Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns. This skill covers Playwright (recommended) and Puppeteer, with patterns for testing, scraping, and agentic browser control. Key insight: Playwright won the framework war. Unless you need Puppeteer's stealth ecosystem or are Chrome-only, Playwright is the better choice in 202
SkillScore100Maintained
Automatic
◆QA & Test Engineering pack
Last verified 8/29/2026
What it changes
Passed 22 of 22 test cases with the skill, and 20 of 22 without it.
Without skill91%
With skill100%
Checks it passed that the model alone missed
Recommends using a user-facing locator like getByRole or getByText rather than CSS or XPath.
Recommends realistic user agent headers, realistic viewport contexts, and natural action triggers over explicit time delays.
2 fixed20 passed either way0 still failing0 broke
Pass-rate lift
+9 pp
Tokens
+3%
Agent turns
0%
Response time
-14%
Model gemini-3.6-flashMeasured 8/29/2026v122 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 2
Prompt
We are automating a login form test. The primary submit button has class 'btn-primary submit-btn' and ID 'submit-id', and its visible text is 'Log In'. To make the test resilient against styling refactors, write a selector strategy to target this button.
What was checked, without and with the skill
Checked
Without skill
With skill
Recommends using a user-facing locator like getByRole or getByText rather than CSS or XPath.
Missed
Passed
case-01 · gemini-3.6-flash · 8/29/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md36 linessingle file
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.
Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns.