Playwright

Skill aizech/bernhard-zechmann-skills/skills/engineering/playwright

Modular AI agent skills used across engineering, writing, and research workflows. Model‑agnostic, composable, and production‑tested. Includes engineering, productivity, personal, and experimental skill packs.

Install

npx -y skills add aizech/bernhard-zechmann-skills --skill playwright

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Drive a real browser from the terminal for navigation, form filling, snapshots, screenshots, and UI debugging. Use when the user wants terminal-first browser automation with Playwright.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.1 KB, 435 tokens by cl100k_base, as published. Nobody here has run it

Playwright CLI

Drive a real browser from the terminal using Playwright.

Prerequisite

Check for npx:

command -v npx >/dev/null 2>&1

If missing, ask the user to install Node.js/npm.

Quick start

Use the wrapper script or npx directly:

npx --package @playwright/cli playwright-cli open https://example.com --headed
npx --package @playwright/cli playwright-cli snapshot
npx --package @playwright/cli playwright-cli click e3
npx --package @playwright/cli playwright-cli screenshot

Core workflow

Open the page.
Snapshot to get stable element refs.
Interact using refs from the latest snapshot.
Re-snapshot after navigation or big DOM changes.
Capture artifacts when useful.

Re-snapshot after

Navigation
Clicking elements that change the UI
Opening/closing modals or menus
Tab switches

Refs can go stale. When a command fails, snapshot again.

Patterns

Form fill and submit

npx --package @playwright/cli playwright-cli open https://example.com/form
npx --package @playwright/cli playwright-cli snapshot
npx --package @playwright/cli playwright-cli fill e1 "[email protected]"
npx --package @playwright/cli playwright-cli fill e2 "password123"
npx --package @playwright/cli playwright-cli click e3
npx --package @playwright/cli playwright-cli snapshot

Debug with traces

npx --package @playwright/cli playwright-cli open https://example.com --headed
npx --package @playwright/cli playwright-cli tracing-start
# ...interactions...
npx --package @playwright/cli playwright-cli tracing-stop

Guardrails

Snapshot before referencing element ids.
Prefer explicit CLI commands over arbitrary code execution.
Use --headed when a visual check helps.
Default to CLI commands, not Playwright test specs.

Gives 3 of the 12 instructions most e2e browser skills give in 435 tokens

Counted across 407 of the 410 authors here whose files we hold, read 2026-08-06

use page object model patternin 35 of 407, across 25 files
Snapshot to get element refshere, and in 24 of 407, across 14 files
keep tests independentin 23 of 407, across 18 files
Interact using refs from the latest snapshothere, and in 23 of 407, across 11 files
clean up test data after each testin 21 of 407, across 15 files
test user behavior not implementationin 20 of 407, across 14 files
quarantine flaky tests explicitlyin 19 of 407, across 10 files
wait for specific network conditionsin 18 of 407, across 8 files
re-snapshot after navigation or dom changeshere, and in 17 of 407, across 10 files
Detect running dev servers before writing test codein 17 of 407, across 7 files
use web-first assertionsin 17 of 407, across 14 files
capture screenshots or videos on test failurein 17 of 407, across 14 files

Said here and by no other author read

check for npx before starting
snapshot again when a command fails
prefer explicit cli commands over arbitrary code

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.