skills.rest
SarveshPatkr
SarveshPatkrCOMMUNITY
Explore all skills by this author →
𝕏@sarveshpatkar13GitHub

Claw Browser

Automate browser actions for AI agents with a live remote browser.

4|Updated Mar 10, 2026
Search Tags:#cli#ai-agent#browser-automation#openclaw#novnc
One-click install
npx skills add https://github.com/SarveshPatkr/claw-browser --skill claw-browser
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Claw Browser
Source: https://github.com/SarveshPatkr/claw-browser/tree/main
Command: npx skills add https://github.com/SarveshPatkr/claw-browser --skill claw-browser

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires docker, python3, node, openssl, and includes scripts (resource) components.

What problem does it solve?

Claw Browser enables AI agents to automate browser tasks while preserving browser state through a human-in-the-loop workflow, reducing blocked tasks and handoffs.

Core Features & Use Cases

  • Script-driven browser automation via a CLI and noVNC-enabled UI
  • Human takeover for gated steps (CAPTCHA, login, 2FA) with state continuity
  • Persistent browser sessions for long-running tasks across tasks

Quick Start

Run the provided start script to boot the engine and connect the client to the live browser session.

Frequently Asked Questions about Claw Browser

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

FAQPage Schema
How do I automate browser tasks with a stateful AI agent workflow?▼

Stateful browser automation is achieved by using a CLI to control a live remote browser, allowing AI agents to execute tasks while preserving session state across multiple steps and reducing blocked handoffs.

Can a human take over browser automation for CAPTCHA or 2FA without losing session state?▼

Human takeover for gated steps like CAPTCHA and 2FA is supported through a noVNC-enabled UI, allowing manual unblocking while maintaining state continuity for the AI agent's ongoing workflow.

Do I need Docker and Python to run remote browser automation scripts?▼

Docker, Python3, Node, and OpenSSL are required dependencies to run the client-server setup and execute the repository's CLI scripts for live remote browser control.

How do persistent browser sessions work for long-running automation tasks?▼

Persistent browser sessions maintain state continuity across long-running tasks by operating a live remote browser environment, ensuring context is preserved even when execution pauses for human input.

What is the best way to unblock an AI agent during a gated browser automation step?▼

Unblocking gated steps is handled through a human-in-the-loop workflow where the human owner manually completes the required action via the noVNC UI, allowing the agent to resume its stateful workflow.

How do I set up API key configuration for authenticated browser control?▼

Optional API key configuration enables authenticated control of the browser automation engine, set up during the client-server initialization process before running the provided start script.

Related Skills

Explore More Software Engineering Skills→
me2Docme2Doc
6

Canvas Skill

Render HTML content on remote OpenClaw nodes via a local HTTP server.

Community
Intermediate
mrudmrud

oracle

Run long AI queries in persistent tmux sessions with the Oracle CLI.

Community
Advanced
samlaggzsamlaggz

live-browser-cdp-workflows

Share a live CDP-backed Chromium browser across GUI and Hermes automation.

Community
Advanced
felipesantiago-coderfelipesantiago-coder

Agent Browser

Automate web page navigation, clicking, form filling, and data extraction via CLI or Node.js runtime.

Community
Intermediate