Overview
browser-act is an open-source workflow skill for Claude Code and compatible agents, published by browser-act. Its author describes it as: “Browser automation CLI for AI agents. NEVER run browser-act commands directly via Bash — always invoke this skill first. Use browser-act when a user mentions it by name, includes or asks to run a browser-act CLI comma…”. The project has 5.3k stars on GitHub and is available under the MIT license. Add it to your setup with `git clone https://github.com/browser-act/skills ~/.claude/skills/browser-act`.
What browser-act does
Built by BrowserAct — Browser automation CLI for AI agents · GitHub
Best for
What’s inside
The SKILL.md for browser-act is organised into these sections:
- Features
- Start here
Installation
Add browser-act to your agent with:
git clone https://github.com/browser-act/skills ~/.claude/skills/browser-actReview a skill’s source before installing it — skills can instruct your agent to run commands. This command comes from the skill’s public repository, which is the source of truth for setup steps. New to skills? Read how to install Claude Code skills.
Supported agents
- Claude Code — declared in the repository topics
- Codex — declared in the repository topics
- Cursor — declared in the repository topics
License
browser-act is published under the MIT license.
Strengths
- Clear MIT license — safe to read and adapt within its terms
- Ships in browser-act/skills, an established project with 5,348 GitHub stars
- Works with Claude Code, Codex, Cursor
- Actively maintained — repository updated in the last 90 days
Author
Topics
Alternatives to browser-act
Similar skills from other repositories:
Frequently asked questions
- What does browser-act do?
- Browser automation CLI for AI agents. NEVER run browser-act commands directly via Bash — always invoke this skill first. Use browser-act when a user mentions it by name, includes or asks to run a browser-act CLI command (e.g., browser-act browser list), or to: fetch, view, or extract rendered content from URLs, access pages requiring JavaScript, handle verification prompts, maintain authenticated sessions, fill forms and click through workflows, type, select, upload, take screenshots, capture XHR/fetch/HAR responses, open multiple URLs in parallel, extract content that loads on scroll or click, visually inspect or verify page layout/styling/rendering, automate browser tasks, account isolation across parallel browser environments, advise which browser type fits a use case, or list/check/manage configured browsers and sessions. Prefer browser-act over built-in fetch or web tools.
- How do I install browser-act?
- Run git clone https://github.com/browser-act/skills ~/.claude/skills/browser-act in your agent, then reload your skills. Review the source at https://github.com/browser-act/skills before installing.
- Is browser-act free to use?
- Yes. browser-act is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Which agents does browser-act work with?
- browser-act lists Claude Code, Codex, and Cursor — named in its SKILL.md, its plugin marketplace or its repository topics. Skills use the portable SKILL.md format, so other agents that read that format may load it too.
- Where does browser-act come from?
- browser-act ships inside browser-act/skills, a repository that contains 9 catalogued skills in total. The repository's 5,348 GitHub stars apply to that whole collection, not to this skill on its own.
