drive-to-merge

Automate PR/MR progression to merge across GitHub and GitLab.

23|2|Updated Mar 7, 2026
One-click install
npx skills add https://github.com/kirich1409/krozov-ai-tools --skill drive-to-merge
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: drive-to-merge
Source: https://github.com/kirich1409/krozov-ai-tools/tree/main/plugins/developer-workflow/skills/drive-to-merge
Command: npx skills add https://github.com/kirich1409/krozov-ai-tools --skill drive-to-merge

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill automates the end-to-end drive of a PR/MR from its current state to a merged outcome by handling CI, reviews, fixes, and re-requests.

Core Features & Use Cases

  • End-to-end PR driver: diagnose CI failures, categorize reviewer comments, propose fixes, delegate tasks, push changes, re-request reviews, and wait for merge until complete.
  • Flexible modes: default interactive loop, --auto autonomous mode, and --dry-run for a safe, non-destructive simulation.
  • Safety and state tracking: uses a resumable session state file to persist progress, surface blockers, and guard against unsafe actions.

Quick Start

Invoke the drive-to-merge skill on a PR to start autonomous driving toward merge.

Frequently Asked Questions about drive-to-merge

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

FAQPage Schema
How do I automatically drive a pull request to merge after CI passes?

Automating a pull request to merge involves managing CI, categorizing reviews, proposing fixes, and rebasing out-of-date branches. This skill handles the end-to-end PR driving process across GitHub and GitLab to reach a merged outcome.

What is the best way to handle pending reviews and CI failures on a pull request automatically?

Handling pending reviews and CI failures automatically requires an autonomous workflow that categorizes comments, delegates edits, pushes fixes, and re-requests reviews. This skill operates in default, auto, or dry-run modes to manage the full merge cycle safely.

Can I simulate driving a pull request to merge without making destructive changes?

You can simulate driving a pull request to merge without destructive changes by using a dry-run mode. This skill provides a --dry-run option to safely simulate the autonomous workflow, including CI diagnosis and review management, without altering your repository.

Does this PR merge automation work with both GitHub and GitLab?

This PR merge automation works with both GitHub and GitLab. It manages the end-to-end drive of a PR or MR from its current state to a merged outcome by handling CI, reviews, and necessary rebase actions across both platforms.

How does autonomous PR merging track progress and recover from interruptions?

Autonomous PR merging tracks progress and recovers from interruptions by using a resumable session state file. This skill persists progress, surfaces blockers, and guards against unsafe actions throughout the round-based decision and delegation process.

Why do my automated pull requests get stuck waiting for out-of-date base branches?

Automated pull requests get stuck waiting for out-of-date base branches when the base requires a rebase before merging. This skill resolves the issue by applying necessary rebase or fixes to the PR, allowing the autonomous merge process to continue.