<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Writing on Top AI Skills</title><link>https://topaiskills.com/tags/writing/</link><description>Recent content in Writing on Top AI Skills</description><generator>Hugo</generator><language>en</language><lastBuildDate>Thu, 15 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://topaiskills.com/tags/writing/index.xml" rel="self" type="application/rss+xml"/><item><title>Explore Then Exploit: Matt Pocock's Writing Skills (452K)</title><link>https://topaiskills.com/tutorials/guides/writing-shape-explore-exploit-narrative-experience/</link><pubDate>Thu, 15 Oct 2026 00:00:00 +0000</pubDate><guid>https://topaiskills.com/tutorials/guides/writing-shape-explore-exploit-narrative-experience/</guid><description>&lt;p&gt;Most &amp;ldquo;AI writing&amp;rdquo; skills do the same thing: you hand over a topic, prose comes back. &lt;a href="https://github.com/mattpocock/skills" rel="nofollow" target="_blank"&gt;mattpocock/skills&lt;/a&gt; went the other way with its newest writing family — &lt;code&gt;writing-fragments&lt;/code&gt; widens the space of what could be written and refuses to structure anything, then &lt;code&gt;writing-shape&lt;/code&gt; takes the pile and commits to an article, one paragraph at a time, arguing with you at every step. Neither skill can be triggered by the model. I read both SKILL.md files in full (5,922 and 3,558 bytes), plus their older sibling &lt;code&gt;writing-beats&lt;/code&gt;, and pulled the skills.sh counters on 2026-10-15.&lt;/p&gt;</description></item></channel></rss>