Browser Automation

SkillWeb & browsing

Browser automation skill is a skill that teaches an AI agent to write reliable browser scripts for web testing, scraping, and agent-driven page interactions. It covers Playwright (recommended) and Puppeteer, focusing on the three main sources of flakiness: bad selectors, missing waits, and detection systems.

Available today. Use it from your connected AI after setup.

Have an agent that can load skill instructions.

Then ask your AI: use the Browser Automation skill

What your AI can do with it

  • Choose selectors the way users see elements (user-facing locators) instead of CSS/XPath fi
  • Use Playwright's auto-wait instead of arbitrary timeouts and waitForTimeout calls
  • Isolate each test with fresh state and separate browser contexts
  • Scrape pages with delays between requests and stealth plugins when needed
  • Handle popups by waiting for them before triggering
  • Enable traces for failures and set a consistent viewport

Getting started

  1. Have an agent that can load skill instructions.
  2. Add the browser-automation skill to the agent's available skills.
  3. Pick Playwright unless you need Puppeteer's stealth ecosystem or Chrome-only support.
  4. Ask the agent to apply the patterns: user-facing locators, auto-waits, and test isolation.
  5. Pair it with related skills like test-architect or workflow-automation when relevant.

What this skill tells your AI

The instructions your AI receives, as published by davila7/claude-code-templates in cli-tool/components/skills/utilities/browser-automation/SKILL.md and read by ahel’s review.

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

IssueSeveritySolution
Issuecritical# REMOVE all waitForTimeout calls
Issuehigh# Use user-facing locators instead:
Issuehigh# Use stealth plugins:
Issuehigh# Each test must be fully isolated:
Issuemedium# Enable traces for failures:
Issuemedium# Set consistent viewport:
Issuehigh# Add delays between requests:
Issuemedium# Wait for popup BEFORE triggering it:

Related Skills

Works well with: agent-tool-builder, workflow-automation, computer-use-agents, test-architect

Signals

GitHub stars
32k
Forks
4k
Last commit
Sep 2026

Questions

Playwright or Puppeteer?
The skill recommends Playwright unless you need Puppeteer's stealth ecosystem or are Chrome-only.
Why do my browser scripts fail randomly?
Most failures come from bad selectors, missing waits, and detection systems. Use user-facing locators, rely on auto-waits instead of fixed timeouts, and isolate each test session.
Is this a runnable tool?
No, it is a skill: instruction patterns an agent follows when writing browser automation with Playwright or Puppeteer.
Advanced
Item type
skill
Key
browser-automation-davila7
Source
github.com/davila7/claude-code-templates