Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Browser Automation (Playwright)

Builds production-grade Playwright workflows for scraping, form filling, screenshot/PDF capture, session reuse and anti-detection.

AutomationIntermediate★ 24,151⑂ 3,405AI score 9/10Last updated: Aug 9, 2026

What it does

  • Provides Playwright patterns for extracting tables, listings and nested data into JSON/CSV/JSONL.
  • Covers pagination (next button, ?page=N, infinite scroll, load-more) plus SPA/AJAX wait strategies.
  • Saves and restores login state via storage_state.json so long jobs skip repeated logins.
  • Splits multi-step forms into per-step functions and handles uploads, custom dropdowns and downloads.
  • Full-page/element screenshots, PDF export (Chromium only) and visual-regression baseline naming.
  • Prioritized anti-detection stack: strip navigator.webdriver, rotate user agents, realistic viewport, randomized delays, proxies — plus exponential backoff and 429 handling.
  • Flags common anti-patterns: hardcoded waits, credentials in code, ignoring robots.txt, leaked browser instances.

Who it's for

  • Python developers and data engineers building crawlers or web data pipelines.
  • Ops/analysts automating repetitive portal logins and report downloads.
  • Teams migrating from Selenium/Puppeteer who need durable selector strategy.
  • Not for E2E test suites — use the playwright-pro skill instead.

Examples

  1. "Scrape 50 pages of search results into a CSV of title, price and link" → pagination loop with dedupe and incremental writes.
  2. "Log into our portal each morning and download the monthly report" → stored session state plus expect_download().
  3. "Capture just the dashboard chart as a daily PNG for comparison" → element screenshot with {page}_{viewport}_{state}.png baselines.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/alirezarezvani/claude-skills/HEAD/.gemini/skills/browser-automation/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the .gemini/skills/browser-automation folder from the GitHub repo alirezarezvani/claude-skills into my ~/.claude/skills/browser-automation/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/alirezarezvani/claude-skills.git /tmp/claude-skills && mkdir -p ~/.claude/skills && cp -r /tmp/claude-skills/.gemini/skills/browser-automation ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/alirezarezvani/claude-skills.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r claude-skills/.gemini/skills/browser-automation ~/.claude/skills/
  5. Install Playwright: pip install playwright then python3 -m playwright install chromium
  6. Restart Claude Code and ask something like "scrape the product data from this page" to trigger the skill.
  7. For authenticated flows, keep credentials in a gitignored .env or environment variables instead of the script.
View source on GitHub ↗License: MIT