skills.rest
czh-ee-2023
czh-ee-2023COMMUNITY
Explore all skills by this author →
WebsiteGitHub

experiment-audit

Audits experimental integrity via cross-model review and external backend.

Updated Jun 7, 2026
Search Tags:#fraud detection#cross-model review#experiment integrity#experiment verification#research auditing
One-click install
npx skills add https://github.com/czh-ee-2023/zotero-aris --skill experiment-audit-czh-ee-2023
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: experiment-audit
Source: https://github.com/czh-ee-2023/zotero-aris/tree/main/.claude/skills/experiment-audit
Command: npx skills add https://github.com/czh-ee-2023/zotero-aris --skill experiment-audit-czh-ee-2023

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires mcp__codex__codex, mcp__codex__codex-reply, mcp__manual_review__review, mcp__manual_review__review_reply, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill audits the integrity of experimental results before claims are made, using cross-model review to check for common fraud patterns.

Core Features & Use Cases

  • Fraud Detection: Checks for fake ground truth, score normalization fraud, phantom results, and insufficient scope.
  • Cross-Model Review: Utilizes an external reviewer backend to assess integrity.
  • Use Case: Run this Skill after experiments are completed but before claims are made to ensure the integrity of the results.

Quick Start

Run the experiment-audit skill with the path to your experiment directory.

Frequently Asked Questions about experiment-audit

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

FAQPage Schema
How do I detect fraud patterns in my experiment results before publication?▼

Experiment integrity auditing detects fraud patterns like fake ground truth, score normalization fraud, and phantom results by checking evaluation scripts and result files before claims are made.

What is cross-model review for research auditing and how does it work?▼

Cross-model review for research auditing uses an external reviewer backend, such as Codex MCP or Manual Review MCP, to assess experiment integrity and verify that results match paper claims.

How do I run an experiment verification audit on my research directory?▼

Run the audit skill with the path to your experiment directory after experiments are completed, and it will automatically check evaluation scripts and result files for common fraud patterns.

Do I need a specific backend to perform cross-model review of experiment integrity?▼

Yes, cross-model review requires an external reviewer backend like Codex MCP or Manual Review MCP to assess experiment integrity and check for insufficient scope or fake ground truth.

What common fraud patterns does an experiment integrity audit check for?▼

An experiment integrity audit checks for fake ground truth, score normalization fraud, phantom results, and insufficient scope in evaluation scripts, result files, and paper claims.

When should I run a research auditing check on my experiment files?▼

Run a research auditing check after experiments are completed but before claims are made in papers, ensuring result files and evaluation scripts are free from common fraud patterns.

Related Skills

Explore More Education & Research Skills→
dogekikidogekiki

experiment-audit

Audit experimental integrity by cross-referencing scripts, results, and claims against fraud patterns.

Community
Advanced
goupup-aigoupup-ai
2

experiment-audit

Audit machine learning experiment results for fraudulent reporting patterns.

Community
Advanced
in-the-loop-labsin-the-loop-labs
48

pr

Open the current branch's GitHub pull request in the pair-review web UI.

Official
Basic
xqinagxqinag

experiment-audit

Audit ML experiment integrity using configurable cross-model reviewer backends.

Community
Advanced