/experiment-audit-skills-codex
Audit experiment integrity before claiming results. Uses fresh-agent GPT-6-Astra review (same-family provisional in the base Codex mirror) 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\"…
- 安裝次數
- 487
- 專案星數
- 1.8 萬 ★
- 授權
- MIT
- 專案更新
- 2026-11-01
怎麼裝
npx skills add https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep --skill experiment-audit安裝前請先看過原文內容。中文說明是 AI 翻譯，不保證安全。
原文
Audit experiment integrity before claiming results. Uses fresh-agent GPT-6-Astra review (same-family provisional in the base Codex mirror) 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.