Browser Automation
Use when the user asks to automate browser tasks, scrape websites, fill forms, capture screenshots, extract structured data from web pages, or build web automation workflows.
Before & after
Same prompt, same agent — the only difference is the skill.
Web scraping can be useful for collecting data from websites. You'll need to think about how to extract the information you want. Different sites have different structures so you might need to adjust your approach for each one. You could use a browser automation tool to navigate and click through pages. Parsing HTML can help you extract specific elements. Consider the performance and speed of your scraper. You might want to respect rate limits to avoid overloading the servers. Error handling is important too.
BROWSER AUTOMATION WORKFLOW
SETUP:
Target: competitor-saas.example.com/pricing
Extract: Plan names, prices, feature count, feature list text, CTA button text
Output format: JSON per competitor (rows with plan_name, price_usd, features_json, cta_text)
STEP 1: Navigate and scan
Load pricing page → wait for pricing-table selector to render (timeout: 10s)
Capture current URL (verify no redirect)
STEP 2: Click through tabs (if pricing is tabbed)
If 'Monthly/Annual toggle' exists → click Annual → wait 1s for rerender
Extract both versions (frequency data)
STEP 3: Parse plan cards
Select all .pricing-plan elements
For each plan card:
- Extract text: plan-name, plan-price, feature-list (bullets or checkmarks)
- Extract CTA button: button text, destination URL
STEP 4: Screenshot differentiators
Capture full pricing section as PNG (size comparison, visual hierarchy)
STEP 5: Save and alert
Write JSON: competitors/pricing_2026-07-31.json
Log: '3 plans extracted, feature parity analysis ready'
OUTPUT EXAMPLE:
{
"competitor": "AppName",
"pricing_page_url": "...",
"plans": [
{"name": "Starter", "price_monthly": 29, "features": ["API access", "10k calls/mo"]},
{"name": "Pro", "price_monthly": 99, "features": ["Unlimited API", "Priority support"]}
],
"scraped_at": "2026-07-31T14:32:00Z"
}
NOTE: Respect robots.txt; 2sec delay between page loadsAbout this skill
name: browser-automation description: Use when Use when the user asks to automate browser tasks, scrape websites, fill forms, capture screenshots, extract structured data from web pages, or build web automation workflows.
Browser Automation
Use when the user asks to automate browser tasks, scrape websites, fill forms, capture screenshots, extract structured data from web pages, or build web automation workflows. NOT for testing — use playwright-pro for that.
What you get
- Public GitHub repo (alirezarezvani/claude-skills)
- the browser-automation skill folder with SKILL.md. Part of a 337-skill / 30-agent / 70-command install.
Customize your output
- Fork the repo and adapt the skill's instructions and references to your workflow.
Example output
Activates automatically when your request matches Browser Automation; chains with the other skills, agents, and commands in the collection.
Best for
Creators, builders, and teams using Claude Code.
SKILL.md preview
---
name: browser-automation
description: Use when the user asks to automate browser tasks, scrape websites, fill forms, capture screenshots, extract structured data from web pages, or build web automation workflows.
version: 1.0.0
category: Development / Engineering
author: AgentVolt
license: proprietary
tags:
- development
- engineering
---
# Browser Automation
Builds browser automation workflows: scraping websites, filling forms, capturing screenshots, and extracting structured data from web pages. Not for automated testing — that belongs to a dedicated testing skill.
## When to use
… (sign up to view the full skill)More development skills
View all Development skills →Generate
Scaffold code, tests, and boilerplate from a short spec.
Performance Profiler
Systematic performance profiling for Node.js, Python, and Go applications.
Threat Detection
Use when hunting for threats in an environment, analyzing IOCs, or detecting behavioral anomalies in telemetry.
Agent Harness
Turns a domain folder of skills into a bounded agentic loop: compile a goal into a task plan, execute with the domain's tools, verify every task, retry within a budget.