← Auto-claude-code-research-in-sleep

/result-to-claim-skills-codex

檢查與出貨Auto-claude-code-research-in-sleepAI翻譯

實驗完成後,判斷結果支持哪些主張、不支持哪些,以及還缺哪些證據。由次要 Codex agent 對照預期主張評估結果,並導向下一步:轉向、補充或確認。

安裝次數
526
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 result-to-claim

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

Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. A secondary Codex agent evaluates results against intended claims and routes to next action (pivot, supplement, or confirm). Use after experiments finish — before writing the paper or running ablations.