check

Coordinate parallel code reviews of pull requests and feature branches.

10|Updated Jan 5, 2026
One-click install
npx skills add https://github.com/alexanderop/dotfiles --skill check-alexanderop
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: check
Source: https://github.com/alexanderop/dotfiles/tree/main/claude/skills/check
Command: npx skills add https://github.com/alexanderop/dotfiles --skill check-alexanderop

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill coordinates multiple review workflows by orchestrating parallel subagents to assess current changes, enabling faster, more thorough code reviews.

Core Features & Use Cases

  • Orchestrated Review: Dispatches 2-4 reviewers based on file types and diffs.
  • Parallel Execution: Runs reviews concurrently to reduce turnaround time.
  • Consolidated Reporting: Aggregates findings into a single, actionable report.

Quick Start

Coordinate parallel reviews of the current changes by launching the configured reviewers.

Frequently Asked Questions about check

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

FAQPage Schema
How do I run parallel code reviews on a feature branch?

To run parallel code reviews, this skill dispatches 2 to 4 subagents concurrently based on file types and diffs. It processes uncommitted changes, staged changes, and pull requests to reduce turnaround time.

What is the best way to automate reviewer selection for pull requests?

Automating reviewer selection is handled by assessing current diffs and file types to dispatch 2 to 4 reviewers. This orchestrated approach matches specific changes to appropriate reviewers automatically.

Can I review uncommitted and staged changes concurrently?

Yes, you can review uncommitted and staged changes concurrently. The skill orchestrates parallel subagents to assess all current changes, aggregating their findings into a single consolidated report.

Does parallel code review work without external dependencies?

Parallel code review works without external dependencies, relying entirely on internal subagent orchestration. It independently launches concurrent review tasks and consolidates the results.

How are findings reported when running multiple reviewers in parallel?

When running multiple reviewers in parallel, findings are aggregated into a single, actionable consolidated report. This ensures that results from all dispatched subagents are unified for easy review.

When should I not use parallel subagents for code review?

You should avoid parallel subagents for code review when assessing extremely minimal diffs where sequential review is faster. The overhead of dispatching 2 to 4 subagents is best suited for complex feature branches.