judge

Coordinate independent reviewers to assess work for approach flaws and risks.

10|5|Updated Mar 3, 2026
One-click install
npx skills add https://github.com/JHostalek/dotclaude --skill judge-jhostalek
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: judge
Source: https://github.com/JHostalek/dotclaude/tree/main/skills/judge
Command: npx skills add https://github.com/JHostalek/dotclaude --skill judge-jhostalek

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill prevents authors from approving their own work without rigorous outside scrutiny, exposing flawed approaches, missed alternatives, and domain-specific risks before acceptance or extension.

Core Features & Use Cases

  • Independent Review Panel: Coordinates three clean-context reviewers covering domain expertise, pragmatism, and fundamentally different alternatives.
  • Credibility-Based Synthesis: Filters findings for evidence, actionability, trade-off honesty, and calibrated severity while elevating convergent concerns.
  • Structured Verdicts: Produces an expert-grade, solid, rethink, or red-flag assessment with strengths, prioritized findings, alternatives, and a highest-leverage recommendation.
  • Use Case: Ask it to review a newly implemented feature before merging so independent reviewers can assess architecture, proportionality, production fitness, and overlooked solution paths.

Quick Start

Use the judge skill to independently review the most recent substantive work in this conversation and provide a calibrated expert verdict.

Frequently Asked Questions about judge

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

FAQPage Schema
How do I get an independent expert verdict before merging a new feature implementation?

To identify architecture flaws before shipping, coordinate multiple independent reviewers covering domain expertise, pragmatism, and alternative paths. The review evaluates production fitness, proportionality, and overlooked solution paths to expose approach-level flaws.

What is the best way to review architecture decisions for missed alternatives?

To review architecture decisions for missed alternatives, apply alternative-path reviewers to evaluate fundamentally different solutions. The synthesis filters findings for evidence, actionability, and trade-off honesty while elevating convergent concerns into a calibrated assessment.

How does an independent code review panel evaluate software quality?

An independent code review panel evaluates software quality by using credibility-based synthesis to filter findings for evidence and calibrated severity. It assesses production fitness and proportionality, producing structured expert, solid, rethink, or red-flag verdicts with prioritized findings.

Can I use an expert review process for architectural decisions, not just code?

Yes, expert review applies to architectural decisions, feature designs, and other substantive work, not just code implementations. It provides an independent expert verdict by assessing approach-level flaws, domain-specific risks, and actionable trade-offs before acceptance.

When do I need a red-flag assessment during software quality review?

A red-flag assessment is needed during software quality review when independent expert reviewers identify critical approach-level flaws or domain-specific risks that require a complete rethink before acceptance. It indicates the work is not production-fit.