browser-automation · sickn33 — Claude Code skill: what it does, install
This skill builds browser checks around observed UI state and explicit outcomes. Use it for UI workflows, timing failures, or authorised page-data collection.
npx skills add sickn33/agentic-awesome-skills --skill browser-automation -a claude-codeWhat browser-automation does
The skill structures browser checks around the current page state, semantic locators, bounded waits, isolated test data, and explicit outcome checks. It uses the browser tool already selected or installed in the project, with Playwright, Puppeteer, or Selenium chosen from the actual integration. Separate browser contexts keep cookies and storage from one test out of another.
Its Playwright examples cover cart actions, form fields, role-based locators, downloads, and JSON inspection. For an export, register the download event before clicking, inspect the file, and verify that changing the input invalidates the old preview. CSS selectors tied to structure, XPath, and generated selectors are treated as fragile choices.
The project needs a running app, an available browser, its imports, a test runner, and fixture routes. The skill installs none of these. Auto-waiting checks whether an action is actionable, not whether a backend write succeeded. Retrying checkout, deletion, or message sending can duplicate a side effect, so verify state before repeating it.
What it helps with
- verify a real browser workflow
- keep data isolated between UI tests
- choose locators from roles or labels
- inspect an exported JSON file
- diagnose a UI timing failure
Example prompts for the agent
- Use the available browser to test adding an item to the cart and verify the final cart count.
- Write a Playwright test for JSON export: register the download, inspect the file, and confirm that editing the form invalidates the old preview.
- Inspect the current page, choose semantic locators, and check keyboard focus at explicit desktop and mobile viewports.
How to install browser-automation
1Skills CLI (Vercel)
npx skills add sickn33/agentic-awesome-skills --skill browser-automation -a claude-code2Manually: put the files in place
~/.claude/skills/browser-automation/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/browser-automation/
1Skills CLI (Vercel)
npx skills add sickn33/agentic-awesome-skills --skill browser-automation -a codex2Manually: put the files in place
.agents/skills/browser-automation/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add sickn33/agentic-awesome-skills --skill browser-automation -a cursor2Manually: put the files in place
.cursor/skills/browser-automation/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install sickn33/agentic-awesome-skills browser-automation2Manually: put the files in place
.github/skills/browser-automation/SKILL.md1Skills CLI (Vercel)
npx skills add sickn33/agentic-awesome-skills --skill browser-automation -a gemini-cli2Platform CLI
gemini skills install https://github.com/sickn33/agentic-awesome-skills --path skills/browser-automationManually: put the files in place
.devin/skills/browser-automation/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add sickn33/agentic-awesome-skills --skill browser-automation -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set3
The whole set →Other versions of browser-automation
Similar
Questions about browser-automation
How do I install browser-automation in Claude Code?
Run npx skills add sickn33/agentic-awesome-skills --skill browser-automation -a claude-code, then run npx skills add sickn33/agentic-awesome-skills --skill browser-automation -a claude-code again. The skill file is available at ~/.claude/skills/browser-automation/SKILL.md.
What does browser-automation do?
It helps build browser checks that observe UI state, use semantic locators, wait within bounds, isolate test data, and verify outcomes explicitly. It also covers download checks and the risks of repeating side-effecting actions.
What do the browser-automation examples require?
They require a running app, an available browser, the project imports, a test runner, and fixture routes. The examples use Playwright, Puppeteer, or Selenium according to the existing integration.
Source text
SKILL.md · MIT
---
name: browser-automation
description: Build reliable browser checks using observed UI state, semantic locators, bounded waits, isolated test data and explicit outcome verification.
risk: critical
source: vibeship-spawner-skills (Apache 2.0)
date_added: 2026-02-27
---
# Browser Automation
Use the browser tool already selected by the user or installed in the project. Playwright, Puppeteer and Selenium have different integrations; choose from actual requirements rather than unsupported success-rate claims. Modified by AAS maintainers on 2026-09-05: removed unverified comparisons and bypass defaults, clarified waiting and evidence limits.
Separate tests of applications you control from interaction with an existing authenticated browser. Do not replace the latter with a fresh unauthenticated session or extract credentials to make an automation test work.
## Detailed Guide
Read [the detailed guide](references/detailed-guide.md) before executing this skill. It retains the complete procedure and reference material. Treat its safety, prerequisites, and validation requirements as mandatory. For focused work, load the relevant sections; for end-to-end work, read the guide completely.
## Playwright Test Example
"""
import { test, expect } from '@playwright/test';
// Each test runs in isolated browser context
test('user can add item to cart', async ({ page }) => {
// Fresh context - no cookies, no storage from other tests
await page.goto('/products');
await page.getByRole('button', { name: 'Add to Cart' }).click();
await expect(page.getByTestId('cart-count')).toHaveText('1');
});
test('user can remove item from cart', async ({ page }) => {
// Completely isolated - cart is empty
await page.goto('/cart');
await expect(page.getByText('Your cart is empty')).toBeVisible();
});
"""
## Good Examples (User-Facing)
"""
// By role - THE BEST CHOICE
await page.getByRole('button', { name: 'Submit' }).click();
await page.getByRole('link', { name: 'Sign up' }).click();
await expect(page.getByRole('heading', { name: 'Dashboard' })).toBeVisible();
await page.getByRole('textbox', { name: 'Search' }).fill('query');
// By text content
await expect(page.getByText('Welcome back')).toBeVisible();
await page.getByText(/Order #\d+/).click(); // Regex supported
// By label (forms)
await page.getByLabel('Email address').fill('[email protected]');
await page.getByLabel('Password').fill('secret');
// By placeholder
await page.getByPlaceholder('Search...').fill('query');
// By test ID (when no user-facing option works)
await page.getByTestId('submit-button').click();
"""
## Bad Examples (Fragile)
"""
// DON'T - CSS selectors tied to structure
await page.locator('.btn-primary.submit-form').click();
await page.locator('#header > div > button:nth-child(2)').click();
// DON'T - XPath tied to structure
await page.locator('//div[@class="form"]/button[1]').click();
// DON'T - Auto-generated selectors
await page.locator('[data-v-12345]').click();
"""
## When to Use
Use to verify a real browser workflow, diagnose a UI timing failure or collect explicitly authorized page data. Inspect the current page and available tool APIs before selecting locators or actions.
## Worked example and prerequisites
Input: exporting a reviewed JSON file from a local web app. Have the app running, the intended browser available and a synthetic form value. Observe the export control, register the download event before clicking, inspect the downloaded JSON and confirm that editing the input invalidates the old preview. Expected: one file containing the reviewed value, with no hidden project data or network submission.
Use explicit desktop/mobile viewports and inspect keyboard/focus behavior when the task includes usability. A locked desktop leaves interactive verification pending; unit tests and headless probes are separate evidence.
## Limitations
- Auto-waiting checks actionability, not business correctness or successful backend writes.
- Screenshots, HTML, traces and auth-state files may contain private information; capture only the authorized scope.
- Retrying a read can be safe; retrying checkout, deletion or sending a message may duplicate a side effect. Verify state before repeating it.
- Resource blocking and mocked responses change the environment and cannot establish unmodified production behavior.
- Examples require the project’s imports, runner and fixture routes; no browser, service or account is installed by this skill.
© sickn33 · MIT · sickn33/agentic-awesome-skills