skills.rest
AlejandroFerp
AlejandroFerpCOMMUNITY
Explore all skills by this author →
GitHub

judgment-day

Launch two independent blind judge sub-agents to review a target and synthesize verdicts.

Updated Apr 20, 2026
Search Tags:#automation#verification#quality-assurance#code-review#adversarial-review#dual-review
One-click install
npx skills add https://github.com/AlejandroFerp/EcoAdmin --skill judgment-day-alejandroferp
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: judgment-day
Source: https://github.com/AlejandroFerp/EcoAdmin/tree/main/.copilot/skills/judgment-day
Command: npx skills add https://github.com/AlejandroFerp/EcoAdmin --skill judgment-day-alejandroferp

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Parallel adversarial review protocol that launches two independent blind judge sub-agents simultaneously to review the same target, synthesizes their findings, applies fixes, and re-judges until both pass or escalates after 2 iterations.

Core Features & Use Cases

  • Parallel evaluation: two separate judges review the same target to surface diverse issues.
  • Verdict synthesis and iterative fixes: combine conclusions and re-judge up to two cycles with escalation if needed.
  • Trigger-based activation: responds to user phrases like judgment day, judgment-day, or dual review to start the process.

Quick Start

Provide a target to review and say the trigger Judgment Day to initiate dual blind reviewers.

Frequently Asked Questions about judgment-day

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

FAQPage Schema
How does dual blind code review improve software quality assurance?▼

A dual review process improves quality assurance by launching two independent blind judge sub-agents to evaluate the same target simultaneously, synthesizing their diverse findings to surface critical issues with higher confidence.

How do I trigger an adversarial review for architectural decisions?▼

You trigger an adversarial review by providing your target code or architectural decision and using the activation phrase Judgment Day. This initiates the parallel dual blind review process to evaluate your target.

What happens when two independent reviewers disagree during code verification?▼

When reviewers disagree during verification, the system synthesizes their verdicts, applies necessary fixes, and re-judges the target. This iterative cycle repeats up to two times before escalating unresolved issues.

Can I use parallel evaluation for feature validation in software engineering?▼

Yes, you can use parallel evaluation for feature validation. The protocol launches two separate blind judges to review your feature implementation, ensuring diverse perspectives verify logic and surface defects.

What are the limitations of automated adversarial review cycles?▼

The main limitation of automated adversarial review is the two-iteration maximum. If both judges do not pass the target after two rounds of fixes, the process stops and escalates unresolved issues.

Related Skills

Explore More Software Engineering Skills→
FrantssFrantss

code-review

Compare git diffs against repository standards and project specifications.

Community
Advanced
usk6666usk6666
11

review-gate

Automates the PR review cycle with parallel code and security checks.

Community
Advanced
nanorepublicananorepublica
61

Testing Unit Tests

Standardize unit-test coding practices across Claude Code projects.

Community
Basic
lchenriquelchenrique

parallel-agents

Coordinate multiple specialized agents for parallel analysis and synthesis.

Community
Advanced