Install any skill in seconds. Free to start, no credit card required.
Get Started Free →zebbern/playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction using playwright-cli.
Passed 21 of 22 test cases with the skill, and 9 of 22 without it.
and 21 more in the full report
12 fixed9 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
I have an element ref e3 pointing to an HTML file input element. What CLI command attaches the local file `./document.pdf` to this element?
| Checked | Without skill | With skill |
|---|---|---|
| Executes `upload e3 ./document.pdf` | Missed | Passed |
The instructions your model reads when the skill loads.
Comprehensive CLI-driven browser automation — navigate, interact, mock, debug, record, and generate tests without writing a single script file.
# Install and set up
playwright-cli install --skills
playwright-cli install-browser
# Open a browser and navigate
playwright-cli open https://playwright.dev
# Take a snapshot to see interactive elements (refs like e1, e2, e3...)
playwright-cli snapshot
# Interact using element refs from the snapshot
playwright-cli click e15
playwright-cli fill e5 "search query"
playwright-cli press Enter
# Take a screenshot
playwright-cli screenshot
# Close the browser
playwright-cli close
snapshot first — identify element refs before interacting; never guess ref numbersfill for inputs, click for buttons — type sends keystrokes one-by-one, fill replaces the entire value-s=name isolates cookies, storage, and tabs per sessionstate-save auth.json after login, state-load auth.json to skip login next timetracing-start before the failing step, not afterrun-code for advanced scenarios — when CLI commands aren't enough, drop into full Playwright APIclose or close-all when done; kill-all for zombie processesscreenshot --filename=checkout-step3.png not screenshotroute to intercept third-party services, not your own apptest cases passed, vs 9 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.