<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>MCP on Research Logs</title><link>https://williamresearch.com/tags/mcp/</link><description>Recent content in MCP on Research Logs</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Fri, 10 Apr 2026 00:05:00 +0700</lastBuildDate><atom:link href="https://williamresearch.com/tags/mcp/index.xml" rel="self" type="application/rss+xml"/><item><title>🧩 Decoding AI Skills: Prompt, Workflow, and MCP Without the Hype</title><link>https://williamresearch.com/posts/decoding-ai-skills-without-the-hype/</link><pubDate>Fri, 10 Apr 2026 00:05:00 +0700</pubDate><guid>https://williamresearch.com/posts/decoding-ai-skills-without-the-hype/</guid><description>&lt;h2 id="the-hook-why-skills-sound-smarter-than-they-are"&gt;The Hook: Why &amp;ldquo;Skills&amp;rdquo; Sound Smarter Than They Are&lt;/h2&gt;
&lt;p&gt;The current discourse around AI &amp;ldquo;skills&amp;rdquo; is noisy for a simple reason: the word sounds like capability, progress, even a form of learning. That framing is convenient for demos and marketplaces. It is also misleading.&lt;/p&gt;
&lt;p&gt;From a systems perspective, a skill is not intelligence. It is not a new reasoning engine. It is not proof that the model has learned a reusable capability in the way engineers usually mean learning. In practice, a skill is a structured way to constrain how a model receives instructions, how it decides the next step, and which tools it is allowed to call.&lt;/p&gt;</description></item></channel></rss>