<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Code Review on Top AI Skills</title><link>https://topaiskills.com/tags/code-review/</link><description>Recent content in Code Review on Top AI Skills</description><generator>Hugo</generator><language>en</language><lastBuildDate>Fri, 21 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://topaiskills.com/tags/code-review/index.xml" rel="self" type="application/rss+xml"/><item><title>Code Review Skill: Two-Axis Review That Keeps Standards and Spec Honest</title><link>https://topaiskills.com/skills/general/code-review/</link><pubDate>Fri, 21 Aug 2026 00:00:00 +0000</pubDate><guid>https://topaiskills.com/skills/general/code-review/</guid><description>&lt;p&gt;A code review that only checks &amp;ldquo;does this look clean?&amp;rdquo; misses the more expensive failure: code that follows every standard but implements the wrong thing. Matt Pocock&amp;rsquo;s Code Review skill fixes that by running &lt;strong&gt;two reviews in parallel&lt;/strong&gt; — one against the repo&amp;rsquo;s coding standards, one against the originating spec — and reporting them side by side, never merged. It comes from the &lt;a href="https://github.com/mattpocock/skills" rel="nofollow" target="_blank"&gt;mattpocock/skills&lt;/a&gt; family (228K stars), which already powers &lt;a href="https://topaiskills.com/skills/general/handoff/"&gt;handoff&lt;/a&gt;, &lt;a href="https://topaiskills.com/skills/general/prototype/"&gt;prototype&lt;/a&gt;, and &lt;a href="https://topaiskills.com/tutorials/guides/domain-modeling-procedural-guide/"&gt;domain-modeling&lt;/a&gt;. I read the actual SKILL.md line by line, and the two-axis split is the sharpest idea in it.&lt;/p&gt;</description></item></channel></rss>