Agent skill

experiment-audit

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.

★ 15,641 stars MIT wanshuiyin/Auto-claude-code-research-in-sleep

Install this skill

This command installs the skill into the portable ~/.agents/skills directory. The homepage installer can generate the native path for your specific agent.

mkdir -p $HOME/.agents/skills/'experiment-audit' && curl -fsSL 'https://raw.githubusercontent.com/wanshuiyin/Auto-claude-code-research-in-sleep/HEAD/skills/skills-codex/experiment-audit/SKILL.md' -o $HOME/.agents/skills/'experiment-audit'/SKILL.md

View raw SKILL.md View repository

Skill details

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
SKILL.md path: skills/skills-codex/experiment-audit/SKILL.md
Author: wanshuiyin
Tags: agent-skill