judgment-day

Run high-rigor adversarial review cycles until implementation quality is accepted or escalated.

Skill by imported-and-adapted-by-lucy-camilo

IndexedApache-2.0★ 19

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/camiloandresgtruniandes-judgment-day

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Run high-rigor adversarial review cycles until implementation quality is accepted or escalated. Trigger: when the user requests judgment day, adversarial review, dual review, or extra-rigorous validation.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/judgment-day

What's inside

Skill name: judgment-day
Description: Run high-rigor adversarial review cycles until implementation quality is accepted or escalated. Trigger: when the user requests judgment day, adversarial review, dual review, or extra-rigorous validation.
License: Apache-2.0
Metadata: author: imported-and-adapted-by-lucy-camilo · version: 1.1
Instructions: 45 lines in SKILL.md · view on GitHub

Files (1)

SKILL.md

SKILL.md (first lines)

# Judgment Day Review

## When to Use

Use when a change needs more rigor than standard verification, especially for security-sensitive, architectural, data-migration, or high-risk PRs.

## Rules

- Do not replace SDD Verify; this is an additional rigor layer.
- Run two independent review passes with different perspectives.
- Keep evidence traceable to files, tests, commands, and observed behavior.
- Synthesize findings into concrete fix tasks.
- Re-run review after fixes with an explicit delta report.
- Escalate after repeated failures instead of looping forever.

## Review Passes

1. **Correctness reviewer** — spec compliance, edge cases, tests, regressions.
2. **Adversarial reviewer** — security, misuse, data loss, concurrency, operational risks.

## Output Format

```markdown
## Judgment Day Result

### Verdict
Accepted / Fixes required / Escalate

### Evidence
- [test/build/lint/inspection evidence]

### Correctness Findings
- [finding, severity, file:line]

### Adversarial Findings
- [finding, severity, file:line]

### Required Fix Tasks
- [ ] [concrete task]

### Delta After Fixes
- [what changed and what was re-verified]
```

From CamiloAndresGTRUniandes/lucy-ai, Apache-2.0.

Signals

Stars: 19
Forks: 2
Open issues: 0
Last commit (this folder): Jul 29, 2026 (3 months ago)
Last release: Jul 31, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Version: 1.1
License: Apache-2.0
Repository: github.com/CamiloAndresGTRUniandes/lucy-ai
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from imported-and-adapted-by-lucy-camilo

Cite this page

judgment-day skill. Agent Mart. https://agentmart.dev/skills/camiloandresgtruniandes-judgment-day (last updated 2026-10-24)