| Test web applications end-to-end by simulating user interactions and verifying expected outcomes. QA a feature, check that a page works correctly, validate user journeys, or test a deployment.
npx skills add https://github.com/billy-enrizky/openbrowser-ai --skill e2e-testing
Simulate real user interactions and verify web application behavior using Python code execution. Covers navigation, form interaction, content assertions, and multi-page flows.
All code runs via openbrowser-ai -c. The daemon starts automatically and persists variables across calls. All browser functions are async -- use await.
The CLI daemon also persists cookies and login state in ~/.config/openbrowser/profiles/daemon/storage_state.json, so authenticated sessions can be reused across later runs.
Before running, verify openbrowser-ai is installed:
openbrowser-ai --help
If not found, install:
# macOS/Linux
curl -fsSL https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.sh | sh
# Windows (PowerShell)
irm https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.ps1 | iex
openbrowser-ai -c - <<'EOF'
await navigate("https://staging.example.com")
state = await browser.get_browser_state_summary()
assert "example" in state.url.lower(), f"Unexpected URL: {state.url}"
assert state.title, "Page title is empty"
print(f"Page loaded: {state.title} ({state.url})")
EOF
openbrowser-ai -c - <<'EOF'
# Check for expected text using JS
has_welcome = await evaluate("""
(function(){ return !!document.body.textContent.match(/Welcome to Example App/i) })()
""")
assert has_welcome, "Welcome message not found"
# Check specific element content
h1_text = await evaluate("document.querySelector('h1')?.textContent?.trim()")
assert h1_text == "Example App", f'Expected "Example App", got "{h1_text}"'
# Check no error messages
error_count = await evaluate("document.querySelectorAll('.error-message').length")
assert error_count == 0, f"Found {error_count} error messages on page"
print("All content assertions passed")
EOF
openbrowser-ai -c - <<'EOF'
# Get form fields
state = await browser.get_browser_state_summary()
for idx, el in state.dom_state.selector_map.items():
if el.attributes.get("type") in ("email", "text", "password") or el.tag_name == "button":
etype = el.attributes.get("type", "")
placeholder = el.attributes.get("placeholder", "")
print(f"[{idx}] <{el.tag_name}> type={etype} placeholder=\"{placeholder}\"")
# Fill and submit
await input_text(index=3, text="[email protected]")
await input_text(index=4, text="test-password")
await click(index=5) # Login button
await wait(2)
# Assert logged in
state = await browser.get_browser_state_summary()
assert "dashboard" in state.url.lower() or "welcome" in state.title.lower(), \
f"Login may have failed. URL: {state.url}, Title: {state.title}"
print("Login test passed")
EOF
openbrowser-ai -c - <<'EOF'
# Click settings link
state = await browser.get_browser_state_summary()
for idx, el in state.dom_state.selector_map.items():
if "settings" in el.get_all_children_text(max_depth=1).lower():
await click(index=idx)
break
await wait(1)
# Assert URL changed
path = await evaluate("window.location.pathname")
assert "/settings" in path, f"Expected /settings path, got {path}"
# Test back button
await go_back()
await wait(1)
state = await browser.get_browser_state_summary()
print(f"After back: {state.url}")
EOF
openbrowser-ai -c - <<'EOF'
# Submit form with invalid data
await input_text(index=3, text="not-an-email")
await click(index=5)
await wait(1)
# Assert validation errors appear
errors = await evaluate("""
(function(){
const errs = document.querySelectorAll(".error, .invalid-feedback, [aria-invalid=\"true\"]");
return Array.from(errs).map(e => e.textContent.trim());
})()
""")
assert len(errors) > 0, "Expected validation errors but found none"
print(f"Validation errors shown: {errors}")
# Assert page did not navigate
path = await evaluate("window.location.pathname")
print(f"Still on: {path}")
EOF
openbrowser-ai -c - <<'EOF'
viewport = await evaluate("""
(function(){
return {
width: window.innerWidth,
height: window.innerHeight
}
})()
""")
vw = viewport["width"]
vh = viewport["height"]
print(f"Viewport: {vw}x{vh}")
# Check mobile menu visibility
mobile_display = await evaluate("""
(function(){
const el = document.querySelector(".mobile-menu");
return el ? window.getComputedStyle(el).display : "not found";
})()
""")
print(f"Mobile menu display: {mobile_display}")
EOF
openbrowser-ai -c - <<'EOF'
test_results = []
# Cart page
await navigate("https://staging.example.com/cart")
await wait(1)
cart_title = await evaluate("document.querySelector('h1')?.textContent?.trim()")
test_results.append({"test": "cart_page_loads", "passed": cart_title is not None, "detail": cart_title})
# Checkout
cart_count = await evaluate("JSON.parse(localStorage.getItem('cart'))?.items?.length || 0")
test_results.append({"test": "cart_has_items", "passed": cart_count > 0, "detail": f"{cart_count} items"})
# Print results
import json
passed = sum(1 for t in test_results if t["passed"])
total = len(test_results)
print(f"\nResults: {passed}/{total} passed")
print(json.dumps(test_results, indent=2))
EOF
-c - <<'EOF'), so all Python syntax works without shell escaping issues.assert statements for test assertions -- they produce clear error messages on failure.await wait(N) after interactions that trigger page loads or animations.-c calls while the daemon is running, so you can accumulate test results across calls.evaluate() for DOM state assertions and browser.get_browser_state_summary() for page metadata.This step is mandatory. Run it after the test run finishes, whether assertions passed or failed. Without it, the daemon keeps Chrome running until its 10-minute idle timeout, leaving a stale browser process, a locked profile, and (on macOS/Linux desktop) a visible window.
Stop the daemon, then verify it is gone:
openbrowser-ai daemon stop
openbrowser-ai daemon status
daemon stop closes every tab, exits Chrome, flushes saved cookies/login state to the profile, and shuts down the daemon process. daemon status should report the daemon is not running. If it still reports running, the daemon is wedged, force-kill it:
pkill -f 'openbrowser.*daemon' || true
E2E runs fail often by design (that is what assertions are for). Guarantee cleanup with a shell trap so a failed assertion never leaks a browser:
trap 'openbrowser-ai daemon stop >/dev/null 2>&1 || true' EXIT
# ... openbrowser-ai -c calls here ...
Do not rely on the idle timeout. Do not call done() as a substitute, done() only marks the task complete inside the agent loop, it does not close the browser.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Use when implementing any feature or bugfix, before writing implementation code
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Expert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating quantitative trading strategies. Covers "beating ideas to death" methodology, parameter robustness testing, slippage modeling, bias prevention, and interpreting backtest results. Applicable when user asks about backtesting, strategy validation, robustness testing, avoiding overfitting, or systematic trading development.
Cloud laboratory platform for automated protein testing and validation. Use when designing proteins and needing experimental validation including binding assays, expression testing, thermostability measurements, enzyme activity assays, or protein sequence optimization. Also use for submitting experiments via API, tracking experiment status, downloading results, optimizing protein sequences for better expression using computational tools (NetSolP, SoluProt, SolubleMPNN, ESM), or managing protein design workflows with wet-lab validation.
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
Take billy-enrizky/e2e-testing from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.