<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Claude on cloud_affects</title><link>https://cloudaffects.com/tags/claude/</link><description>Recent content in Claude on cloud_affects</description><generator>Hugo</generator><language>en</language><copyright>CC BY-NC-SA 4.0</copyright><lastBuildDate>Sat, 18 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://cloudaffects.com/tags/claude/index.xml" rel="self" type="application/rss+xml"/><item><title>claude-cookbooks — Anthropic's Reference Notebooks</title><link>https://cloudaffects.com/gems/claude-cookbooks/</link><pubDate>Sat, 18 Apr 2026 00:00:00 +0000</pubDate><guid>https://cloudaffects.com/gems/claude-cookbooks/</guid><description>&lt;p&gt;&lt;a href="https://github.com/anthropics/claude-cookbooks"&gt;claude-cookbooks&lt;/a&gt; is Anthropic&amp;rsquo;s pile of Jupyter notebooks for building with the Claude API. 40k stars, MIT, mostly Python. Not a tutorial series. Reference code you run, diff against your own, and copy from.&lt;/p&gt;
&lt;p&gt;Worth pulling up: prompt caching, tool use with SQL and a calculator, sub-agents (Haiku feeding Opus), PDF parsing, JSON mode, moderation filters, and the eval notebooks. The evals are the quiet one. Most of us ship prompt changes on vibes. These show how to score a change against a held-out set before it merges.&lt;/p&gt;</description></item></channel></rss>