peer-review

Orchestrate parallel pull request code reviews across multiple AI agents.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/RagnarokButMemorySafe/opencode-config --skill peer-review-ragnarokbutmemorysafe
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: peer-review
Source: https://github.com/RagnarokButMemorySafe/opencode-config/tree/main/skills/peer-review
Command: npx skills add https://github.com/RagnarokButMemorySafe/opencode-config --skill peer-review-ragnarokbutmemorysafe

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill streamlines the code review process by orchestrating parallel reviews from multiple agents and synthesizing their findings into a single, actionable summary.

Core Features & Use Cases

  • Parallel Review Execution: Dispatches review tasks to multiple agents concurrently.
  • Findings Synthesis: Consolidates feedback into a structured report, highlighting agreed-upon issues, disagreements, and individual reviewer comments.
  • Automated Verdict Suggestion: Provides a suggested approval status based on the synthesized findings.
  • Use Case: When a pull request is ready for review, this Skill can be invoked to get comprehensive feedback from two distinct reviewer personas simultaneously, accelerating the feedback loop.

Quick Start

Initiate a peer review for the current branch by asking the assistant to run the peer-review skill.

Frequently Asked Questions about peer-review

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

FAQPage Schema
How do I run parallel code reviews on a pull request using multiple AI agents?

To run parallel code reviews, you provide a PR number, branch name, or file path. The system dispatches review tasks to multiple AI agents concurrently and synthesizes their findings into a single unified summary report.

What is the best way to synthesize feedback from multiple AI code reviewers?

The best way to synthesize feedback from multiple AI code reviewers is using a parallel orchestration process. It consolidates individual reviewer comments, highlights disagreements, and generates an automated verdict suggestion for the pull request.

Can I target specific file paths or branch names for AI pull request reviews?

Yes, you can target specific file paths or branch names for AI pull request reviews. The system identifies target code or diffs from your input and routes those specific segments to the designated sub-agents for concurrent processing.

Does the synthesized PR review report show disagreements between reviewer agents?

Yes, the synthesized PR review report explicitly shows disagreements between reviewer agents. The consolidated feedback structure highlights agreed-upon issues, differing opinions, and individual reviewer comments to provide a comprehensive verdict.

How does automated verdict suggestion work for pull request approvals?

Automated verdict suggestion works by analyzing synthesized findings from concurrent AI code reviews. It evaluates the consolidated feedback report to recommend a pull request approval status, accelerating the overall feedback loop.