wanshuiyin/Auto-claude-code-research-in-sleep✦ 精选0°

experiment-audit

仓库创建 2026年3月10日最近提交 5 天前SkillHot 收录 20 天前

⬈ GitHub 仓库 ⬈ SKILL.md 原文件 ⬇ Raw 原始文件

▸ 精选理由

用于发现伪造或不当归一化等科学诚信问题

▸ 风险提示

会作出判断性结论，误判有声誉风险

这个 Skill 做什么

对实验结果做跨模型/跨视角的诚信与有效性审查。

能帮你在宣称结果前把实验的诚信问题挑出来，像是否用了假标注、分数归一作弊、虚假结果或覆盖范围不足等。常在实验跑完、准备写结论或投稿/同行评审前使用，作为最后的校验步骤。特点是通过跨模型复核和外部审阅后台做交叉验证，给出独立且有判定力的审计意见，而不是简单的格式检查。

▸ 展开 SKILL.md 英文原文

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.

研究检索实验审计诚信核查结果验证通用

1.4w

Stars

1.2k

Forks

仓库内 Skill

+844

7 日增星

安装 / 使用

给你的 Agent 一句话（通用）

帮我安装这个 skill：https://raw.githubusercontent.com/wanshuiyin/Auto-claude-code-research-in-sleep/main/skills/experiment-audit/SKILL.md

或 curl 直取 SKILL.md

curl -fsSL "https://raw.githubusercontent.com/wanshuiyin/Auto-claude-code-research-in-sleep/main/skills/experiment-audit/SKILL.md"

SKILL.MD 节选查看完整文件 ↗

# Experiment Audit: Cross-Model Integrity Verification

> 🔒 **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**

via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有