<?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>Prompt Engineering on MK's Lab</title><link>https://blog.mklee.org/tags/prompt-engineering/</link><description>Recent content in Prompt Engineering on MK's Lab</description><generator>Hugo -- 0.146.0</generator><language>zh-tw</language><lastBuildDate>Tue, 24 Mar 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://blog.mklee.org/tags/prompt-engineering/index.xml" rel="self" type="application/rss+xml"/><item><title>讓 AI Agent 的技能自我進化：用 GEPA 自動優化 SKILL.md</title><link>https://blog.mklee.org/posts/2026-03-gepa-skill-evolution/</link><pubDate>Tue, 24 Mar 2026 00:00:00 +0000</pubDate><guid>https://blog.mklee.org/posts/2026-03-gepa-skill-evolution/</guid><description>借鏡 ICLR 2026 的 GEPA 論文，用 MiniMax M2.5 建了一套 skill 自動演化 pipeline。blog-writer 從 84 分提升到 95 分，但過程中學到的教訓比分數本身更有價值。</description></item></channel></rss>