<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Html on WRITELOOP</title><link>https://writeloop.dev/tags/html/</link><description>Recent content in Html on WRITELOOP</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 20 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://writeloop.dev/tags/html/index.xml" rel="self" type="application/rss+xml"/><item><title>Turning HTML into markdown with html-to-markdown</title><link>https://writeloop.dev/posts/turning-html-into-markdown/</link><pubDate>Wed, 20 May 2026 00:00:00 +0000</pubDate><guid>https://writeloop.dev/posts/turning-html-into-markdown/</guid><description>&lt;h1 id="how-i-did-that"&gt;How I did that?&lt;/h1&gt;
&lt;p&gt;The pi coding agent I use is pretty minimal by design. So every now and then I end up needing to create a skill or an extension to handle something specific.&lt;/p&gt;
&lt;p&gt;One of the first things I needed was a way to grab HTML from the web (blog posts, library docs) and turn it into markdown locally with a CLI tool. I didn&amp;rsquo;t want the agent to waste tokens parsing raw HTML itself.&lt;/p&gt;</description></item></channel></rss>