# Experiment Audit

Audit experiment integrity before claiming results.

- Repository: https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep (18443 stars)
- Category: Writing
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill experiment-audit -g -a claude-code -y`
Codex: `npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill experiment-audit -g -a codex -y`
Cursor: `npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill experiment-audit -g -a cursor -y`
Gemini CLI: `npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill experiment-audit -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add wanshuiyin/Auto-claude-code-research-in-sleep`

## Description

Audit experiment integrity before claiming results. Uses cross-model review (external reviewer backend) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says \"审计实验\", \"check experiment integrity\", \"audit results\", \"实验诚实度\", or after experiments complete before writing claims.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Experiment Audit: Cross-Model Integrity Verification

> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.


> 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** It is
> verdict-bearing, it judges experiment integrity. Re-running that verdict on a
> timer adds no new signal, and a loop that accepts its own output to decide
> when to stop crosses into self-acquittal (`acceptance-gate.md`). Schedule the
> *external wait that precedes it*, experiments done → then audit **once**. See
> [`shared-references/external-cadence.md`](../shared-references/external-cadence.md).

Audit experiment integrity for: **$ARGUMENTS**

## Why This Exists

LLM agents can produce fraudulent experimental results through:
1. **Fake ground truth**, creating synthetic "reference" from model outputs, then reporting high agreement as performance
2. **Score normalization**, dividing metrics by the model's own max to get 0.99+
3. **Phantom results**, claiming numbers from files that don't exist or functions never called
4. **Insufficient scope**, reporting 2-scene pilots as "comprehensive evaluation"

These are NOT intentional deception, they are failure modes of optimizing agents that lack integrity constraints. This skill adds that constraint.

## Core Principle

The rest: https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/blob/HEAD/skills/experiment-audit/SKILL.md