Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp...
IMPORTANT - Path Resolution:
This skill can be installed in different locations (plugin system, manual installation, global, or project-specific). Before executing any commands, determine the skill directory based on where you loaded this SKILL.md file, and use that path in all commands below. Replace $SKILL_DIR with the actual discovered path.
Common installation paths:
~/.claude/plugins/marketplaces/playwright-py-skill/skills/playwright-py-skill~/.claude/skills/playwright-py-skill<project>/.claude/skills/playwright-py-skillWhen writing and executing Playwright scripts, ALWAYS use Write and Bash tools in separate responses:
ā DO NOT use parallel execution (causes race condition):
Write: create /tmp/playwright-test.py
Bash: uv run run.py /tmp/playwright-test.py <-- Executes before Write completes!
ā ALWAYS use sequential execution:
Response 1: Write /tmp/playwright-test.py
Response 2: Bash: cd $SKILL_DIR && uv run run.py /tmp/playwright-test.py
This prevents race conditions where Bash executes before the file is fully written.
General-purpose browser automation skill. I'll write custom Playwright code for any automation task you request and execute it via the universal executor.
CRITICAL WORKFLOW - Follow these steps in order:
Auto-detect dev servers - For localhost testing, ALWAYS run server detection FIRST:
cd $SKILL_DIR && uv run python -c "from lib.helpers import detect_dev_servers; import asyncio, json; print(json.dumps(asyncio.run(detect_dev_servers())))"
Write scripts to /tmp - NEVER write test files to skill directory; always use /tmp/playwright-test-*.py
Use visible browser by default - Always use headless=False unless user specifically requests headless mode
Parameterize URLs - Always make URLs configurable via environment variable or constant at top of script
/tmp/playwright-test-*.py (won't clutter your project)cd $SKILL_DIR && uv run run.py /tmp/playwright-test-*.pycd $SKILL_DIR
uv run run.py --help
This will automatically install Playwright via PEP 723 metadata. Chromium browser must already be installed (correct version for Playwright 1.56.0).
Step 1: Detect dev servers (for localhost testing)
cd $SKILL_DIR && uv run python -c "from lib.helpers import detect_dev_servers; import asyncio, json; print(json.dumps(asyncio.run(detect_dev_servers())))"
Step 2: Write test script to /tmp with URL parameter
#!/usr/bin/env python3
# /// script
# requires-python = ">=3.10"
# dependencies = [
# "playwright==1.56.0",
# ]
# ///
# /tmp/playwright-test-page.py
from playwright.sync_api import sync_playwright
# Parameterized URL (detected or user-provided)
TARGET_URL = 'http://localhost:3001' # <-- Auto-detected or from user
with sync_playwright() as p:
browser = p.chromium.launch(headless=False)
page = browser.new_page()
page.goto(TARGET_URL)
print('Page loaded:', page.title())
page.screenshot(path='/tmp/screenshot.png', full_page=True)
print('šø Screenshot saved to /tmp/screenshot.png')
browser.close()
Step 3: Execute from skill directory
cd $SKILL_DIR && uv run run.py /tmp/playwright-test-page.py
#!/usr/bin/env python3
# /// script
# requires-python = ">=3.10"
# dependencies = [
# "playwright==1.56.0",
# ]
# ///
# /tmp/playwright-test-responsive.py
from playwright.sync_api import sync_playwright
TARGET_URL = 'http://localhost:3001' # Auto-detected
with sync_playwright() as p:
browser = p.chromium.launch(headless=False, slow_mo=100)
page = browser.new_page()
# Desktop test
page.set_viewport_size({'width': 1920, 'height': 1080})
page.goto(TARGET_URL)
print('Desktop - Title:', page.title())
page.screenshot(path='/tmp/desktop.png', full_page=True)
# Mobile test
page.set_viewport_size({'width': 375, 'height': 667})
page.screenshot(path='/tmp/mobile.png', full_page=True)
browser.close()
#!/usr/bin/env python3
# /// script
# requires-python = ">=3.10"
# dependencies = [
# "playwright==1.56.0",
# ]
# ///
# /tmp/playwright-test-login.py
from playwright.sync_api import sync_playwright
TARGET_URL = 'http://localhost:3001' # Auto-detected
with sync_playwright() as p:
browser = p.chromium.launch(headless=False)
page = browser.new_page()
page.goto(f'{TARGET_URL}/login')
page.fill('input[name="email"]', 'test@example.com')
page.fill('input[name="password"]', 'password123')
page.click('button[type="submit"]')
# Wait for redirect
page.wait_for_url('**/dashboard')
print('ā
Login successful, redirected to dashboard')
browser.close()
#!/usr/bin/env python3
# /// script
# requires-python = ">=3.10"
# dependencies = [
# "playwright==1.56.0",
# ]
# ///
# /tmp/playwright-test-form.py
from playwright.sync_api import sync_playwright
TARGET_URL = 'http://localhost:3001' # Auto-detected
with sync_playwright() as p:
browser = p.chromium.launch(headless=False, slow_mo=50)
page = browser.new_page()
page.goto(f'{TARGET_URL}/contact')
page.fill('input[name="name"]', 'John Doe')
page.fill('input[name="email"]', 'john@example.com')
page.fill('textarea[name="message"]', 'Test message')
page.click('button[type="submit"]')
# Verify submission
page.wait_for_selector('.success-message')
print('ā
Form submitted successfully')
browser.close()
#!/usr/bin/env python3
# /// script
# requires-python = ">=3.10"
# dependencies = [
# "playwright==1.56.0",
# ]
# ///
from playwright.sync_api import sync_playwright
with sync_playwright() as p:
browser = p.chromium.launch(headless=False)
page = browser.new_page()
page.goto('http://localhost:3000')
links = page.locator('a[href^="http"]').all()
results = {'working': 0, 'broken': []}
for link in links:
href = link.get_attribute('href')
try:
response = page.request.head(href)
if response.ok:
results['working'] += 1
else:
results['broken'].append({'url': href, 'status': response.status})
except Exception as e:
results['broken'].append({'url': href, 'error': str(e)})
print(f'ā
Working links: {results["working"]}')
print(f'ā Broken links:', results['broken'])
browser.close()
#!/usr/bin/env python3
# /// script
# requires-python = ">=3.10"
# dependencies = [
# "playwright==1.56.0",
# ]
# ///
from playwright.sync_api import sync_playwright
with sync_playwright() as p:
browser = p.chromium.launch(headless=False)
page = browser.new_page()
try:
page.goto('http://localhost:3000', wait_until='networkidle', timeout=10000)
page.screenshot(path='/tmp/screenshot.png', full_page=True)
print('šø Screenshot saved to /tmp/screenshot.png')
except Exception as error:
print(f'ā Error: {error}')
finally:
browser.close()
#!/usr/bin/env python3
# /// script
# requires-python = ">=3.10"
# dependencies = [
# "playwright==1.56.0",
# ]
# ///
# /tmp/playwright-test-responsive-full.py
from playwright.sync_api import sync_playwright
TARGET_URL = 'http://localhost:3001' # Auto-detected
with sync_playwright() as p:
browser = p.chromium.launch(headless=False)
page = browser.new_page()
viewports = [
{'name': 'Desktop', 'width': 1920, 'height': 1080},
{'name': 'Tablet', 'width': 768, 'height': 1024},
{'name': 'Mobile', 'width': 375, 'height': 667},
]
for viewport in viewports:
print(f'Testing {viewport["name"]} ({viewport["width"]}x{viewport["height"]})')
page.set_viewport_size({'width': viewport['width'], 'height': viewport['height']})
page.goto(TARGET_URL)
page.wait_for_timeout(1000)
page.screenshot(path=f'/tmp/{viewport["name"].lower()}.png', full_page=True)
print('ā
All viewports tested')
browser.close()
For quick one-off tasks, you can execute code inline without creating files:
# Take a quick screenshot
cd $SKILL_DIR && uv run run.py "
with sync_playwright() as p:
browser = p.chromium.launch(headless=False)
page = browser.new_page()
page.goto('http://localhost:3001')
page.screenshot(path='/tmp/quick-screenshot.png', full_page=True)
print('Screenshot saved')
browser.close()
"
When to use inline vs files:
Optional utility functions in lib/helpers.py:
from lib.helpers import *
# Detect running dev servers (CRITICAL - use this first!)
servers = await detect_dev_servers()
print('Found servers:', servers)
# Safe click with retry
safe_click(page, 'button.submit', retries=3)
# Safe type with clear
safe_type(page, '#username', 'testuser')
# Take timestamped screenshot
take_screenshot(page, 'test-result')
# Handle cookie banners
handle_cookie_banner(page)
# Extract table data
data = extract_table_data(page, 'table.results')
See lib/helpers.py for full list.
Configure custom headers for all HTTP requests via environment variables. Useful for:
Single header (common case):
PW_HEADER_NAME=X-Automated-By PW_HEADER_VALUE=playwright-py-skill \
cd $SKILL_DIR && uv run run.py /tmp/my-script.py
Multiple headers (JSON format):
PW_EXTRA_HEADERS='{"X-Automated-By":"playwright-py-skill","X-Debug":"true"}' \
cd $SKILL_DIR && uv run run.py /tmp/my-script.py
Headers are automatically applied when using create_context():
context = create_context(browser)
page = context.new_page()
# All requests from this page include your custom headers
For scripts using raw Playwright API, use the get_context_options_with_headers():
context = browser.new_context(
get_context_options_with_headers({'viewport': {'width': 1920, 'height': 1080}})
)
For comprehensive Playwright API documentation, see API_REFERENCE.md:
detect_dev_servers() before writing test code for localhost testingPW_HEADER_NAME/PW_HEADER_VALUE env vars to identify automated traffic to your backend/tmp/playwright-test-*.py, never to skill directory or user's projectTARGET_URL constant at the top of every scriptheadless=False unless user explicitly asks for headless modeheadless=True when user specifically requests "headless" or "background" executionslow_mo=100 to make actions visible and easier to followwait_for_url, wait_for_selector, wait_for_load_state instead of fixed timeoutsprint() to track progress and show what's happeningPlaywright not installed:
cd $SKILL_DIR && uv run run.py --help
# This will auto-install playwright==1.56.0 via PEP 723
Module not found:
Ensure running from skill directory via run.py wrapper
Browser doesn't open:
Check headless=False and ensure display available
Element not found:
Add wait: page.wait_for_selector('.element', timeout=10000)
User: "Test if the marketing page looks good"
Claude: I'll test the marketing page across multiple viewports. Let me first detect running servers...
[Runs: detect_dev_servers()]
[Output: Found server on port 3001]
I found your dev server running on http://localhost:3001
[Writes custom automation script to /tmp/playwright-test-marketing.py with URL parameterized]
[Runs: cd $SKILL_DIR && uv run run.py /tmp/playwright-test-marketing.py]
[Shows results with screenshots from /tmp/]
User: "Check if login redirects correctly"
Claude: I'll test the login flow. First, let me check for running servers...
[Runs: detect_dev_servers()]
[Output: Found servers on ports 3000 and 3001]
I found 2 dev servers. Which one should I test?
- http://localhost:3000
- http://localhost:3001
User: "Use 3001"
[Writes login automation to /tmp/playwright-test-login.py]
[Runs: cd $SKILL_DIR && uv run run.py /tmp/playwright-test-login.py]
[Reports: ā
Login successful, redirected to /dashboard]
/tmp for automatic cleanup (no clutter)run.py