<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Skill on Chuanxilu for Skilled Homo sapiens</title><link>https://blog.chuanxilu.net/en/tags/skill/</link><description>Recent content in Skill on Chuanxilu for Skilled Homo sapiens</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Sun, 21 Jun 2026 08:00:00 +0800</lastBuildDate><atom:link href="https://blog.chuanxilu.net/en/tags/skill/index.xml" rel="self" type="application/rss+xml"/><item><title>kdatasrc-helper: Let AI Agents Query Financial Data Directly</title><link>https://blog.chuanxilu.net/en/posts/2026/06/kdatasrc-helper-financial-data-skill/</link><pubDate>Sun, 21 Jun 2026 08:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/06/kdatasrc-helper-financial-data-skill/</guid><description>kimi CLI&amp;#39;s datasource plugin can query stock quotes, macro indicators, corporate registries, and academic papers, but calling it from an AI agent workflow is awkward. kdatasrc-helper wraps it: single query, batch parallel, auto-parse, market-aware merge. This post covers its design and usage.</description></item></channel></rss>