nodriver-browser

Automate persistent Chrome and Chromium sessions via the Chrome DevTools Protocol.

18|1|Updated Apr 8, 2026
One-click install
npx skills add https://github.com/appautomaton/webmaton --skill nodriver-browser
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nodriver-browser
Source: https://github.com/appautomaton/webmaton/tree/main/skills/nodriver-browser
Command: npx skills add https://github.com/appautomaton/webmaton --skill nodriver-browser

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires nodriver, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill solves the challenge of automating complex, interactive web tasks that require session persistence, JavaScript execution, and human-like interaction patterns which standard fetch-based scrapers cannot handle.

Core Features & Use Cases

  • Persistent Browser Sessions: Maintains a single, long-running Chrome/Chromium daemon across multiple agent turns, preserving cookies, login states, and tab history.
  • Interactive Automation: Provides primitives for clicking, typing, hovering, and scrolling, allowing agents to navigate SPAs, bypass anti-bot challenges, and complete multi-step forms.
  • Stable DOM Referencing: Uses a unique snapshotting system to assign stable, numbered references to interactive elements, ensuring reliable interaction even on dynamic pages.

Quick Start

Use the nodriver-browser skill to navigate to the target URL and perform a snapshot to identify interactive elements for subsequent actions.

Frequently Asked Questions about nodriver-browser

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

FAQPage Schema
How do I maintain persistent Chrome sessions for multi-step web automation?

You can maintain persistent Chrome sessions by using a long-running Chromium daemon that preserves cookies, login states, and tab history across multiple agent turns. This ensures session continuity for complex web interactions.

What is the best way to interact with dynamic DOM elements on JavaScript-rendered pages?

The best way to interact with dynamic DOM elements is using a snapshotting system that assigns stable, numbered references to interactive elements. This ensures reliable clicking and typing even on highly dynamic, JavaScript-rendered pages.

How do I bypass anti-bot challenges when automating Chromium browsers?

You can bypass anti-bot challenges by utilizing human-like interaction primitives such as clicking, typing, hovering, and scrolling. This high-fidelity control helps navigate SPAs and overcome detection mechanisms that block standard fetch requests.

Do I need the nodriver library to execute Chrome DevTools Protocol automation?

Yes, the nodriver library is required. It interfaces directly with the Chrome DevTools Protocol (CDP) to provide high-fidelity browser control, enabling JavaScript execution and human-like DOM manipulation in environments where static fetching fails.

Why does standard fetch-based scraping fail on single-page applications?

Standard fetch-based scraping fails on SPAs because it cannot execute JavaScript or maintain session continuity. Complex web tasks require persistent browser automation to handle dynamic rendering, multi-step forms, and interactive navigation.

When should I avoid using persistent browser sessions for web scraping?

You should avoid persistent browser sessions for simple, static data extraction where standard fetching is sufficient. Browser automation introduces unnecessary overhead for tasks that do not require JavaScript rendering or complex human-like interaction patterns.