pull requests and retry failed CI jobs.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/andreasasprou/polaris --skill babysit-pr-andreasasprou
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: babysit-pr
Source: https://github.com/andreasasprou/polaris/tree/main/.agents/skills/babysit-pr
Command: npx skills add https://github.com/andreasasprou/polaris --skill babysit-pr-andreasasprou

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Babysit PRs persistently until they are ready to merge by monitoring CI, review activity, and mergeability, and taking autonomous corrective actions as needed.

Core Features & Use Cases

  • Continuous PR babysitting: watch CI status, review comments, and merge state.
  • Automated remediation: diagnose CI failures, retry flaky jobs, and push safe fixes on the PR head if appropriate.
  • Bot-review coordination: track trusted bot reviewers and surface unresolved feedback to keep PRs moving.

Quick Start

Run the watcher script with a PR reference and enable watch mode to begin continuous monitoring.

Frequently Asked Questions about babysit-pr

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automatically monitor GitHub pull requests to keep CI green and merge-ready?

Automatically monitor GitHub pull requests by continuously watching CI status, review comments, and merge state to keep them green and merge-ready. The watcher takes autonomous corrective actions like diagnosing CI failures and retrying flaky jobs.

Can I automatically retry failed CI jobs on a GitHub PR?

Yes, you can automatically retry failed CI jobs on a GitHub PR up to a configured budget. The monitoring process diagnoses failures and triggers retries for flaky jobs to keep the pull request moving toward merge readiness.

How do I handle bot reviewer comments on long-running pull requests?

Handle bot reviewer comments on long-running pull requests by tracking trusted bot reviewers and surfacing unresolved feedback. The bot-review coordination ensures automated comments are addressed while monitoring continues on multi-repo workflows.

Does PR babysitting work with multi-repo workflows and SHA changes?

PR babysitting works with multi-repo workflows and long-running pull requests by preserving state across SHA changes. It applies autonomous remediation across multiple repositories to ensure mergeability is maintained throughout the development lifecycle.

What is the best way to apply safe fixes to failing pull requests automatically?

The best way to apply safe fixes to failing pull requests automatically is through continuous monitoring that diagnoses CI failures and pushes fixes directly to the PR head if appropriate. This hands-free approach maintains merge readiness without manual intervention.

Are there limitations to autonomous PR mergeability monitoring?

Autonomous PR mergeability monitoring limits corrective actions to deterministic, safe fixes and a configured retry budget. It cannot resolve complex CI failures requiring manual code changes, but it will surface unresolved trusted reviewer feedback for human intervention.