# Playwright Automate

> Browser automation workflows with Playwright MCP integration

- Skill: `manastalukdar/playwright-automate` (Agent Skill)
- Install (CLI): `npx skillmds@latest add manastalukdar/playwright-automate`
- Raw SKILL.md: https://api.skillmd.com/api/skills/manastalukdar/playwright-automate/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: manastalukdar (https://skillmd.com/u/manastalukdar)
- Updated: 2026-09-10
- Page: https://skillmd.com/skills/manastalukdar/playwright-automate

---


# Playwright Browser Automation

I'll help you automate browser tasks using Playwright for testing, screenshots, PDFs, and workflow automation.

Arguments: `$ARGUMENTS` - automation task (screenshot, pdf, scrape, test) or specific URL/workflow

## Automation Capabilities

**Common Workflows:**
- Browser testing and validation
- Screenshot capture (full page, specific elements)
- PDF generation from web pages
- Web scraping and data extraction
- Form automation and submissions
- Performance monitoring

## Token Optimization

**Expected range**: 500–2,000 tokens (initial), 100 tokens (no Playwright)

**Caching**: Caches selector patterns in `.claude/cache/playwright-automate/selector-patterns.json` for 7 days.

**Early exit**: Returns immediately if Playwright is not installed in the project.

**Patterns used**: Grep-before-Read, early exit, template-based generation, caching