AI for Developers
Agent skill (SKILL.md) Open source MIT 6.3k

Browser Act 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, isolate...

Install

For this project
$ npx skills add browser-act/skills -a claude-code
For every project
$ npx skills add browser-act/skills -a claude-code -g

Or copy the skill folder into .claude/skills/ (project) or ~/.claude/skills/ (all projects).

For this project
$ npx skills add browser-act/skills -a codex
For every project
$ npx skills add browser-act/skills -a codex -g

Or copy the skill folder into .agents/skills/ (project) or ~/.agents/skills/ (all projects).

For this project
$ npx skills add browser-act/skills -a cursor
For every project
$ npx skills add browser-act/skills -a cursor -g

Or copy the skill folder into .agents/skills/ (project) or ~/.cursor/skills/ (all projects).

For this project
$ npx skills add browser-act/skills -a openclaw
For every project
$ npx skills add browser-act/skills -a openclaw -g

Or copy the skill folder into skills/ (project) or ~/.openclaw/skills/ (all projects).

See the repository README for installation instructions.

When to use

Use it when an agent has to operate a real browser across several sessions or accounts, such as extracting data from pages that need a login. Make sure you have the right to access what you automate.

BrowserAct is a browser automation CLI built for AI agents, covering real-browser automation, web data extraction and account-based workflows. It lets agents run parallel tasks without cross-contamination and keep multiple accounts in independent browsers, and it can hand a task to a human when the agent gets stuck. The README also lists stealth fingerprints, TLS rotation, residential proxies and CAPTCHA solving.

Two modes exist: a cloud-managed mode, where it builds and runs a reusable scraping bot for you, and local control of a browser from your own agent. The cloud service is a commercial product. Many sites forbid automated access or bypassing their protections in their terms, so check them before you scrape.

Related skills

All skills