<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Skills on Eugeniusz Zabłocki Blog</title>
    <link>https://ezablocki.com/tags/skills/</link>
    <description>Recent content in Skills on Eugeniusz Zabłocki Blog</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <copyright>© Eugeniusz Zabłocki</copyright>
    <lastBuildDate>Wed, 27 May 2026 10:00:00 +0200</lastBuildDate><atom:link href="https://ezablocki.com/tags/skills/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Beyond Prompt Files: Cursor Skills and Subagents</title>
      <link>https://ezablocki.com/posts/cursor-skills-and-subagents/</link>
      <pubDate>Wed, 27 May 2026 10:00:00 +0200</pubDate>
      
      <guid>https://ezablocki.com/posts/cursor-skills-and-subagents/</guid>
      <description>You built a /review-diff command. Fifty lines of Markdown: check scope creep, flag missing tests, don&amp;rsquo;t edit files. You run it before every PR. Perfect.
Every time you run it, the same failure mode shows up: the agent &amp;ldquo;reviews&amp;rdquo; your auth middleware change by rewriting three unrelated components, deletes a test it decided was redundant, and gives you a cheerful summary that never mentions the security regression you introduced two files up.</description>
    </item>
    
  </channel>
</rss>
