skills
Browser automation CLI built for AI agents. Break through anti-bot walls, hand off to humans across platforms when stuck. Parallel multi-task execution, independent multi-session operation, isolated multi-account browsing.
BrowserAct Skills is a browser automation agent skill that equips AI agents with real-browser control capabilities through command-line interfaces. It enables agents to bypass anti-bot protections, handle CAPTCHAs automatically, hand off sessions to humans when stuck, and run parallel browser tasks with isolated fingerprints and proxies. The skill supports multiple browser modes including local Chrome profile reuse, stealth privacy mode for scraping, and fixed-identity stealth for multi-account management. Agents discover available commands through a unified get-skills interface and execute indexed, token-efficient browser interactions without DOM parsing.
Key Features
Use Cases
- 01Extracting data from bot-protected websites that block standard scraping tools
- 02Automating multi-account workflows with isolated browser fingerprints and stable IP addresses per account
- 03Running parallel web scraping tasks without session cross-contamination or cookie conflicts
- 04Reusing local Chrome login sessions for agent-driven authenticated workflows
- 05Generating live URLs for human intervention when agents encounter complex workflows or verification steps
- 06Building repeatable data extraction pipelines for sites like LinkedIn, Amazon, or Google Maps using auto-generated skills
Related Skills
View moresuperpowers
An agentic skills framework & software development methodology that works.
skills
Skills for Real Engineers. Straight from my .agents directory.
skills
Public repository for Agent Skills
ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
skills — FAQ
What is BrowserAct Skills and what does it do?+
BrowserAct Skills is a command-line browser automation agent skill that gives AI agents real-browser control with anti-bot bypass, CAPTCHA solving, and human handoff capabilities. It provides indexed, LLM-friendly browser interaction commands through a shell interface.
How do I install BrowserAct Skills in my AI agent?+
Instruct your AI agent to install browser-act from the GitHub repository at https://github.com/browser-act/skills/tree/main/browser-act. After installation, verify it works by running browser-act get-skills to discover available commands and environment state.
Which AI agents and clients are compatible with BrowserAct Skills?+
BrowserAct Skills works with any agent capable of executing shell commands and loading skills, including Claude Code, Cursor, VS Code, OpenCode, OpenClaw, Codex, and Gemini CLI on Windows, macOS, and Linux.
Is BrowserAct Skills free or does it require API keys?+
Most features are free with no signup required for basic browser automation. Login-only free features include up to 5 stealth browsers, stealth-extract, solve-captcha, and remote-assist. Paid features only include managed proxies and stealth browsers beyond the first 5.
What are the prerequisites for using BrowserAct Skills?+
You need an AI agent or development environment capable of executing shell commands on Windows, macOS, or Linux. For stealth features and CAPTCHA solving, you'll need to create a free account; managed proxies and additional stealth browsers require paid credits.
Can BrowserAct Skills run multiple browser sessions in parallel?+
Yes, BrowserAct supports zero-interference concurrency with cross-browser parallel execution using isolated fingerprints and proxies, same-browser multi-session support with shared login state, and privacy mode with fresh fingerprints per session.
How do I install skills?+
Open the source repository on GitHub and follow its README. skills is a skill — MCP Agents Market links you directly to the official repo.
Is skills free?+
skills is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.