<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: dlfelps</title><link>https://news.ycombinator.com/user?id=dlfelps</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 18 May 2026 09:11:11 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=dlfelps" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by dlfelps in "Show HN: Statewright – Visual state machines that make AI agents reliable"]]></title><description><![CDATA[
<p>How do you force the agent to use an MCP server? From my experience it can be tricky to get an agent to call an MCP server in the first place. This must require something beyond instructions in the CLAUDE.md.</p>
]]></description><pubDate>Sun, 17 May 2026 15:57:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=48170067</link><dc:creator>dlfelps</dc:creator><comments>https://news.ycombinator.com/item?id=48170067</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48170067</guid></item><item><title><![CDATA[New comment by dlfelps in "Show HN: Sx – an open-source package manager for AI skills, MCPs, and commands"]]></title><description><![CDATA[
<p>Could there be a way to somehow create / export / import a local config of skills? it seems like that could be really useful to share across a single team.</p>
]]></description><pubDate>Sun, 17 May 2026 15:54:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=48170032</link><dc:creator>dlfelps</dc:creator><comments>https://news.ycombinator.com/item?id=48170032</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48170032</guid></item></channel></rss>