<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>實證醫學 on 陳柏威醫師 Po-Wei Chen, MD</title><link>https://drpwchen.com/tags/%E5%AF%A6%E8%AD%89%E9%86%AB%E5%AD%B8/</link><description>Recent content in 實證醫學 on 陳柏威醫師 Po-Wei Chen, MD</description><image><title>陳柏威醫師 Po-Wei Chen, MD</title><url>https://drpwchen.com/og-default.png</url><link>https://drpwchen.com/og-default.png</link></image><generator>Hugo</generator><language>zh-TW</language><lastBuildDate>Tue, 07 Jul 2026 12:30:00 +0800</lastBuildDate><atom:link href="https://drpwchen.com/tags/%E5%AF%A6%E8%AD%89%E9%86%AB%E5%AD%B8/index.xml" rel="self" type="application/rss+xml"/><item><title>我把 journal club 的「讀論文腦」寫成了 AI skill，還逼它不能靠印象唬爛</title><link>https://drpwchen.com/posts/paper-tools/</link><pubDate>Tue, 07 Jul 2026 09:30:00 +0800</pubDate><guid>https://drpwchen.com/posts/paper-tools/</guid><description>我把 journal club 評讀一篇論文的整套流程，寫成兩個 Claude Code skill，還特地寫了兩支確定性的小程式，把證據等級與邏輯漏洞的判斷交給程式算，不讓 AI 靠整體印象唬爛。已經開源放上 GitHub。</description></item></channel></rss>