<?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>Ai-Program on Wilson Wu</title><link>https://wilsonwu.me/en/tags/ai-program/</link><description>Recent content in Ai-Program on Wilson Wu</description><generator>Hugo -- 0.127.0</generator><language>en-US</language><lastBuildDate>Wed, 22 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://wilsonwu.me/en/tags/ai-program/index.xml" rel="self" type="application/rss+xml"/><item><title>AI Programming Enters the Skill Era: From Prompts to the Leap Toward Capability Packaging</title><link>https://wilsonwu.me/en/blog/2026/ai-skills/</link><pubDate>Wed, 22 Apr 2026 00:00:00 +0000</pubDate><guid>https://wilsonwu.me/en/blog/2026/ai-skills/</guid><description>Over the past year, the mainstream way developers interact with AI for programming has gone through a clear evolution:
Prompt -&amp;gt; Prompt Engineering -&amp;gt; Context Engineering -&amp;gt; Skill (Capability Packaging)
If a prompt is a one-off invocation of model capability, then a Skill is essentially a reusable intelligent capability module. It enables AI to evolve from &amp;ldquo;answering questions&amp;rdquo; to &amp;ldquo;executing tasks.&amp;rdquo;
This article will systematically explain:
What a Skill means in the context of AI programming The fundamental difference between a Skill and a prompt How to apply Skill thinking in VS Code + GitHub Copilot Chat Real engineering-level examples What Is a Skill?</description></item></channel></rss>