judgment-day

Runs blind dual-judge adversarial code review with bounded fix and re-judgment rounds.

Updated May 24, 2026
One-click install
npx skills add https://github.com/etrigan16/v0-cipher-ar --skill judgment-day-etrigan16
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: judgment-day
Source: https://github.com/etrigan16/v0-cipher-ar/tree/main/.opencode/skills/judgment-day
Command: npx skills add https://github.com/etrigan16/v0-cipher-ar --skill judgment-day-etrigan16

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Single-reviewer code reviews can miss defects or produce unverified findings. This Skill orchestrates an explicit dual-review process where two independent blind judges examine the same immutable target, so only findings confirmed by both judges trigger fixes. ## Core Features & Use Cases - Blind Dual Review: Launches two read-only judges in parallel against an identical immutable target with identical scope and criteria, then merges their findings into a frozen ledger. - Bounded Fix Rounds: Applies corrections only to severe findings confirmed by both judges, with at most two fix rounds and two scoped re-judgments before escalation. - Structured Verdicts: Produces a frozen ledger with confirmed, suspect, contradiction, and info counts, ending in a terminal state of approved or escalated. - Use Case: Before merging a critical authentication module, request a Judgment Day review so two independent judges verify correctness, security, and error handling, with fixes validated by scoped re-judgment. ## Quick Start Ask the assistant to run Judgment Day on a specific file or change set, for example by saying run judgment day on the auth module.

Frequently Asked Questions about judgment-day

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

FAQPage Schema
How do I run a dual adversarial code review?▼

Explicitly request Judgment Day for a concrete target. The orchestrator builds one immutable target, launches two blind read-only judges in parallel with identical scope, merges their findings into a frozen ledger, and fixes only severe findings both judges confirm.

What is the difference between Judgment Day and a normal code review?▼

Judgment Day replaces the ordinary review flow for a target and uses two independent blind judges whose agreement corroborates findings. A normal review uses a single reviewer or lens without the dual-confirmation and bounded re-judgment mechanism.

How many fix rounds does Judgment Day allow?▼

Judgment Day permits at most two fix rounds and two scoped re-judgments. If any severe issue remains after the second round, the transaction escalates and stops; no third round exists.

What happens when the two judges disagree?▼

When judges contradict each other, the finding is recorded as a contradiction and escalated for an explicit human decision. Findings reported by only one judge are marked suspect and are never auto-fixed.

When should I not use Judgment Day review?▼

Avoid it for routine low-risk changes where a single review pass suffices, since it requires explicit activation and a full dual-judge cycle. It is designed for targets where corroborated severity confirmation justifies the extra rounds.