<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>SKILL on Chung-Hao Lee</title><link>https://chunghaolee.com/tags/skill/</link><description>Recent content in SKILL on Chung-Hao Lee</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 06 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://chunghaolee.com/tags/skill/index.xml" rel="self" type="application/rss+xml"/><item><title>【AI Side Project Vol.07】Multi-Lens Thinking: A Skill That Allows AI to Think From Your Perspective</title><link>https://chunghaolee.com/portfolio/multi_lens_thinking/</link><pubDate>Sat, 06 Jun 2026 00:00:00 +0000</pubDate><guid>https://chunghaolee.com/portfolio/multi_lens_thinking/</guid><description>&lt;p>&lt;strong>GitHub&lt;/strong>: &lt;a href="https://github.com/lch99310/multi-lens-thinking" target="_blank" rel="noreferrer">lch99310/multi-lens-thinking&lt;/a>&lt;/p>
&lt;hr>
&lt;h2 id="when-one-prompt-is-never-enough-why-i-built-multi-lens-thinking" class="relative group">When One Prompt Is Never Enough: Why I Built multi-lens-thinking &lt;span class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100">&lt;a class="group-hover:text-primary-300 dark:group-hover:text-neutral-700" style="text-decoration-line: none !important;" href="#when-one-prompt-is-never-enough-why-i-built-multi-lens-thinking" aria-label="Anchor">#&lt;/a>&lt;/span>&lt;/h2>&lt;h2 id="一個-prompt-永遠不夠為什麼我開發了這個多維視角分析框架" class="relative group">一個 Prompt 永遠不夠：為什麼我開發了這個多維視角分析框架 &lt;span class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100">&lt;a class="group-hover:text-primary-300 dark:group-hover:text-neutral-700" style="text-decoration-line: none !important;" href="#%e4%b8%80%e5%80%8b-prompt-%e6%b0%b8%e9%81%a0%e4%b8%8d%e5%a4%a0%e7%82%ba%e4%bb%80%e9%ba%bc%e6%88%91%e9%96%8b%e7%99%bc%e4%ba%86%e9%80%99%e5%80%8b%e5%a4%9a%e7%b6%ad%e8%a6%96%e8%a7%92%e5%88%86%e6%9e%90%e6%a1%86%e6%9e%b6" aria-label="Anchor">#&lt;/a>&lt;/span>&lt;/h2>&lt;p>There is a version of AI assistance that feels impressive the first time and hollow the tenth. You ask about gold markets, geopolitical risk, or whether a career move makes sense — and the model returns a polished, confident, and completely generic answer. One calibrated for the median reader. The problem is that the median reader is not you.&lt;/p></description></item></channel></rss>