skills.rest
dyad-sh
dyad-shOFFICIAL
Explore all skills by this author →
WebsiteGitHub

dyad:multi-pr-review

Orchestrate multiple Claude sub-agents to review PR diffs and post consensus results.

21.2k|2.6k|Updated Apr 11, 2025
Search Tags:#automation#Claude#multi-agent#consensus#PR#code-review
One-click install
npx skills add https://github.com/dyad-sh/dyad --skill dyad-multi-pr-review
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dyad:multi-pr-review
Source: https://github.com/dyad-sh/dyad/tree/main/.claude/skills/multi-pr-review
Command: npx skills add https://github.com/dyad-sh/dyad --skill dyad-multi-pr-review

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires anthropic, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill orchestrates multiple Claude-based sub-agents to review pull request diffs in parallel, aggregates findings via consensus voting, and deduplicates against existing PR comments to deliver comprehensive, non-redundant feedback.

Core Features & Use Cases

  • Orchestrates multiple agents to review PR diffs in parallel, reducing bias and improving coverage.
  • Aggregates results via consensus, deduplicates against PR comments, and posts a concise summary with inline feedback.
  • Supports configurable agents, thinking budget, and severity thresholds to fit team reviews and governance.

Quick Start

Run the orchestrator to spawn agents, analyze diffs, and publish a consensus review.

Frequently Asked Questions about dyad:multi-pr-review

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

FAQPage Schema
How does multi-agent code review improve PR feedback quality?▼

Multi-agent code review improves PR feedback by spawning multiple Claude sub-agents to analyze diffs in parallel, reducing individual bias and improving coverage before aggregating findings with consensus voting and deduplication.

How do I orchestrate consensus voting for automated pull request reviews?▼

You can orchestrate consensus voting by running the coordinator to spawn sub-agents that analyze PR diffs, aggregate findings via consensus, and post deduplicated inline feedback to GitHub PR comments.

Can I configure agent roles and thinking budgets for Claude code reviews?▼

Yes, the multi-agent PR review process supports configurable agent roles and extended thinking budgets, allowing you to customize analysis depth and severity thresholds to fit team governance requirements.

Does multi-agent PR review work with existing GitHub PR comments?▼

Yes, the multi-agent review process is compatible with GitHub PR comments and deduplicates new findings against existing comments to ensure the final posted feedback is concise and non-redundant.

Do I need the anthropic dependency to run multi-agent consensus reviews?▼

Yes, you need the anthropic dependency because the orchestrator spawns multiple Claude sub-agents to perform parallel triage-style analysis on pull request diffs before aggregating the results.

What is the best way to deduplicate automated PR review findings?▼

The best way to deduplicate PR review findings is using a consensus-driven orchestrator that aggregates parallel sub-agent analyses, filters redundant issues against existing comments, and posts a concise summary.

Related Skills

Explore More Software Engineering Skills→
BerryKuipersBerryKuipers
7

fetch-github-issue-analysis

Fetch GitHub issue data and AI analysis comments into structured JSON.

Community
Intermediate
mt-krainskimt-krainski
1

address-pr

Fetch and address GitHub PR review comments with direct replies.

Community
Advanced
pavan53732pavan53732

dyad:multi-pr-review

Distribute a PR diff across three Claude sub-agents for consensus-based review.

Community
Advanced
CoWork-OSCoWork-OS
420

dyad:multi-pr-review

Coordinate three Claude agents to review PR diffs via consensus voting.

Official
Advanced