babysit-ci

Monitors pull request checks and iterates on failures until all checks pass.

Updated Aug 30, 2026
One-click install
npx skills add https://github.com/ryanportfolio/threejs-interview-test --skill babysit-ci-ryanportfolio
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: babysit-ci
Source: https://github.com/ryanportfolio/threejs-interview-test/tree/main/.agents/skills/babysit-ci
Command: npx skills add https://github.com/ryanportfolio/threejs-interview-test --skill babysit-ci-ryanportfolio

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Pull requests often stall on failing or pending CI checks, forcing developers to repeatedly poll status, diagnose failures, and push fixes manually. This Skill automates that watch-and-fix loop until the checks turn green. ## Core Features & Use Cases - Continuous Check Monitoring: Watches a PR's CI checks and detects failing or pending statuses without manual polling. - Iterative Failure Resolution: Diagnoses check failures and applies fixes repeatedly until all checks pass. - Use Case: After opening a PR, you notice the build and lint checks are failing. Invoke this Skill to watch the pipeline, identify the failing step, apply a fix, and re-verify until every check is green. ## Quick Start Ask the assistant to watch the CI checks on my open pull request and fix any failures until they all pass.

Frequently Asked Questions about babysit-ci

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

FAQPage Schema
How do I automatically fix failing CI checks on a pull request?▼

Invoke the babysit-ci workflow, which watches the PR's checks, diagnoses each failure, applies a fix, and re-runs verification. It repeats this loop until every check reports green.

What does the babysit-ci skill do when checks are still pending?▼

It keeps watching the pending checks rather than acting prematurely. Once results arrive, it either confirms success or begins diagnosing and fixing any failures.

Can this skill commit or push fixes on its own?▼

No. The adapter explicitly states that invoking the skill does not authorize commits, pushes, merges, or other outward actions unless the user explicitly requests them.

Why does the skill directory only contain an adapter file?▼

The SKILL.md is a generated Codex adapter that delegates to the canonical workflow at .claude/skills/babysit-ci/SKILL.md. All relative scripts and references resolve from that canonical directory.

Does babysit-ci work with multi-agent review steps?▼

Only if the current session exposes the required multi-agent tools. The adapter instructs confirming tool availability before any Task, Agent, or Workflow step and forbids replacing independent review with self-review.