<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Automation on Vibe Coding</title><link>https://vibecoding.rest/tags/automation/</link><description>Recent content in Automation on Vibe Coding</description><generator>Hugo</generator><language>en</language><atom:link href="https://vibecoding.rest/tags/automation/index.xml" rel="self" type="application/rss+xml"/><item><title>Puppeteer</title><link>https://vibecoding.rest/mcp-servers/puppeteer/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://vibecoding.rest/mcp-servers/puppeteer/</guid><description>&lt;p&gt;The Puppeteer server gives an agent control of a real (or headless) Chrome browser — navigating to URLs, clicking elements, filling in forms, and capturing screenshots as it goes.&lt;/p&gt;&#10;&lt;h2 id="why-it-matters"&gt;Why it matters&lt;/h2&gt;&#10;&lt;p&gt;Some tasks can only be verified by actually looking at rendered output — a UI change, a broken layout, a JavaScript-heavy page that a plain HTTP fetch can&amp;rsquo;t render. Browser automation closes that verification gap.&lt;/p&gt;</description></item><item><title>Playwright</title><link>https://vibecoding.rest/mcp-servers/playwright/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://vibecoding.rest/mcp-servers/playwright/</guid><description>&lt;p&gt;Playwright MCP gives an agent structured control over a real browser — Chromium, Firefox, or WebKit — using Playwright&amp;rsquo;s accessibility tree instead of pixel-based screenshots. It exposes tools for navigation, clicking, form filling, and page inspection so an agent can complete multi-step web tasks deterministically.&lt;/p&gt;</description></item><item><title>Skill Seekers</title><link>https://vibecoding.rest/skills/skill-seekers/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://vibecoding.rest/skills/skill-seekers/</guid><description>&lt;p&gt;Skill Seekers automatically converts any documentation website into a ready-to-use Claude skill, turning scattered docs into structured, invokable reference material.&lt;/p&gt;&#10;&lt;h2 id="why-a-skill-for-this"&gt;Why a skill for this&lt;/h2&gt;&#10;&lt;p&gt;Most third-party libraries have documentation but no packaged skill. Automating the conversion means any well-documented tool can get a working skill without hand-authoring one from scratch.&lt;/p&gt;</description></item><item><title>Chrome Relay</title><link>https://vibecoding.rest/skills/chrome-relay/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://vibecoding.rest/skills/chrome-relay/</guid><description>&lt;p&gt;Chrome Relay drives the user&amp;rsquo;s already-signed-in Chrome session — cookies, SSO, localhost included — through a local CLI bridge, as a real-browser counterpart to headless Playwright automation.&lt;/p&gt;&#10;&lt;h2 id="why-a-skill-for-this"&gt;Why a skill for this&lt;/h2&gt;&#10;&lt;p&gt;Some flows only work correctly inside an authenticated, already-logged-in browser session — SSO-gated internal tools, for instance. Relaying through the real Chrome session sidesteps re-authenticating a separate automated browser.&lt;/p&gt;</description></item><item><title>n8n Skills</title><link>https://vibecoding.rest/skills/n8n-skills/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://vibecoding.rest/skills/n8n-skills/</guid><description>&lt;p&gt;n8n Skills lets Claude directly understand and operate n8n automation workflows — reading, editing, and reasoning about workflow graphs rather than treating them as opaque JSON.&lt;/p&gt;&#10;&lt;h2 id="why-a-skill-for-this"&gt;Why a skill for this&lt;/h2&gt;&#10;&lt;p&gt;n8n workflows are graphs of connected nodes that are awkward to reason about as raw exported JSON. A skill that understands the workflow model can edit and debug workflows the way a human building them in the n8n UI would.&lt;/p&gt;</description></item><item><title>Loki Mode</title><link>https://vibecoding.rest/skills/loki-mode/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://vibecoding.rest/skills/loki-mode/</guid><description>&lt;p&gt;Loki Mode orchestrates dozens of coordinated AI agents to build, deploy, and operate a complete startup end-to-end, from a PRD through to a live, revenue-generating product.&lt;/p&gt;&#10;&lt;h2 id="why-a-skill-for-this"&gt;Why a skill for this&lt;/h2&gt;&#10;&lt;p&gt;Coordinating many agents toward one large goal needs explicit role division and hand-off structure, or the agents duplicate work or conflict. This skill packages that orchestration pattern rather than leaving it to be improvised per project.&lt;/p&gt;</description></item><item><title>Reviewpad</title><link>https://vibecoding.rest/tools/reviewpad/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://vibecoding.rest/tools/reviewpad/</guid><description>&lt;p&gt;Reviewpad lets teams define pull request automation as code, covering reviewer assignment, labeling, and merge rules, and layers AI-generated review comments on top so common issues get flagged without manual triage.&lt;/p&gt;</description></item></channel></rss>