skills.rest
aniwei
aniweiCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

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

Updated Feb 3, 2026
Search Tags:#QA#web-testing#screenshot#data-extraction#browser-automation#form-filling#agent-browser
One-click install
npx skills add https://github.com/aniwei/vitamin-code --skill agent-browser-aniwei
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/aniwei/vitamin-code/tree/main/refs/oh-my-opencode/src/features/builtin-skills/agent-browser
Command: npx skills add https://github.com/aniwei/vitamin-code --skill agent-browser-aniwei

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates browser interactions for web testing, form filling, screenshots, and data extraction, helping users navigate websites, interact with web pages, fill forms, capture screenshots, test web apps, and extract data from pages.

Core Features & Use Cases

  • Automates end-to-end browser interactions (open pages, snapshot, click, fill, etc.)
  • Supports data extraction from pages and testing workflows
  • Use Case: QA testers automating repetitive site interactions, form filling, and screenshot capture across multiple pages.

Quick Start

Use this Skill to automate a simple form:

agent-browser open https://example.com/form agent-browser snapshot -i agent-browser fill @e1 "[email protected]" agent-browser fill @e2 "password" agent-browser click @e3 agent-browser wait --load networkidle agent-browser snapshot -i

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 for web testing and form filling?▼

Browser automation for web testing and form filling is achieved by using CLI-driven commands to open pages, snapshot elements, fill inputs, and click buttons. This streamlines repetitive site interactions and data extraction across multi-page sites.

Can I capture screenshots during automated browser testing workflows?▼

Yes, capturing screenshots during automated browser testing is supported natively. You can issue commands to open a URL, navigate through pages, and capture screenshots to verify visual states during QA automation or user onboarding flows.

What is the best way to extract data from web pages using browser automation?▼

Data extraction from web pages using browser automation is handled by taking snapshots of page elements. You can interact with multi-page sites sequentially and output the extracted data in optional JSON format for machine processing.

Does this browser automation approach support machine-readable output for data collection?▼

Yes, browser automation for data collection supports optional JSON output. This allows you to extract structured data from web pages and pass it directly to downstream machine processing workflows or scripts.

How do I fill out a web form automatically using CLI commands?▼

To fill out a web form automatically, you open the target URL, take a snapshot to get element refs, and then use fill commands targeting those refs like @e1 with your desired input values before clicking the submit button.

Can I manage browser sessions and profiles for automated web testing?▼

Yes, managing browser sessions and profiles is supported for automated web testing. This allows you to maintain state across multiple pages and interactions during QA automation and data collection tasks.

Related Skills

Explore More Software Engineering Skills→
npc-livenpc-live
168

agent-browser

Automate browser interactions via Chrome/CDP using the agent-browser CLI.

Official
Intermediate
pradyumnasagarpradyumnasagar
6

agent-handoff

Automate inter-skill data transfer and provenance capture via JSON Material Passports.

Community
Advanced
gandazgulgandazgul
14

playwright-cli

Automate browser interactions and generate Playwright test scripts.

Community
Advanced
nanocoainanocoai
30.5k

agent-browser

Automate web browsing to extract data, fill forms, and capture screenshots.

Official
Intermediate