📦

judge

Name: judge
Author: 2389-research

Content revision r1 Safe ⚙️ External commands

Score Code Implementation Cookoffs

Comparing multiple AI-built implementations can be inconsistent and slow. This skill provides a fixed rubric for Claude, Codex, and Claude Code reviews.

Supports: Claude Codex Code(CC)

🥉 78 Bronze

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "judge" from https://skillstore.io/skills/2389-research-judge.md and its manifest at https://skillstore.io/api/skills/2389-research-judge/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/2389-research-judge.md Signed manifest GET /api/skills/2389-research-judge/manifest Signed lockfile GET /api/skills/2389-research-judge/lockfile

Test it

Using "judge". Compare two implementations that both pass tests but differ in complexity.

Expected outcome:

A worksheet with passing gates, five criterion scores, total scores, and a winner chosen for lower justified complexity.

Using "judge". Judge three variants where one handles scale poorly.

Expected outcome:

A scorecard that flags feasibility risks, lowers robustness for the weak variant, and explains the final winner.

Using "judge". Choose between two approaches with different product fit.

Expected outcome:

A decision record that applies the fitness gate and documents what the losing approach did better.

Security Audit

Safe

v6 • 7/6/2026 Open versioned report

The two static findings are false positives caused by Markdown template text. The fenced block is an output format example, and the trade-off placeholder does not request system reconnaissance. No prompt injection, data exfiltration, or malicious intent was found in SKILL.md.

Files scanned

178

Lines analyzed

Review items

False positives ignored

Risk Factors

⚙️ External commands (1)

SKILL.md:18-129

No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/2389-research-judge/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/2389-research-judge/security.svg)](https://skillstore.io/skills/2389-research-judge?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/2389-research-judge?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/2389-research-judge/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/2389-research-judge.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

2389-research. (2026). judge security audit report (audit version 6) [Author version unspecified]. Skillstore. https://skillstore.io/skills/2389-research-judge/audits/6

BibTeX citation

@techreport{2389-research-2389-research-judge-2026,
  author = {2389-research},
  title = {judge security audit report (audit version 6)},
  institution = {Skillstore},
  year = {2026},
  number = {6},
  url = {https://skillstore.io/skills/2389-research-judge/audits/6},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "judge security audit report (audit version 6)"
version: "unspecified"
type: report
authors:
  - name: "2389-research"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/2389-research-judge/audits/6"
identifiers:
  - type: other
    value: "skillstore:2389-research-judge:audit:6"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Compare AI Code Variants

Score several generated implementations of the same design and choose the strongest result.

Review Engineering Cookoffs

Use one rubric to compare competing solutions during an internal implementation challenge.

Document Selection Decisions

Create a repeatable decision record with scores, gates, winner rationale, and trade-offs.

Try These Prompts

Score Two Implementations

Use the judge skill to compare impl-1 and impl-2. Fill every worksheet section and select the winner.

Judge A Cookoff

Use the judge skill for impl-1, impl-2, and impl-3. Apply all five scoring criteria and hard gates.

Evaluate Omakase Variants

Use the judge skill to compare variant-a and variant-b. Treat fitness differences as real product fit differences.

Audit A Close Decision

Use the judge skill and explain any tied or close criteria. Make the winner rationale evidence-based and specific.

Best Practices

Provide all candidate implementations and the original requirements before invoking the skill.
Use evidence from tests, code structure, and realistic user scenarios for each score.
Keep scores as integers from 1 to 5 and fill every required section.

Avoid

Do not use the skill before the implementations and requirements are available.
Do not skip the worksheet and provide only a winner.
Do not award half points or change the scoring scale.

Frequently Asked Questions

When should I use this skill?

Use it when two or more implementations need a structured comparison and a clear winner.

Does the skill execute tests?

No. It records test results supplied in context and uses them during scoring.

Can it compare different designs?

Yes. The omakase guidance supports different approaches and treats fitness gaps as product fit differences.

What criteria does it score?

It scores fitness for purpose, justified complexity, readability, robustness and scale, and maintainability.

Can I change the output format?

The skill is designed for a fixed worksheet. Changing the format reduces consistency across reviews.

Is this a security audit tool?

No. It can notice robustness issues, but it is not a dedicated security assessment.

Developer Details

Author

2389-research

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/2389-research/claude-plugins/tree/main/test-kitchen/skills/judge

Ref

c1fdca50ff516318f65fed0d7f9e82797c5171dc

Maintenance freshness

7/18/2026

Usage

7 downloads · 158 views

File structure

📄 SKILL.md