skillfed

agent-browser

agent-browser enables programmatic control of web browsers to streamline repetitive tasks like automated testing, form submission, and information gathering. Integrate this skill to build intelligent agents that interact with web pages, extract structured data, and execute complex browser workflows at scale.

agent-browser is a browser automation tool designed to enable programmatic control of web browsers for streamlining repetitive tasks. The skill supports automated testing, form submission, and information gathering, allowing you to build intelligent agents that interact with web pages, extract structured data, and execute complex browser workflows at scale.

AI-generated summary based on this skill's SKILL.md

4,264 447 MIT updated by m1heng

Install

m1heng/clawdbot-feishu/agent-browser · repository language: TypeScript

CLI (skillfed)coming soon
git clone https://github.com/m1heng/clawdbot-feishu
cp -r clawdbot-feishu/.agents/skills/agent-browser ~/.claude/skills/agent-browser

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

What is agent-browser used for?

agent-browser is a browser automation tool designed to enable programmatic control of web browsers for streamlining repetitive tasks. The skill supports automated testing, form submission, and information gathering, allowing you to build intelligent agents that interact with web pages, extract structured data, and execute complex browser workflows at scale.

Can agent-browser automate browser interactions for web testing, form filling, and data extraction?

Yes, agent-browser is specifically built to automate browser interactions for web testing, form filling, and data extraction. It provides the core functionality needed to programmatically control browsers, fill out web forms automatically, and gather information from web pages as part of your automated workflows.

How does agent-browser handle web page navigation and element interaction?

agent-browser enables you to navigate websites and interact with web pages programmatically. The skill allows you to control browser navigation, click on web elements, fill form fields, and execute complex interactions with web pages, making it suitable for both simple and sophisticated automation scenarios.

What screenshot and content capture capabilities does agent-browser provide?

agent-browser supports screenshot automation and the ability to capture web page content. You can take screenshots of websites during your automated workflows to document page states, verify visual elements, or extract visual information as part of your testing and data extraction processes.

Does agent-browser support browser session management and authentication?

Yes, agent-browser includes functionality to manage browser sessions and handle authentication flows. This capability allows you to maintain persistent browser sessions, manage cookies and credentials, and automate login processes as part of your larger browser automation workflows.

What license does agent-browser use?

agent-browser is released under the MIT license, which is a permissive open-source license that allows you to use, modify, and distribute the skill with minimal restrictions.

SKILL.md

rendered from the published skill — quoted content, verbatim

Browser Automation with agent-browser

Quick start

agent-browser open <url>        # Navigate to page
agent-browser snapshot -i       # Get interactive elements with refs
agent-browser click @e1         # Click element by ref
agent-browser fill @e2 "text"   # Fill input by ref
agent-browser close             # Close browser

Core workflow

  1. Navigate: agent-browser open <url>
  2. Snapshot: agent-browser snapshot -i (returns elements with refs like @e1, @e2)
  3. Interact using refs from the snapshot
  4. Re-snapshot after navigation or significant DOM changes

Commands

Navigation

```bash agent-browser open <url> # Navigate to URL (aliases: goto, navigate) # Supports: https://, http://, file://, about:, data:// # Auto-prepends https:// if no protocol

(truncated - see the full file via the links below)

Read as markdown · JSON record · Browse the source repository

File tree — 9 files
.agents/skills/agent-browser/SKILL.md
.agents/skills/agent-browser/references/authentication.md
.agents/skills/agent-browser/references/proxy-support.md
.agents/skills/agent-browser/references/session-management.md
.agents/skills/agent-browser/references/snapshot-refs.md
.agents/skills/agent-browser/references/video-recording.md
.agents/skills/agent-browser/templates/authenticated-session.sh
.agents/skills/agent-browser/templates/capture-workflow.sh
.agents/skills/agent-browser/templates/form-automation.sh

Related skills

Tags

headless-testing web-scraping form-automation ui-testing screenshot-capture element-interaction session-persistence network-interception device-emulation