skills.rest
jpaddison3
jpaddison3COMMUNITY
Explore all skills by this author →
WebsiteGitHub

review-multi

Run parallel code reviews with Claude and Codex on pull request changes.

2|Updated Sep 3, 2016
Search Tags:#automation#codex#claude#parallel#synthesis#code-review
One-click install
npx skills add https://github.com/jpaddison3/dotfiles --skill review-multi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: review-multi
Source: https://github.com/jpaddison3/dotfiles/tree/main/claude-skills/review-multi
Command: npx skills add https://github.com/jpaddison3/dotfiles --skill review-multi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinating simultaneous code reviews with multiple AI agents is time‑consuming and error‑prone, making it hard to get a unified view of code quality.

Core Features & Use Cases

  • Parallel Execution: Launches Claude and Codex reviews at the same time, reducing wait time.
  • Mode Flexibility: Supports collaborative synthesis, raw pass‑through, and autonomous fixing modes.
  • Branch Comparison: Handles base‑branch reviews for PRs or any diff context.
  • Use Case: Developers needing rapid, comprehensive feedback on pull requests can invoke this skill to obtain combined insights and optional automated fixes.

Quick Start

Run /review-multi to start combined code reviews and receive a synthesized summary.

Frequently Asked Questions about review-multi

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

FAQPage Schema
How do I run parallel code reviews with multiple AI agents?▼

Use the /review-multi command to launch parallel code reviews with Claude and Codex simultaneously. This reduces wait time and provides combined insights for pull request changes, base branch comparisons, or any diff requiring comprehensive analysis.

What is the best way to get unified feedback on a pull request from multiple models?▼

The best way to get unified pull request feedback is using collaborative synthesis mode, which combines Claude and Codex reviews into a single summary. This eliminates the error-prone manual coordination of checking separate AI agents.

Can I pass through raw code review outputs without synthesizing them?▼

Yes, you can use raw pass-through mode to receive unmodified code review outputs directly from Claude and Codex. This is configurable alongside collaborative synthesis and autonomous fixing modes based on your specific needs.

Does this approach support autonomous fixing for issues found in diffs?▼

Yes, autonomous fixing mode automatically addresses issues found during the parallel code review of diffs. This allows developers to obtain combined insights and optional automated fixes without manual intervention.

How do I review base branch comparisons for a PR?▼

Base branch comparisons are handled by applying the parallel review skill to your PR diff context. It analyzes the changes between your feature branch and the base branch to provide comprehensive feedback.

Related Skills

Explore More Software Engineering Skills→
kk20300113-pngkk20300113-png

ship

Automate code release workflows from branch merging to pull request creation.

Community
Advanced
qsimeonqsimeon
1

gh-issues

Orchestrate parallel sub-agents to fix GitHub issues and create pull requests.

Community
Advanced
jiroamatojiroamato

pr

Create pull requests from current branches using GitHub templates and validation checks.

Community
Intermediate
dimsourdimsour
2

pr-review

Fetch GitHub pull request diffs and run parallel code quality, security, testing, and Iron Law reviewers.

Community
Advanced