skills.rest
bond23869
bond23869COMMUNITY
Explore all skills by this author →
GitHub

agent-browser

Automates browser interactions for web testing, form filling, screenshots, and data extraction.

Updated Jul 14, 2026
Search Tags:#data extraction#screenshots#cli#browser automation#web testing#web scraping#form filling
One-click install
npx skills add https://github.com/bond23869/skills --skill agent-browser-bond23869
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/bond23869/skills/tree/main/agent-browser
Command: npx skills add https://github.com/bond23869/skills --skill agent-browser-bond23869

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Manually navigating websites, filling forms, and extracting page data is repetitive and error-prone, especially when testing web applications or scraping information at scale. This Skill provides a command-line browser automation interface that lets an AI agent navigate pages, interact with elements, capture screenshots, and extract data programmatically. ## Core Features & Use Cases - Page Interaction via Element Refs: Snapshot pages to get interactive elements with refs, then click, fill, hover, drag, and select using those refs or semantic locators like role, text, and label. - Capture & Recording: Take screenshots, export pages as PDF, record session videos, and capture traces for debugging web application behavior. - State & Network Control: Manage cookies, localStorage, authentication state, tabs, frames, and intercept or mock network requests for testing scenarios. - Use Case: A QA engineer needs to verify a login flow. The agent opens the login page, snapshots the form, fills credentials, submits, waits for the dashboard URL, and saves the authenticated session state for reuse in later test runs. ## Quick Start Ask the agent to open a website, snapshot the interactive elements, fill in the login form, and take a screenshot of the result.

Frequently Asked Questions about agent-browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate form filling on a website?▼

Open the page with agent-browser open, run snapshot -i to list interactive elements with refs, then use fill with each ref to enter values and click the submit button ref. Wait for navigation with wait --url or --load networkidle before verifying the result.

How to take a screenshot of a web page from the command line?▼

Run agent-browser open with the target URL, then use agent-browser screenshot path.png to save the capture. Add --full for a full-page screenshot, or use pdf output.pdf to save the page as a PDF document instead.

Can I reuse login sessions across browser automation runs?▼

Yes, authenticate once, then run agent-browser state save auth.json to persist cookies and storage. In later sessions, load the file with agent-browser state load auth.json before navigating to authenticated pages.

Does agent-browser support running multiple browsers in parallel?▼

Yes, use the --session flag with a session name to run isolated browser instances concurrently, such as agent-browser --session test1 open site-a.com. List active sessions with agent-browser session list.

Why is my browser automation click not working on an element?▼

The page DOM likely changed after navigation, invalidating old refs. Re-run snapshot -i to get fresh refs, or use semantic locators like find role button click --name "Submit" which resolve elements at execution time.

How do I debug a failing browser automation script?▼

Run with --headed to watch the browser, check console and errors commands for page issues, and use highlight to visually confirm element targets. You can also record a video or capture a trace with trace start and trace stop for detailed replay.

Related Skills

Explore More Software Engineering Skills→
BrunoAMSilvaBrunoAMSilva

playwright-explore-website

Explore websites via Playwright MCP to record locators and generate test cases.

Community
Intermediate
Likas07Likas07

analytics-reporter

Analyze raw data into business insights with statistical analysis and dashboards.

Community
Advanced
bennybennisonbennybennison

mock-api-contracts

Define UI-facing API contracts and validate screen flows against mocked FastAPI endpoints.

Community
Intermediate
okwindsokwinds
50

headless-web-viewer

Render JavaScript-heavy webpages and extract visible text with Playwright.

Community
Intermediate