$npx skillfedfor your agent

agent-browser

agent-browser enables Claude to control web browsers for automation and testing tasks. Execute end-to-end workflows, interact with web applications, and validate user journeys through code-driven browser control. Perfect for QA automation, web scraping, and business process testing.

agent-browser enables Claude to control web browsers for automation and testing tasks. Execute end-to-end workflows, interact with web applications, and validate user journeys through code-driven browser control. Perfect for QA automation, web scraping, and business process testing.

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

11 4 MITupdated by Casper-Studios

Decision gist · record as of 2026-07-27

agent-browser enables Claude to control web browsers for automation and testing tasks. Execute end-to-end workflows, interact with web applications, and validate user journeys through code-driven browser control. Perfect for QA automation, web scraping, and business process testing.

manual: git clone https://github.com/Casper-Studios/casper-marketplace → cp -r casper-marketplace/plugins/engineering/testing/skills/agent-browser ~/.claude/skills/agent-browser
plugins/engineering/testing/skills/agent-browser/SKILL.md · version e09068bc

Use it when

  • Yes, agent-browser supports filling forms and interacting with web page elements programmatically.
  • agent-browser functions as a modern browser automation solution that enables end-to-end testing workflows and web interactions.

Verify before relying

Read SKILL.md below before installing (6 files). Open directory: indexed for reading, not audited.

Same gist for agents: .md · .json

Install

Casper-Studios/casper-marketplace/agent-browser · repository language: Python

Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.

Frequently asked questions

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

What is agent-browser used for?

agent-browser enables Claude to control web browsers for automation and testing tasks. Execute end-to-end workflows, interact with web applications, and validate user journeys through code-driven browser control. Perfect for QA automation, web scraping, and business process testing.

Can agent-browser automate form filling and web page interactions?

Yes, agent-browser supports filling forms and interacting with web page elements programmatically. You can automate repetitive data entry tasks, click buttons, select dropdown options, and manipulate any interactive element on a web page through code-driven commands.

Is agent-browser a selenium alternative for browser automation?

agent-browser functions as a modern browser automation solution that enables end-to-end testing workflows and web interactions. Like other automation tools, agent-browser allows you to control browser behavior, interact with page elements, and validate application functionality—making it suitable for QA automation and testing scenarios where you need programmatic browser control.

What testing capabilities does agent-browser provide?

agent-browser supports multiple testing scenarios including end-to-end testing workflows, login flow automation testing, and UI testing with screenshot capture. You can capture screenshots and snapshots for visual verification, test authentication flows and login sequences, and validate user journeys. The tool also enables accessibility testing and visual regression testing through its snapshot and element detection features.

How does agent-browser handle element targeting and identification?

agent-browser uses ref-based element targeting for reliable DOM element identification automation. This approach allows you to target specific page elements programmatically without relying on fragile selectors, making your automation scripts more robust and maintainable across page changes.

Can agent-browser scrape and extract content from web pages?

Yes, agent-browser supports web scraping and content extraction from web pages. Combined with its browser automation capabilities, you can navigate to pages, interact with dynamic content, and extract data programmatically—making it suitable for data collection and web page interaction automation tasks.

SKILL.md

Rendered from the published skill. Quoted content, verbatim.

Agent Browser Testing Skill

Browser automation and end-to-end testing using Vercel's agent-browser CLI. Uses ref-based element targeting for reliable, AI-friendly browser interaction.

Quick Decision Tree

What do you need?
│
├─ Take a screenshot of a page?
│  └─ agent-browser open [url] && agent-browser screenshot
│
├─ Fill out a form?
│  └─ open → snapshot -i → fill @ref → click @submit → snapshot
│
├─ Test a login flow?
│  └─ See references/authentication.md
│
├─ Run an E2E test?
│  └─ See references/testing-patterns.md
│
├─ Scrape page content?
│  └─ agent-browser open [url] && agent-browser snapshot -i
│
└─ Debug element targeting?
   └─ agent-browser snapshot -i --format json

Installation

```bash

Install agent-browser globally

npm install -g agent-browser

Install browser dependencies (Chromium)

agent-browser install

Verify

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

File tree — 6 files
plugins/engineering/testing/skills/agent-browser/SKILL.md
plugins/engineering/testing/skills/agent-browser/references/authentication.md
plugins/engineering/testing/skills/agent-browser/references/commands.md
plugins/engineering/testing/skills/agent-browser/references/snapshot-workflow.md
plugins/engineering/testing/skills/agent-browser/references/testing-patterns.md
plugins/engineering/testing/skills/agent-browser/scripts/browser_test.py

Let your AI agent find skills like this

Example. Real query, live index.

You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.

wish › “Automate browser interactions and end-to-end testing workflows”

Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →

Related skills

Agent Browser
by ratacat · ratacat/claude-skills

Agent Browser equips your agent with web navigation and content retrieval capabilities. Access live web pages, extract information, and interact with online resources seamlessly. Perfect for agents that need real-time data gathering and web-based research.

no license declared → metadata onlyupdated Feb 2026
★ 49repo stars
Agent Browser
by davekilleen · davekilleen/Dex

Agent Browser equips Claude Code with web navigation and internet connectivity, letting your AI workflows fetch live data and interact with online services. Expand what your agents can accomplish by bridging the gap between local processing and the broader web.

no license declared → metadata onlyfor claude-codeupdated Jul 2026
★ 448repo stars
Agent Browser
by eyadsibai · eyadsibai/ltk

Agent Browser equips AI systems with real-time web navigation capabilities, allowing them to fetch pages, parse content, and perform interactions just like a human user would. Perfect for agents that need to research information, fill forms, or gather data from dynamic websites without relying on static APIs.

no license declared → metadata onlyupdated Jan 2026
★ 6repo stars
agent-browser
by UnicomAI · UnicomAI/wanwu

agent-browser enables you to orchestrate multi-step browser interactions through deterministic element references, eliminating the fragility of traditional selector-based automation. Deploy structured workflows that reliably navigate, interact with, and extract data from web applications at scale.

Apache-2.0updated Jul 2026
★ 2,569repo stars
agent-browser
by slopus · slopus/happy

agent-browser lets you script repetitive web interactions—form submissions, element clicks, page navigation—directly through Claude Code. Built for end-to-end encrypted access, it brings browser automation to your workflow without leaving SkillFed's environment.

MITfor claude-codeupdated Jul 2026
★ 22,898repo stars
agent-browser
by joneqian · joneqian/claude-skills-suite

agent-browser equips Claude with the ability to interact with web browsers, enabling automated testing, screenshot capture, and page validation. This skill extends Claude's capabilities to handle real-world web automation tasks directly within your workflow.

MITupdated Feb 2026
★ 26repo stars

More skills Agent Browser (unlicensed) · agent-browser (MIT) · agent-browser (MIT)

Tags
headless-automationref-targeting-systemcli-driven-testingsession-persistencesemantic-locatorsvisual-testingworkflow-orchestrationbrowser-state-management