<?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>AI Path L1→L2 Upgrade Guide on Chuanxilu for Skilled Homo sapiens</title><link>https://blog.chuanxilu.net/en/series/ai-path-l1l2-upgrade-guide/</link><description>Recent content in AI Path L1→L2 Upgrade Guide on Chuanxilu for Skilled Homo sapiens</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Wed, 12 Aug 2026 16:00:00 +0800</lastBuildDate><atom:link href="https://blog.chuanxilu.net/en/series/ai-path-l1l2-upgrade-guide/index.xml" rel="self" type="application/rss+xml"/><item><title>Automating Skill Documents: Four Core Blocks for Tailored AI Workflows</title><link>https://blog.chuanxilu.net/en/posts/2026/08/ai-path-l1-l2-week3-day14/</link><pubDate>Wed, 12 Aug 2026 16:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/08/ai-path-l1-l2-week3-day14/</guid><description>Day 14 practice: automate your skill documents. Four core blocks (identity, input, output requirements, quality requirements) are all it takes for the AI to build your skill.</description></item><item><title>Day 13: Turning a Workflow into a Skill Kit</title><link>https://blog.chuanxilu.net/en/posts/2026/08/ai-path-l1-l2-week3-day13/</link><pubDate>Thu, 06 Aug 2026 16:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/08/ai-path-l1-l2-week3-day13/</guid><description>AI Path L1→L2 Day 13 practice: build a picture book generation workflow into a reusable skill kit through six conversations with an AI agent. Real project, real prompts, real outputs.</description></item><item><title>Your AI Toolbox: How Scripts and AI Agent Work Together</title><link>https://blog.chuanxilu.net/en/posts/2026/08/ai-path-l1-l2-week3-day12/</link><pubDate>Tue, 04 Aug 2026 10:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/08/ai-path-l1-l2-week3-day12/</guid><description>AI Path L1→L2 Day 12: how scripts and AI agent split a batch job. A 71-page Dolch picture book project shows the full pipeline: constraints, structured tables, scripts, and verification.</description></item><item><title>Day 11: How to Verify What AI Gives You</title><link>https://blog.chuanxilu.net/en/posts/2026/07/ai-path-l1-l2-week3-day11/</link><pubDate>Tue, 28 Jul 2026 11:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/07/ai-path-l1-l2-week3-day11/</guid><description>AI Path L1→L2 Day 11: GCO works both ways: it functions as a spec on the way in and a checklist on the way back. Three no-code methods to check whether AI actually did what you asked.</description></item><item><title>Day 10: Your AI Feels Like an Intern? Try the GCO Framework</title><link>https://blog.chuanxilu.net/en/posts/2026/07/ai-path-l1-l2-week3-day10/</link><pubDate>Tue, 21 Jul 2026 07:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/07/ai-path-l1-l2-week3-day10/</guid><description>Here are three exercises that show how vague versus clear task descriptions change AI output, along with the GCO framework that resolves the problem.</description></item><item><title>Codex Cold Start: From Installation to Your First Command</title><link>https://blog.chuanxilu.net/en/posts/2026/07/ai-path-codex-cli-setup/</link><pubDate>Mon, 13 Jul 2026 07:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/07/ai-path-codex-cli-setup/</guid><description>AI Path bonus article: with GPT-5.6 released and Codex merged into the ChatGPT desktop app, here&amp;#39;s how to get started: desktop or CLI, from account setup to your first instruction.</description></item><item><title>OpenCode Cold Start: DeepSeek V4 Flash Free in 5 Minutes</title><link>https://blog.chuanxilu.net/en/posts/2026/07/ai-path-opencode-zen-setup/</link><pubDate>Mon, 06 Jul 2026 06:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/07/ai-path-opencode-zen-setup/</guid><description>AI Path bonus article: a complete cold-start walkthrough. Install OpenCode, register a Zen account, configure your API key, and select the free DeepSeek V4 Flash model.</description></item><item><title>Day 9: API Caching Basics and Why Unit Price Isn't the Whole Story</title><link>https://blog.chuanxilu.net/en/posts/2026/06/ai-path-l1-l2-week2-day9/</link><pubDate>Tue, 30 Jun 2026 07:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/06/ai-path-l1-l2-week2-day9/</guid><description>L1→L2 Week 2 Day 9: Understand how API caching works, evaluate providers by cache hit rate and pricing, and pick a provider that fits your workload.</description></item><item><title>Day 8: Autonomous AI, Automation Without Writing Code</title><link>https://blog.chuanxilu.net/en/posts/2026/06/ai-path-l1-l2-week2-day8/</link><pubDate>Sun, 28 Jun 2026 07:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/06/ai-path-l1-l2-week2-day8/</guid><description>L1 to L2 Week 2 Day 8: Understand autonomous execution AI (Claude Code, OpenCode, Codex), learn to describe tasks so AI can handle the coding, and complete a hands-on file organization exercise.</description></item><item><title>Day 5 Exercise: Teach Your Script to Read More File Formats</title><link>https://blog.chuanxilu.net/en/posts/2026/06/ai-path-l1-l2-week2-day5/</link><pubDate>Fri, 12 Jun 2026 07:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/06/ai-path-l1-l2-week2-day5/</guid><description>L1→L2 Week 2 Day 5 exercise: extend the Part 2 batch script to handle PDF, Word, CSV, and JSON files instead of just .md and .txt.</description></item><item><title>AI Path L1→L2 Upgrade Guide (2): From One Call to Batch Processing: Let Your Program Do 100 Tasks</title><link>https://blog.chuanxilu.net/en/posts/2026/06/ai-path-l1-l2-week1-day4/</link><pubDate>Tue, 09 Jun 2026 07:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/06/ai-path-l1-l2-week1-day4/</guid><description>Part 2 of the AI Path L1→L2 Upgrade Guide: learn to read files with Python, call the API, save results, then loop through an entire folder to build a complete script that auto-summarizes 100 documents.</description></item><item><title>Day 3 Exercise: API Parameter Experiments</title><link>https://blog.chuanxilu.net/en/posts/2026/06/ai-path-l1-l2-week1-day3/</link><pubDate>Mon, 08 Jun 2026 07:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/06/ai-path-l1-l2-week1-day3/</guid><description>Day 3 companion exercise for the AI Path L1→L2 Upgrade Guide: experiment with temperature and max_tokens, observe how they change AI output, and calculate actual API costs.</description></item><item><title>Day 2 Exercise: Run the Same Request on an Aggregator Platform</title><link>https://blog.chuanxilu.net/en/posts/2026/06/ai-path-l1-l2-week1-day2/</link><pubDate>Sat, 06 Jun 2026 07:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/06/ai-path-l1-l2-week1-day2/</guid><description>Day 2 companion exercise for the AI Path L1→L2 Upgrade Guide: register on an aggregator platform, change two parameters, and see how the same code works across platforms.</description></item><item><title>Day 1 Exercise: Run Your First API Code</title><link>https://blog.chuanxilu.net/en/posts/2026/06/ai-path-l1-l2-week1-day1/</link><pubDate>Tue, 02 Jun 2026 07:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/06/ai-path-l1-l2-week1-day1/</guid><description>Day 1 companion exercise for the AI Path L1→L2 Upgrade Guide: run the hello_api.py from Part 1, see AI reply in your terminal, with a troubleshooting guide for common errors.</description></item><item><title>AI Path L1→L2 Upgrade Guide (1): Your First API Call</title><link>https://blog.chuanxilu.net/en/posts/2026/06/ai-path-l1-l2-week1/</link><pubDate>Mon, 01 Jun 2026 07:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/06/ai-path-l1-l2-week1/</guid><description>First part of the AI Path L1→L2 Upgrade Guide series. Learn what APIs are, how they differ from chat windows, register for API accounts (DeepSeek/OpenRouter/Claude), set up Python, run your first API call, and build intuition for token, temperature, context window, and max_tokens.</description></item></channel></rss>