AIBestSkill
Home/Skills/dev-browser
Browser automation · Claude Code Skill

dev-browser adoption decision

Navigate pages, inspect web state, fill forms, or fetch browser-visible evidence for an agent workflow. 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 browse...

GitHub repo Adoption path Source evidence Back to skills last scan today
Job to solvebrowser-backed agent work

Navigate pages, inspect web state, fill forms, or fetch browser-visible evidence for an agent workflow.

Who should use itBuilders who need an agent to work against real browser pages instead of static files only.

Use this as a fit check before reading install commands.

Works withClaude Code

Platform fit comes after the use case, not before it.

Adoption pathSource-verified setup

Setup evidence is available from README.md · CLI Installation. Review the source before installing.

Trust signalREADME + SKILL.md

1 SKILL.md + README + install evidence, 6,027 stars, and 19d ago repo freshness at last scan.

Overview

What job does it solve?Browser automation

Navigate pages, inspect web state, fill forms, or fetch browser-visible evidence for an agent workflow.

Who should use it?Builders who need an agent to work against real browser pages instead of static files only.

browser-backed agent work for Claude Code users.

Works withClaude Code

Check platform compatibility after confirming the use case fits your workflow.

How can I adopt it?Source-verified setup

Setup evidence is available from README.md · CLI Installation. Review the source before installing.

Can I trust it?README + SKILL.md

1 SKILL.md + README + install evidence, 6,027 stars, and 19d ago repo freshness at last scan.

What to compare?5 related skills

Use the comparison list below to avoid adopting the first matching repo blindly.

Quick read

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.

A Claude Skill to give your agent the ability to use a web browser

Why we list it
  • Public because this is a source-backed installable skill-like repo with enough current evidence to qualify for the shortlist.
  • Current GitHub metadata is available for SawyerHood/dev-browser.
  • 1 SKILL.md file(s) were found in the recursive tree scan.
  • Trusted install evidence was extracted from 1 source file(s).

Adoption path for dev-browser

Primary adoption path

Setup evidence extracted from README.md · CLI Installation. Review source before installing.

  • npm install -g dev-browser

Source evidence

Source excerpts used for this adoption decision. Low-confidence cases link back to GitHub instead of forcing a misleading quote.

README excerpt

README.md

Brought to you by Do Browser.

A browser automation tool that lets AI agents and developers control browsers with sandboxed JavaScript scripts.

Key features:

  • Sandboxed execution - Scripts run in a QuickJS WASM sandbox with no host access
  • Persistent pages - Navigate once, interact across multiple scripts
  • Auto-connect - Connect to your running Chrome or launch a fresh Chromium
  • Full Playwright API - goto, click, fill, locators, evaluate, screenshots, and more

Demo

https://github.com/user-attachments/assets/c6cf7fb9-b1dc-46ed-93b9-6e7240990c53

CLI Installation

npm install -g dev-browser
dev-browser install    # installs Playwright + Chromium
Quick start

### Windows notes

PowerShell install:

npm install -g dev-browser

dev-browser install


To attach to a running Chrome instance on Windows:

chrome.exe --remote-debugging-port=9222

dev-browser --connect


Windows npm installs download the native `dev-browser-windows-x64.exe` release asset during `postinstall`, and the generated npm shims invoke that executable directly.
Show scanned SKILL.md paths (1)
  • skills/dev-browser/SKILL.md