gauriiagarwal

E Commerce AI Testing Agent — Testing skill for Claude Code

Testing community

An autonomous QA agent that tests an e-commerce checkout flow end to end, combining Playwright for browser automation, the Claude API for reasoning and reporting, and YOLOv8 + OpenCV for visual-diff d.

How to install E Commerce AI Testing Agent

This entry records only its repository, not the path inside it, so there is no exact command to give. Open gauriiagarwal/-E-Commerce-AI-Testing-Agent and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What E Commerce AI Testing Agent does

An autonomous QA agent that tests an e-commerce checkout flow end to end, combining Playwright for browser automation, the Claude API for reasoning and reporting, and YOLOv8 + OpenCV for visual-diff detection.

Alternatives in Testing

  • Playwright — claude-plugins-official Browser automation, E2E testing, screenshots 29.4k ★
  • Playwright — Automate real browser interactions for navigation, forms, and scraping 14.6k ★
  • Playwright Automation — git clone Browser automation skill for end-to-end testing and web interaction 2.3k ★

README

🛒 E-Commerce AI Testing Agent

An autonomous QA agent that tests an e-commerce checkout flow end to end, combining **Playwright** for browser automation, the **Claude API** for reasoning and reporting, and **YOLOv8 + OpenCV** for visual-diff detection.


📌 Table of Contents

  1. Overview
  2. Problem Statement
  3. Key Features
  4. Tech Stack
  5. Architecture & Workflow
  6. Honest Note on YOLOv8
  7. Getting Started
  8. Configuration
  9. Step-by-Step Breakdown
  10. Test Run Results & Debugging
  11. Responsible Testing Practices
  12. Limitations
  13. Future Scope
  14. Project Structure
  15. Disclaimer

🔍 Overview

Manual testing of a checkout flow means repeating the same **login → search → cart → address → coupon → payment** sequence for every release, plus every edge case (invalid PIN, missing fields, expired coupons, price mismatches).

This project automates that whole journey with a single agent. It:

  • Logs in and searches for a product
  • Adds the product to the cart and validates the cart contents
  • Fills shipping details, including negative edge cases
  • Tests coupon codes (valid, expired, wrong format, max-use, stacking)
  • Verifies that the order total is mathematically correct
  • Completes a sandbox-only payment
  • Generates a structured HTML QA report

It was built and executed in **Google Colab** against [automationexercise.com](https://automationexercise.com), a public practice site made for QA automation training.

Two implementations are included:

Version Description
Claude-assisted The AI picks the best product, checks for CAPTCHAs, validates cart contents, and writes the final report.