← Back to Skills Marketplace
Browser Act
by
browser-act skill
· GitHub ↗
· v1.0.0
· MIT-0
10236
Downloads
1
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install browser-act-skills
Description
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...
Usage Guidance
Install only if you want an agent to use the browser-act CLI as a primary browser automation path. Review when it will be invoked, keep confirmation prompts enabled for login, form submission, file upload, browser creation, and deletion, and prefer simpler read-only web tools for ordinary page fetching unless browser rendering or session automation is actually needed.
Capability Assessment
Purpose & Capability
The stated purpose is browser automation, and the disclosed capabilities include navigation, extraction, screenshots, form automation, authenticated sessions, network capture, and verification assistance.
Instruction Scope
The description tells agents to prefer browser-act over built-in fetch or web tools and to use it for broad fetch/view/extract tasks, which is over-scoped for a tool that can interact with authenticated browser sessions and perform state-changing workflows.
Install Mechanism
The artifact contains only SKILL.md and instructs installation of an external PyPI CLI via uv; no executable scripts are bundled in the skill artifact.
Credentials
Network access, local browser profile storage, logs, and optional CDP access are coherent with browser automation, but they are high-impact capabilities users should understand.
Persistence & Privilege
The skill discloses local browser profiles and rotated session logs, and claims confirmation gates for browser creation and sensitive operations; no hidden persistence or privilege escalation appears in the artifact.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install browser-act-skills - After installation, invoke the skill by name or use
/browser-act-skills - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of the browser-act skill for browser automation CLI tasks.
- Enables AI agents to automate browser actions including navigation, data extraction, screenshots, form automation, and more.
- Supports advanced workflows: session and account isolation, verification challenge assistance, and human-in-the-loop collaboration.
- Safety and privacy features: explicit user confirmation required for sensitive operations; all session data handled locally.
- Universal compatibility with major AI agent platforms; requires Python 3.12+ and the uv package manager.
- Strong focus on following operational directives—requires users to start with get-skills core for correct and safe use.
Metadata
Frequently Asked Questions
What is Browser Act?
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 is an AI Agent Skill for Claude Code / OpenClaw, with 10236 downloads so far.
How do I install Browser Act?
Run "/install browser-act-skills" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Browser Act free?
Yes, Browser Act is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Browser Act support?
Browser Act is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Browser Act?
It is built and maintained by browser-act skill (@browseract-cli); the current version is v1.0.0.
More Skills