<?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>Claude Code on Shin Li</title><link>https://shin13.github.io/tags/claude-code/</link><description>Recent content in Claude Code on Shin Li</description><generator>Hugo</generator><language>en-US</language><copyright>Shin Li</copyright><lastBuildDate>Thu, 07 May 2026 12:35:59 +0800</lastBuildDate><atom:link href="https://shin13.github.io/tags/claude-code/index.xml" rel="self" type="application/rss+xml"/><item><title>[Dev] Learning from Matt Pocock’s Agent Skills</title><link>https://shin13.github.io/notes/learning-from-matt-pocock-agent-skills/</link><pubDate>Thu, 07 May 2026 08:53:00 +0800</pubDate><guid>https://shin13.github.io/notes/learning-from-matt-pocock-agent-skills/</guid><description>&lt;p&gt;I recently read Matt Pocock’s article, &lt;a href="https://www.aihero.dev/5-agent-skills-i-use-every-day"&gt;“5 Agent Skills I Use Every Day”&lt;/a&gt;. It resonated with my experience using coding agents such as Claude Sonnet and Claude Opus.&lt;/p&gt;
&lt;p&gt;The article gave me a clearer language for something I have been feeling: good agent work depends on good engineering process. We need better questions, written context, small slices, tests, and codebases that agents can understand.&lt;/p&gt;</description></item></channel></rss>