skills.rest
gabrielnsmnto
gabrielnsmntoCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

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

3|Updated Feb 7, 2026
Search Tags:#screenshots#cli#browser automation#web testing#web scraping#form filling#playwright
One-click install
npx skills add https://github.com/gabrielnsmnto/kord-aios --skill agent-browser-gabrielnsmnto
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/gabrielnsmnto/kord-aios/tree/main/src/features/builtin-skills/agent-browser
Command: npx skills add https://github.com/gabrielnsmnto/kord-aios --skill agent-browser-gabrielnsmnto

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires agent-browser, playwright.

What problem does it solve? Manually testing web pages, filling forms, and scraping page content is repetitive and error-prone. This Skill gives an AI agent full control of a real browser through a CLI, so navigation, clicking, typing, screenshots, and data extraction can be scripted and automated. ## Core Features & Use Cases - Element Interaction via Refs: Snapshot a page to get interactive elements with refs like @e1, then click, fill, hover, drag, or upload files against those refs. - Page Capture & Inspection: Take screenshots, export PDFs, record videos, read console logs and page errors, and extract text, HTML, attributes, and element state. - Sessions, Profiles & Network Control: Run isolated parallel sessions, persist login state with profiles, intercept or mock network requests, and manage cookies and storage. - Use Case: Automate an end-to-end login flow test: open the login page, snapshot the form, fill credentials, submit, wait for the dashboard URL, then save the authenticated state for reuse in later runs. ## Quick Start Ask the agent to open a website with agent-browser, 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 in a browser from the command line?▼

Open the page with agent-browser open, run agent-browser snapshot -i to list interactive elements with refs, then use agent-browser fill @ref "value" for each field and agent-browser click @ref to submit. Re-snapshot after navigation to verify the result.

How do I take a screenshot of a web page programmatically?▼

Run agent-browser open <url> followed by agent-browser screenshot path.png to save a screenshot to a file. Add the --full flag for a full-page capture, or use agent-browser pdf output.pdf to save the page as a PDF.

Can agent-browser keep me logged in between sessions?▼

Yes. Use agent-browser state save auth.json after logging in and agent-browser state load auth.json later, or launch with --profile <path> to persist cookies, localStorage, IndexedDB, and cache across browser restarts.

Why does agent-browser install fail on darwin-arm64?▼

The install command may report "No binary found" on some platforms. Work around it by creating a temp project with bun add playwright and running bun playwright install chromium, which downloads Chrome for Testing to the Playwright cache.

Can I run multiple isolated browser sessions in parallel?▼

Yes. Pass --session <name> to each command, for example agent-browser --session test1 open site-a.com and agent-browser --session test2 open site-b.com. Use agent-browser session list to view active sessions.

How do I mock or block network requests during browser automation?▼

Use agent-browser network route <url> to intercept requests, add --abort to block them or --body '{}' to return a mocked response. Run agent-browser network requests to inspect tracked traffic and network unroute to remove rules.

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
nuurpronuurpro
1

canary

Detect post-deploy console errors, performance regressions, and page failures via the browse daemon.

Community
Intermediate
lucasfdigitallucasfdigital

webapp-testing

Execute Playwright web application tests with screenshots and accessibility checks.

Community
Advanced
aemsitesaemsites
3

Testing Blocks

Automate testing of AEM Edge Delivery code changes with unit, browser, and lint checks.

Official
Intermediate