quorum-review

Coordinate multi-provider quorum reviews of AI plans to derive consensus.

Updated Mar 13, 2026
One-click install
npx skills add https://github.com/eworthing/agent-skills --skill quorum-review
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: quorum-review
Source: https://github.com/eworthing/agent-skills/tree/main/quorum-review
Command: npx skills add https://github.com/eworthing/agent-skills --skill quorum-review

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Cross-provider reviews of AI plans to surface blockers and converge on a final consensus.

Core Features & Use Cases

  • Anonymous, multi-round panel review with 3+ reviewers
  • Structured blocking/non-blocking issues with canonical IDs (BLK-XXX, NB-XXX)
  • Derived artifact verdict based on surviving blockers and thresholding
  • Round management up to 5 rounds with issue merging and cross-critique

Quick Start

Start a quorum review by providing three reviewers and a plan file, then run the orchestrator to initiate Round 1.

Frequently Asked Questions about quorum-review

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

FAQPage Schema
How do I coordinate multi-provider AI plan reviews to reach consensus?

Multi-provider AI plan reviews coordinate consensus by orchestrating 3+ reviewers across providers like Claude, Gemini, Codex, and Copilot through anonymous cross-critique and multi-round issue merging.

What is a quorum review process for evaluating AI plans?

A quorum review is a structured protocol for evaluating AI plans that enforces an issue ledger with canonical IDs, anonymous cross-critique, and multi-round orchestration to derive a final artifact verdict.

Can I use different AI providers like Claude and Gemini in the same plan review?

Yes, you can use different AI providers in the same plan review. The orchestration supports cross-provider evaluations with Claude, Gemini, Codex, and Copilot acting as anonymous reviewers.

How do I track blocking and non-blocking issues during an AI plan evaluation?

You track blocking and non-blocking issues during AI plan evaluation using a structured issue ledger that assigns canonical IDs like BLK-XXX for blockers and NB-XXX for non-blocking issues.

How many rounds can I run to resolve blockers in a multi-provider AI plan review?

You can run up to 5 rounds to resolve blockers in a multi-provider AI plan review. Round management includes issue merging, cross-critique, and verification before deriving a final artifact verdict.

How does the system handle anonymous cross-critique among AI providers?

The system handles anonymous cross-critique by structuring multi-round panel reviews where 3+ reviewers evaluate AI plans without provider attribution, merging issues across rounds to reach consensus.