skills.rest
RADHA0-max
RADHA0-maxCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

Automates browser navigation, interaction, screenshots, and data extraction via command-line commands.

2|Updated Jan 14, 2026
Search Tags:#data extraction#screenshots#browser automation#web testing#web scraping#form filling#playwright
One-click install
npx skills add https://github.com/RADHA0-max/selfhealbackend --skill agent-browser-radha0-max
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/RADHA0-max/selfhealbackend/tree/main/nanoclaw/container/skills/agent-browser
Command: npx skills add https://github.com/RADHA0-max/selfhealbackend --skill agent-browser-radha0-max

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Manually browsing websites to research topics, fill forms, or extract data is slow and repetitive. This Skill lets an AI agent drive a real browser through simple commands, handling navigation, clicks, form filling, waiting, and data capture without human involvement. ## Core Features & Use Cases - Page Interaction: Navigate to URLs, click elements, fill inputs, select dropdowns, upload files, and press keys using element refs from accessibility snapshots. - Data Extraction & Capture: Read element text, attributes, and page metadata, take screenshots, and save pages as PDF. - Session Persistence: Save and reload authentication state, cookies, and localStorage to stay logged in across sessions. - Use Case: Research a topic by opening search results, reading articles, and capturing screenshots, or automate a login flow once and reuse the saved session for repeated dashboard checks. ## Quick Start Ask the agent to open a website with agent-browser, take an interactive snapshot, and click or fill the elements you specify.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate browser interactions from the command line?▼

Use agent-browser to open a URL, run snapshot -i to list interactive elements with refs like @e1, then click, fill, or select those refs. Re-snapshot after navigation or major DOM changes to get fresh refs.

How to fill out and submit a web form automatically?▼

Open the form page, take an interactive snapshot to find input refs, then use fill for each field and click the submit button. Finish with wait --load networkidle and a new snapshot to verify the result.

Can I reuse a logged-in browser session across runs?▼

Yes. After logging in once, run agent-browser state save auth.json to persist cookies and storage. Later, load it with state load auth.json and navigate directly to authenticated pages.

Why does my browser automation script hang on a wait loop?▼

Unbounded polling loops never exit if the condition never becomes true, wedging the agent session. Always wrap custom waits in a wall-clock timeout and a max-attempts counter, and treat timeouts as failures to inspect.

How do I extract data or take screenshots of a web page?▼

Use get text, get attr, or get html on element refs to extract content, and get count with a CSS selector to count matches. Use screenshot for images, --full for full-page captures, or pdf to save the page as PDF.

Related Skills

Explore More Software Engineering Skills→
hideki5123hideki5123
2

playwright-codegen

Record browser interactions with Playwright codegen and generate structured test suites.

Community
Advanced
Runchuan-BURunchuan-BU
401

agent-browser

Automate web browsing to navigate pages, click elements, fill forms, and extract data.

Community
Advanced
genesis-agentsgenesis-agents
2

Verifier

Cross-check claims against cited sources and return verdicts with evidence.

Community
Advanced
ubay1ubay1
1

react-server-components

Render React components on the server to reduce client JavaScript bundle size.

Community
Intermediate