More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    🧪 Webapp Tester

    1

    Professional E2E Browser Testing The WebApp Tester skill provides a production-grade automated testing workflow using Playwright.

    $15

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    🧪 Webapp Tester

    🧪 Webapp Tester

    Example session with this skill installed

    Run an E2E test of the login flow on both desktop and mobile viewports. Check for success redirects and report any UI errors or failures found during the process.

    • Read your context and instructions
    • Compiled the webapp tester

    Browser Test Results

    • Coverage: Chromium, iPhone 13
    • Steps:
      • PASS: open login page
      • FAIL: submit valid credentials: expected /dashboard but stayed on /login; visible error "Account locked"
    • Artifacts:
      • screenshot: test-results/failure.png
    • Likely fix: Update seed data for the test user.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Professional E2E Browser Testing

    The WebApp Tester skill provides a production-grade automated testing workflow using Playwright. It solves the common problem of "flaky" or shallow AI-generated tests by implementing a structured, artifact-driven approach to browser automation. Instead of just clicking buttons and hoping for the best, this skill ensures your AI agent acts like a professional QA engineer.

    What it does

    • Comprehensive Coverage: Tests flows across desktop and mobile viewports (iOS/Android emulation).
    • Deep Diagnostics: Automatically captures screenshots, Playwright traces, and console logs on failure.
    • Smart Auth: Manages persistent authentication states, preventing redundant login steps across test suites.
    • Visual Regression: Implements screenshot comparison to catch UI regressions that functional tests might miss.
    • Step-Level Reporting: Provides clear, human-readable summaries of exactly where a flow broke.

    Why use this skill?

    Prompting an AI to "test my site" often results in generic scripts that fail on modern React/Next.js apps. This skill enforces test.step() patterns, proper locators, and environmental awareness. It handles dev servers, manages mobile emulation profiles, and produces actionable debugging data that tells you exactly why a test failed—saving you hours of manual reproduction.

    Supported Tools

    • Frameworks: Playwright (primary), Chromium, WebKit, Firefox.
    • Environments: Local dev servers (localhost), staging, and production.
    • Contexts: Mobile Safari, Mobile Chrome, Desktop Responsive.

    Requires Playwright installed (npm install -D @playwright/test). First test run downloads browsers (~500MB). Tests run on localhost only; no remote browser support. Screenshots save to ./test-results/—ensure this directory is gitignored. Does not test mobile apps (web only).

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 5 months ago

    Requires

    playwright
    Node.js

    Permissions

    Browser
    Environment Variables
    Read Files
    Write Files

    File Scopes

    ./test-results/**/*
    ./tests/**/*
    **/*.spec.ts
    **/*.test.js

    WebApp Tester needs terminal access to run Playwright test commands—the industry standard for browser testing in Node.js environments. These commands launch real browsers (Chromium, Firefox, WebKit) that execute test flows like login, checkout, and form submission. No system modifications occur; the skill only reads test configurations and writes test artifacts (reports, screenshots, videos) to help developers debug failures. The skill never modifies source code, never installs software beyond Playwright's documented setup, and makes no external network calls of its own. All testing happens locally on the user's machine against their chosen test environment (localhost, staging, or production URL). For first-time users, the skill will prompt the user to run npx playwright install if browsers are missing—it does not attempt to install them automatically without permission.

    Listed5 months ago
    Updated1 month ago

    What's inside

    Frequently Asked Questions

    This skill is designed specifically to integrate with terminal-based AI agents like Claude Code and Codex, enabling them to execute complex, multi-step Playwright scripts.

    The skill includes a pre-configured Playwright testing framework optimized for AI interactions, mobile emulation profiles, and a structured reporting system for logs and screenshots.

    Yes, Webapp Tester can authenticate once and maintain persistent state, allowing your agent to run multiple test suites without having to re-perform login steps every time.

    Unlike basic AI prompts, this skill uses a "Deep Diagnostic" approach that captures traces and console logs, providing the agent with the exact technical context needed to fix the bug.

    The skill supports testing against local dev servers (localhost), staging environments, and live production URLs across all major browser engines.

    New in Testing & Debugging