babysit-pr

Monitor GitHub pull requests for status, review comments, and CI failures.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/mithran-hq/aegis-code --skill babysit-pr-mithran-hq
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: babysit-pr
Source: https://github.com/mithran-hq/aegis-code/tree/main/.codex/skills/babysit-pr
Command: npx skills add https://github.com/mithran-hq/aegis-code --skill babysit-pr-mithran-hq

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill helps developers and reviewers continuously monitor and diagnose GitHub pull requests, reducing manual oversight.

Core Features & Use Cases

  • Automated PR Watching: Continuously poll PR status, review comments, and CI checks to keep users informed.
  • Failure Diagnosis and Retry: Analyze failed CI jobs, classify failures, and rerun flaky tests up to a configurable limit.
  • Use Case: When managing a complex code review process, automatically detect flaky tests and flaky CI failures, and trigger retries without manual intervention.

Quick Start

Use the babysit-pr skill to monitor a specific pull request and automatically address CI failures or review comments as they occur.

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 for CI status and review comments?

Automated PR monitoring tracks GitHub pull requests for status updates, CI checks, and review comments. It continuously polls CI gatekeeping and review activity, keeping developers informed of real-time changes without manual oversight.

Can I automatically retry failed GitHub Actions jobs when CI tests fail?

Yes, you can automatically retry failed CI jobs. Failure diagnosis analyzes and classifies failed CI checks, then reruns flaky tests up to a configurable limit to resolve intermittent CI failures without manual intervention.

Do I need the GitHub CLI to automate pull request failure diagnosis?

Yes, GitHub CLI and API access are required to automate pull request failure diagnosis. The monitoring process assumes GitHub CLI access to fetch PR status updates, rerun failed jobs, and summarize review activity.

What is the best way to classify and rerun flaky tests in a GitHub PR workflow?

The best way to classify and rerun flaky tests is using automated failure diagnosis. It analyzes failed CI jobs in your GitHub PR workflow, classifies the failures, and triggers retries up to a configured limit.

How does automated failure diagnosis handle complex code review processes?

Automated failure diagnosis handles complex code review processes by detecting flaky tests and CI failures, then triggering retries automatically. It monitors CI gatekeeping to ensure continuous oversight during active PR workflows.

Are there limitations to automating CI gatekeeping and retries for pull requests?

Automated CI gatekeeping retries are limited to a configurable maximum limit for rerunning flaky tests. It requires continuous polling and GitHub API access, meaning limitations apply to API rate limits and the accuracy of failure classification.