chrome-automation

Automate Chrome browser actions on a real Chrome instance using agent-browser.

Updated Mar 4, 2026
One-click install
npx skills add https://github.com/zc277584121/marketing-skills --skill chrome-automation-zc277584121
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: chrome-automation
Source: https://github.com/zc277584121/marketing-skills/tree/main/skills/chrome-automation
Command: npx skills add https://github.com/zc277584121/marketing-skills --skill chrome-automation-zc277584121

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automates repetitive, error-prone browser tasks inside the user's existing Chrome session so the agent can reuse logged-in state, avoid re-authentication, and perform real interactions without launching separate browser profiles.

Core Features & Use Cases

  • Reuse existing Chrome: Connects to the user's real Chrome process via agent-browser and --auto-connect so cookies and sessions are preserved.
  • Deterministic interactions: List tabs, snapshot interactive elements, click, fill, type, press keys, take screenshots, evaluate JS, and verify results after each step.
  • Recording replay & cross-platform workflows: Parse and replay DevTools/Puppeteer/@puppeteer/replay recordings and run sequential subagents for publishing across social and marketing platforms.
  • Robust edge-case handling: Iframe workarounds, contenteditable vs textarea handling, fallback selection strategies, and explicit user confirmations before destructive actions.

Quick Start

Use the chrome-automation skill to connect to your running Chrome with agent-browser --auto-connect, list tabs to reuse a logged-in page, and perform the requested navigation or interaction.

Frequently Asked Questions about chrome-automation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate Chrome browser actions using my existing logged-in session?

Automate Chrome browser actions by connecting to your real Chrome process via agent-browser, which preserves cookies and sessions so you can navigate pages, fill forms, and click buttons without re-authentication.

Can I reuse my active Chrome cookies and tabs for marketing automation tasks?

Yes, reuse active Chrome cookies and tabs by connecting agent-browser with --auto-connect to your running Chrome instance, allowing the agent to list open tabs and perform interactions on logged-in pages.

How do I replay Puppeteer or DevTools recordings for cross-platform social media posting?

Replay Puppeteer or DevTools recordings by parsing them within the automation workflow, enabling sequential subagent orchestration to publish content across multiple social and marketing platforms.

Does browser automation work with complex page elements like iframes and contenteditable fields?

Browser automation handles complex page elements using snapshot-based interactive element references, iframe workarounds, contenteditable vs textarea handling, and fallback selection strategies for robust interactions.

What do I need to set up before running Chrome automation tasks?

Before running Chrome automation tasks, you need the agent-browser CLI installed and Chrome remote debugging enabled so the agent can connect to your real browser instance and execute actions.

How does browser automation handle destructive actions like form submissions and button clicks?

Browser automation handles destructive actions by requiring explicit user confirmations and performing verification checks after each step to ensure interactions completed successfully before proceeding.