skills.rest
spike-land-ai
spike-land-aiOFFICIAL
Explore all skills by this author →
GitHub

agent-browser

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

Updated Aug 27, 2026
Search Tags:#automation#screenshots#web-testing#browser#refs#data-extraction#agent-browser
One-click install
npx skills add https://github.com/spike-land-ai/spike.land --skill agent-browser-spike-land-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/spike-land-ai/spike.land/tree/main/.github/skills/agent-browser
Command: npx skills add https://github.com/spike-land-ai/spike.land --skill agent-browser-spike-land-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automates browser interactions for web testing, form filling, screenshots, and data extraction, reducing repetitive manual browsing tasks.

Core Features & Use Cases

  • Snapshot-driven refs identify and reuse page elements with compact identifiers.
  • Ref-based interactions perform clicks, fills, and navigations using short, stable refs instead of brittle selectors.
  • End-to-end automation supports QA pipelines, demos, and data-extraction workflows by capturing screenshots and exporting content.

Quick Start

Open a URL with agent-browser open, then snapshot to discover refs and interact using those refs.

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 without using brittle CSS selectors?▼

Automate browser interactions using snapshot-driven refs that identify page elements with compact identifiers. This approach replaces brittle selectors by capturing short, stable refs to perform clicks, fills, and navigations for web testing workflows.

What's the best way to extract data from web pages and capture screenshots during automated navigation?▼

Data extraction and screenshot capturing are handled through end-to-end browser automation. You open a URL, take a snapshot to discover refs, and interact with page elements to export content required for data-gathering workflows.

How do I fill out web forms automatically using ref-driven browser controls?▼

Form filling is performed using ref-based interactions that apply short, stable refs to target input fields. Instead of relying on complex selectors, the automation uses these compact identifiers to execute fills and submissions efficiently.

Can I use this browser automation tool for QA pipelines and demos?▼

Browser automation is fully applicable for QA pipelines and demos. It supports navigating pages, taking screenshots, and exporting content, which are required operations for continuous testing and demonstration workflows.

How does the snapshot mechanism work for identifying reusable page elements?▼

The snapshot mechanism works by scanning a page to generate compact identifiers for its elements. These snapshot-driven refs are then reused to perform stable interactions, avoiding the fragility of traditional DOM selectors.

Are there limitations on what actions the browser agent can perform during automation?▼

Actions are constrained by allowed-tools declared in the root SKILL.md frontmatter. This configuration limits what the agent can execute, ensuring operations remain within defined boundaries for web testing and data extraction tasks.

Related Skills

Explore More Software Engineering Skills→
jfmyers9jfmyers9
8

writing-skills

Create Skill Units with standardized SKILL.md frontmatter and Markdown instructions.

Community
Intermediate
jamesrochabrunjamesrochabrun
194

qa-test-planner

Generate QA test plans, manual cases, regression suites, and bug reports.

Community
Advanced
zerAdazerAda

bmad-qa-generate-e2e-tests

Generate end-to-end API and UI tests for identified application features.

Community
Advanced
GitLaw-coGitLaw-co

agent-browser

Automate browser navigation, form filling, clicks, and data capture for AI agents.

Official
Intermediate