<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:sy="http://purl.org/rss/1.0/modules/syndication/" xmlns:media="http://search.yahoo.com/mrss/"><channel><title>Workflow on k4i's blog</title><link>https://k4i.top/tags/workflow/</link><description>Recent content in Workflow on k4i's blog</description><generator>Hugo -- gohugo.io</generator><language>en</language><managingEditor>sky_io@outlook.com (K4i)</managingEditor><webMaster>sky_io@outlook.com (K4i)</webMaster><copyright>All content is subject to the license of &lt;a rel="license noopener" href="https://creativecommons.org/licenses/by-nc-sa/4.0/" target="_blank"&gt;CC BY-NC-SA 4.0&lt;/a&gt; .</copyright><lastBuildDate>Sat, 23 May 2026 10:30:00 +0800</lastBuildDate><atom:link href="https://k4i.top/tags/workflow/index.xml" rel="self" type="application/rss+xml"/><item><title>Agent Skill Management: Turning AI Assistants from Clever to Reliable</title><link>https://k4i.top/posts/agent-skill-management/</link><pubDate>Sat, 23 May 2026 10:30:00 +0800</pubDate><author>sky_io@outlook.com (K4i)</author><atom:modified>Sat, 30 May 2026 00:36:50 +0800</atom:modified><guid>https://k4i.top/posts/agent-skill-management/</guid><description>&lt;h2 id="why-skills-matter"&gt;Why Skills Matter&lt;/h2&gt;
&lt;p&gt;After using coding agents for a while, I have found that the limiting factor is often not whether the model is clever enough today. It is whether the agent can reliably reuse experience.&lt;/p&gt;
&lt;p&gt;In a real repository, there are many implicit rules: which test command to run, which files should not be touched casually, where generated images belong, what must be checked before publishing, and whether a bug report should trigger root-cause analysis before patching. Humans handle these rules through memory and habit. An agent does not automatically know them at startup. Putting everything into one giant &lt;code&gt;AGENTS.md&lt;/code&gt; is not ideal either: the context grows, trigger boundaries blur, and the result becomes &amp;ldquo;everything is written down, but the important part may still not fire at the right time.&amp;rdquo;&lt;/p&gt;</description><dc:creator>K4i</dc:creator><media:content url="https://k4i.top//images/icons/terminal.png" medium="image"><media:title type="html">featured image</media:title></media:content><category>agent</category><category>codex</category><category>skills</category><category>workflow</category><category>notes</category></item></channel></rss>