<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Agent-Skills on Abhishek Walia</title><link>https://awalia.dev/tags/agent-skills/</link><description>Recent content in Agent-Skills on Abhishek Walia</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>Abhishek Walia</copyright><lastBuildDate>Tue, 01 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://awalia.dev/tags/agent-skills/index.xml" rel="self" type="application/rss+xml"/><item><title>Agent Skills Don't Have to Be Flat</title><link>https://awalia.dev/blog/agent-skills-dont-have-to-be-flat/</link><pubDate>Tue, 01 Sep 2026 00:00:00 +0000</pubDate><guid>https://awalia.dev/blog/agent-skills-dont-have-to-be-flat/</guid><description>&lt;p&gt;I used to write Agent Skills as flat instruction files. This basically meant that a set of repeatable instructions I had would be converted into one skill, and before too long, I would have around 50 skills per repo. Each skill described one workflow, and they never called each other. That left a lot of repeated text across them.&lt;/p&gt;</description></item></channel></rss>