skills.rest
rithm84
rithm84COMMUNITY
Explore all skills by this author →
GitHub

agent-browser

Automates browser navigation, interaction, and verification for web pages and dev servers.

Updated Aug 19, 2026
Search Tags:#dev server#cli#browser automation#web testing#form filling#screenshot#e2e verification
One-click install
npx skills add https://github.com/rithm84/Manor --skill agent-browser-rithm84
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/rithm84/Manor/tree/main/.agents/skills/browser-related/agent-browser
Command: npx skills add https://github.com/rithm84/Manor --skill agent-browser-rithm84

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Manually verifying that a dev server renders correctly or testing web app flows by hand is slow and error-prone. This Skill gives an AI agent a CLI to open pages, interact with elements, capture screenshots, and extract data so web verification and browser tasks run automatically. ## Core Features & Use Cases - Page Interaction via Refs: Snapshot interactive elements as refs like @e1, then click, fill, select, and press keys against them. - Dev Server Verification: Open localhost URLs after starting a dev server, wait for network idle, and capture screenshots to confirm the app renders. - State and Session Management: Save and reload authentication state, run multiple named sessions, and chain commands through a persistent background browser daemon. - Use Case: After running npm run dev, ask the agent to open http://localhost:3000, fill in the login form, submit it, and screenshot the dashboard to confirm the flow works end to end. ## Quick Start Ask the agent to open your local dev server URL with agent-browser, take an annotated screenshot, and verify the page loads correctly.

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 testing of a local dev server?▼

Start your dev server, then run agent-browser open with the localhost URL, wait for network idle, and take a screenshot. Use snapshot -i to list interactive elements and click or fill them by ref to verify flows.

How do I fill and submit a web form from the command line?▼

Open the page with agent-browser, run snapshot -i to get element refs, then use fill for each input and click on the submit button ref. Finish with wait --load networkidle to confirm the submission completed.

Can I reuse login sessions across browser automation runs?▼

Yes. After logging in once, run agent-browser state save auth.json to persist cookies and storage. In later sessions, load it with agent-browser state load auth.json before navigating to authenticated pages.

Why do my element refs stop working after clicking a button?▼

Refs like @e1 are invalidated whenever the page navigates or the DOM changes. Always run snapshot -i again after clicks, form submissions, or dynamic content loads to get fresh refs before interacting further.

Does agent-browser support parallel sessions on multiple sites?▼

Yes. Use the --session flag with a name, such as agent-browser --session site1 open URL, to run isolated browser contexts concurrently. List active sessions with agent-browser session list and close them when done.

Related Skills

Explore More Software Engineering Skills→
openaiopenai
5.3k

agent-browser-verify

Verifies dev server pages load correctly using automated browser checks with agent-browser.

Official
Intermediate
i-standard1i-standard1
6

gen-test-report

Consolidate unit, integration, and end-to-end test results into a standardized report.

Official
Intermediate
Skyvern-AISkyvern-AI
22.7k

testing

Tests Skyvern deployments by validating API, frontend rendering, browser sessions, and workflows.

Official
Intermediate
UnicornUnicorn

e2e-test-agent

Generate end-to-end test suites for web and full-stack applications.

Official
Advanced