Browser Automation
- 738 installs
- 29.9k repo stars
- Updated July 27, 2026
- davila7/claude-code-templates
browser-automation is a Claude Code template skill that teaches reliable Playwright and Puppeteer patterns for web testing, scraping, and agentic browser workflows when developers need stable selectors, waits, and anti-d
About
browser-automation in davila7/claude-code-templates documents battle-tested browser automation for testing, scraping, and AI agent control, sourced from vibeship-spawner-skills under Apache 2.0. The skill recommends Playwright as the default framework while covering Puppeteer when stealth or Chrome-only constraints apply. It emphasizes selectors, explicit waiting strategies, and anti-detection patterns that separate flaky scripts from production-grade automation. Developers reach for browser-automation when wiring E2E tests, building scrapers, or giving agents dependable browser tools instead of one-off scripts that break on timing or layout changes.
- Playwright-first patterns with clear guidance on when to choose Puppeteer
- Test Isolation Pattern ensuring each run starts with fresh state
- User-Facing Locator Pattern using elements the way users see them
- Auto-Wait Pattern leveraging Playwright's built-in waiting mechanisms
- Covers web scraping, browser testing, e2e testing, and agentic browser control
Browser Automation by the numbers
- 738 all-time installs (skills.sh)
- +5 installs in the week ending Jul 24, 2026 (Skillselion tracking)
- Ranked #345 of 2,742 Automation & Workflows skills by installs in the Skillselion catalog
- Security screen: MEDIUM risk (skills.sh audit)
- Data as of Jul 28, 2026 (Skillselion catalog sync)
npx skills add https://github.com/davila7/claude-code-templates --skill browser-automationAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 738 |
|---|---|
| repo stars | ★ 29.9k |
| Security audit | 2 / 3 scanners passed |
| Last updated | July 27, 2026 |
| Repository | davila7/claude-code-templates ↗ |
How do you write reliable Playwright browser automation tests?
Reliably control browsers for testing, scraping, and building agentic workflows with Playwright or Puppeteer.
Who is it for?
Developers writing E2E tests, scrapers, or agent browser tools who want Playwright-first guidance with Puppeteer fallbacks.
Skip if: Vision-only UI automation without DOM access, mobile native UI testing, or teams that only need static HTTP API clients.
When should I use this skill?
The user asks for Playwright or Puppeteer help, flaky browser tests, scraping patterns, or agentic web control best practices.
What you get
Playwright or Puppeteer scripts with stable selectors, wait strategies, and anti-flake patterns for tests or scrapers.
- Playwright or Puppeteer automation script
- E2E test or scraper with wait and selector patterns
Files
Browser Automation
You are a browser automation expert who has debugged thousands of flaky tests and built scrapers that run for years without breaking. You've seen the evolution from Selenium to Puppeteer to Playwright and understand exactly when each tool shines.
Your core insight: Most automation failures come from three sources - bad selectors, missing waits, and detection systems. You teach people to think like the browser, use the right selectors, and let Playwright's auto-wait do its job.
For scraping, yo
Capabilities
- browser-automation
- playwright
- puppeteer
- headless-browsers
- web-scraping
- browser-testing
- e2e-testing
- ui-automation
- selenium-alternatives
Patterns
Test Isolation Pattern
Each test runs in complete isolation with fresh state
User-Facing Locator Pattern
Select elements the way users see them
Auto-Wait Pattern
Let Playwright wait automatically, never add manual waits
Anti-Patterns
❌ Arbitrary Timeouts
❌ CSS/XPath First
❌ Single Browser Context for Everything
⚠️ Sharp Edges
| Issue | Severity | Solution |
|---|---|---|
| Issue | critical | # REMOVE all waitForTimeout calls |
| Issue | high | # Use user-facing locators instead: |
| Issue | high | # Use stealth plugins: |
| Issue | high | # Each test must be fully isolated: |
| Issue | medium | # Enable traces for failures: |
| Issue | medium | # Set consistent viewport: |
| Issue | high | # Add delays between requests: |
| Issue | medium | # Wait for popup BEFORE triggering it: |
Related Skills
Works well with: agent-tool-builder, workflow-automation, computer-use-agents, test-architect
Related skills
Agent BrowserGive their coding agent reliable, high-fidelity control over any website or Electron desktop app.577k39.1k
Lark ApprovalLet their AI coding agent create, read, update, and approve items in Lark (Feishu) approval workflows without leaving the coding environment.471kLark EventHandle Feishu/Lark bot events, webhooks, and subscription callbacks in agent-driven backend code.471kLark Workflow Meeting SummaryAutomatically generate structured meeting summaries and action items from Lark/Feishu calls without manual note-taking.470kLark Workflow Standup ReportAutomatically generate and post daily standup reports in Lark/Feishu from their workflow and activity data.470kLark Vc AgentGive their coding agent the ability to read, create, and update documents, tasks, and wiki pages inside Feishu (Lark).415kHow it compares
Use browser-automation for DOM-based Playwright and Puppeteer reliability; use vision-bridge skills when live-session screenshot control is required instead of selectors.
FAQ
Does browser-automation recommend Playwright or Puppeteer?
browser-automation recommends Playwright as the default framework for new automation because of stronger cross-browser tooling and waiting APIs. Puppeteer remains documented for Chrome-only or stealth-focused scraping scenarios.
What problems does browser-automation address for developers?
browser-automation addresses flaky selectors, poor wait strategies, and brittle scraping logic in Playwright and Puppeteer scripts. The skill supplies patterns for reliable testing, data extraction, and agent-controlled browser workflows.
Is Browser Automation safe to install?
skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.