<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Slash-Commands on Chen Kai Blog</title><link>https://www.chenk.top/en/tags/slash-commands/</link><description>Recent content in Slash-Commands on Chen Kai Blog</description><generator>Hugo</generator><language>en</language><lastBuildDate>Mon, 27 Apr 2026 09:00:00 +0000</lastBuildDate><atom:link href="https://www.chenk.top/en/tags/slash-commands/index.xml" rel="self" type="application/rss+xml"/><item><title>Claude Code Hands-On (10): Skills, and When to Reach for Each Extension Mechanism</title><link>https://www.chenk.top/en/claude-code-learn/10-skills-decision-tree/</link><pubDate>Mon, 27 Apr 2026 09:00:00 +0000</pubDate><guid>https://www.chenk.top/en/claude-code-learn/10-skills-decision-tree/</guid><description>&lt;p>Claude Code now has four extension mechanisms: slash commands, MCP servers, hooks, and Skills. They overlap. The first time you have a &amp;ldquo;Claude should know how to do X&amp;rdquo; thought, the question is &lt;em>which&lt;/em> of the four to use.&lt;/p>
&lt;p>This is the closing chapter of the series. Let me lay out the decision tree.&lt;/p>
&lt;p>&lt;figure class="article-figure">
 &lt;img src="https://blog-pic-ck.oss-cn-beijing.aliyuncs.com/posts/en/claude-code-learn/10-skills-decision-tree/illustration_1.png" alt="Claude Code Hands-On (10): Skills, and When to Reach for Each Extension Mechanism — Chapter overview" loading="lazy" decoding="async" class="content-image">
 
&lt;/figure>
&lt;/p></description></item><item><title>Claude Code Hands-On (3): Custom Slash Commands and Conversation Control</title><link>https://www.chenk.top/en/claude-code-learn/03-custom-commands/</link><pubDate>Mon, 20 Apr 2026 09:00:00 +0000</pubDate><guid>https://www.chenk.top/en/claude-code-learn/03-custom-commands/</guid><description>&lt;p>Built-in slash commands like &lt;code>/clear&lt;/code> and &lt;code>/init&lt;/code> are the visible part of the iceberg. The main point of the system is for you to write your own commands, which live in your repo.&lt;/p>
&lt;p>&lt;figure class="article-figure">
 &lt;img src="https://blog-pic-ck.oss-cn-beijing.aliyuncs.com/posts/en/claude-code-learn/03-custom-commands/illustration_1.png" alt="Claude Code Hands-On (3): Custom Slash Commands and Conversation Control — Chapter overview" loading="lazy" decoding="async" class="content-image">
 
&lt;/figure>
&lt;/p>
&lt;hr>
&lt;h2 id="what-a-slash-command-is" class="heading-anchor">What a slash command is&lt;a href="#what-a-slash-command-is" class="heading-link" aria-label="Permalink to this section" title="Copy link to this section">#&lt;/a>
&lt;/h2>&lt;p>A file at &lt;code>.claude/commands/&amp;lt;name&amp;gt;.md&lt;/code>. Contents are a Markdown prompt. Filename becomes the command. After creating the command, you need to restart Claude Code (one of the few places it isn&amp;rsquo;t hot-reloaded).&lt;/p></description></item></channel></rss>