browser-act

SkillWeb & browsing

Your AI can take control of a web browser and work online for you: visiting sites, filling in forms, and completing multi-step tasks. It can run several browsing sessions at the same time, each with its own separate accounts, and it can hand a task over to a human when it gets stuck.

Available today. Use it from your connected AI after setup.

After adding it, give your AI a website and a task, such as filling out a form. Once that works, try running several sessions at the same time.

Then ask your AI: use the browser-act skill

What your AI can do with it

  • Browse websites and fill in forms
  • Run multiple browsing tasks in parallel
  • Keep each session independent from the others
  • Use isolated accounts so logins stay separate
  • Get past anti-bot checks on protected sites
  • Hand a task off to a human when it gets stuck

What this skill tells your AI

The instructions your AI receives, as published by browser-act/skills in browser-act/SKILL.md and read by ahel’s review.

Built by BrowserAct — Browser automation CLI for AI agents · GitHub

Runs a full browser engine: navigation & interaction, data extraction & network capture, screenshots, form automation, multi-browser parallel operation, user-configured proxy support, and human-agent collaboration.

Features

  • Lightweight extraction — fast JS-rendered content fetch without opening a browser session, advanced WebFetch/curl replacement
  • Session management — multi-browser isolation, multi-account parallel operation
  • Verification assistance — when automation encounters interactive challenges, assists completion with user authorization
  • Complex interaction — DOM content extraction, screenshots, form filling, file upload
  • Human-agent collaboration — headed mode + remote assist for manual steps
  • Safety controls — Confirmation Gate protocol requires explicit user approval before browser creation, deletion, and sensitive operations
  • Universal compatibility — works with Cursor, Claude Code, Codex, Windsurf, etc.

Install: uv tool install browser-act-cli --python 3.12

Start here

This file is a discovery stub, not the usage guide. After loading this skill, immediately run the following to get the actual workflow content:

browser-act get-skills core --skill-version 2.0.2

The CLI serves skill content that always matches the installed version, so instructions never go stale. Do NOT truncate the output — none of which are available through --help.

Signals

GitHub stars
6k
Forks
293
Last commit
Aug 2026
Installs
108k installs
Advanced
Catalog kind
skill
Gateway key
browser-act
Source
github.com/browser-act/skills