reviewing

Run self-review and Codex review in parallel and output a reconciled report.

Updated Jan 27, 2026
One-click install
npx skills add https://github.com/wthrk/agent-tools --skill reviewing
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: reviewing
Source: https://github.com/wthrk/agent-tools/tree/main/skills/reviewing
Command: npx skills add https://github.com/wthrk/agent-tools --skill reviewing

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill streamlines content evaluation by running self-review and Codex review in parallel and delivering a reconciled set of findings.

Core Features & Use Cases

  • Parallel reviews: executes self-review and Codex review concurrently to speed up feedback.
  • Reconciliation & reporting: compares results, surfaces agreements and disagreements, and outputs a structured final report.
  • Use Case: ideal for code reviews, documentation reviews, PR reviews, and any content requiring objective assessment and quality signals.

Quick Start

Run a dual-review on the target content to obtain a unified assessment.

Frequently Asked Questions about reviewing

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

FAQPage Schema
How do I run a parallel code review and reconcile the findings?

Parallel code review executes self-review and Codex review concurrently, then compares results to surface agreements and disagreements into a structured final report.

Can I use a dual-review workflow for PR and documentation reviews?

Yes, dual-review workflows apply to PR reviews, documentation reviews, and any content requiring objective evaluation, delivering a reconciled set of findings with clear recommendations.

What is the best way to automate consensus reporting for code reviews?

Automated consensus reporting for code reviews is achieved by running self-review and Codex review in parallel, then reconciling the dual outputs into a structured final report.

Does parallel self-review work without external dependencies?

Yes, parallel self-review and Codex review operate without external dependencies, executing concurrently to speed up feedback and deliver objective assessment signals.

How do I get a structured final report from a Codex review?

A structured final report from a Codex review is generated by reconciling its parallel execution with self-review, outputting clear locations, issues, and recommendations.

When should I use a reconciled dual-review approach for content evaluation?

Use a reconciled dual-review approach for content evaluation when you need objective quality signals from parallel self-review and Codex review, ensuring comprehensive assessment.