review

Run automated checks and blind multi-lens reviews to produce a final verdict.

5|Updated Apr 9, 2026

Search Tags:#automation #merge #review #diff #lint #verdict

Ready to run

npx skills add https://github.com/KodingDev/meridian --skill review-kodingdev

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: review
Source: https://github.com/KodingDev/meridian/tree/main/skills/review
Command: npx skills add https://github.com/KodingDev/meridian --skill review-kodingdev

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates and standardizes the review process for implemented work, reducing manual effort and bias during post-implementation assessment.

Core Features & Use Cases

Automated gating: lint, typecheck, build, and tests run before dispatching reviewers.
Multi-lens reviews: three blind lens passes review changes independently to avoid cross-contamination of reasoning.
Findings aggregation: deduplicate findings and compute a final verdict to guide merging decisions.
Safe orchestration: enforces hard gates and policy constraints before any downstream actions.

Quick Start

Run automated checks on the latest changes and dispatch the three blind reviewer passes to gather a unified review verdict.

Frequently Asked Questions about review

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

FAQPage Schema

How do I automate code review and merge gating for pull requests?▼

Automated code review runs lint, typecheck, build, and test gates, then dispatches three blind, multi-lens passes to independently evaluate changes and output a structured final verdict for merging decisions.

What is blind multi-lens review and how does it reduce bias in code evaluation?▼

Blind multi-lens review dispatches three independent passes over a diff to avoid cross-contamination of reasoning, deduplicates findings, and computes a most-severe verdict to reduce manual bias.

Can I enforce hard gates for lint and typecheck before allowing a merge?▼

Yes, the review process enforces hard gates by running automated lint, typecheck, build, and test checks before dispatching any downstream blind reviewer passes or merging actions.

How do I aggregate duplicate code review findings into a single merge verdict?▼

You can aggregate duplicate review findings by collecting results from multiple independent lens passes, deduplicating the issues, and computing a most-severe final verdict to guide merge decisions.

Does automated review work without external dependencies or components?▼

Yes, the automated review and gating process operates entirely standalone without requiring any external dependencies or components to run its built-in checks and blind passes.