DE

A CLI tool for controlling browser sessions, automating form entry, and extracting data from websites.

Install

mkdir -p .claude/skills/dev-browser && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/460" && unzip -o skill.zip -d .claude/skills/dev-browser && rm skill.zip

Installs to .claude/skills/dev-browser

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.
364 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Intermediate

Key capabilities

  • Navigate websites and fill forms
  • Capture screenshots of web elements
  • Maintain persistent browser page state
  • Execute sandboxed JavaScript scripts
  • Manage browser idle timeouts for unattended tasks

How it works

The tool operates as a CLI that launches and controls browser instances using sandboxed JavaScript. It manages persistent profiles to maintain login sessions across automated tasks.

Inputs & outputs

You give it
Browser interaction commands and JavaScript scripts
You get back
Browser state, screenshots, or extracted web data

When to use dev-browser

  • Automate website login workflows
  • Extract data from a web page
  • Test web application functionality
  • Take screenshots of specific elements

About this skill

Dev Browser

A CLI for controlling browsers with sandboxed JavaScript scripts.

Installation

npm install -g dev-browser
dev-browser install

Usage

Run dev-browser --help to learn more.

Named daemon-launched browsers persist by default. For unattended work, --idle-timeout 5m closes each launched browser after inactivity while preserving its profile and login state. The setting never closes Chrome attached with --connect; use --idle-timeout 0 to disable configured cleanup.

When not to use it

  • Non-browser based automation tasks
  • Environments where CLI installation is restricted

Prerequisites

npm

Limitations

  • Requires manual installation of browser binaries via CLI
  • Idle timeout settings may prematurely close browsers if not configured correctly

How it compares

Unlike manual browser control, this tool automates interactions through a CLI and maintains persistent state for multi-step workflows.

Compared to similar skills

dev-browser side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
dev-browser (this skill)534moReviewIntermediate
agent-browser303moReviewIntermediate
browser-tools69moReviewIntermediate
browser37moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

agent-browser

vercel-labs

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

3075

browser-tools

Whamp

Lightweight Chrome automation toolkit with shared configuration, JSON-first output, and six focused scripts for starting, navigating, inspecting, capturing, evaluating, and cleaning up browser sessions.

694

browser

cexll

This skill should be used for browser automation tasks using Chrome DevTools Protocol (CDP). Triggers when users need to launch Chrome with remote debugging, navigate pages, execute JavaScript in browser context, capture screenshots, or interactively select DOM elements. No MCP server required.

346

agent-browser-skill

MGdaasLab

基于 agent-browser CLI 的浏览器自动化工具。提供快照获取、元素交互、截图等功能。推荐用于需要页面快照分析、通过 ref 引用交互元素的场景。

439

browserwing-executor

browserwing

Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.

27

go-rod-master

rootcastleco

Comprehensive guide for browser automation and web scraping with go-rod (Chrome DevTools Protocol) including stealth anti-bot-detection patterns.

00

Search skills

Search the agent skills registry