Spark
Sign In
Skill

Automate Web E2E Tests with AI

AI-powered E2E testing with Playwright, using YAML scenarios and visual matching for web apps. Beta.

Get skill
Works with githubplaywrightopencvsqlite
Antigravity
Own this? Claim it

Maintainer of this project? Claim this page to edit the listing.

81
Spark score
out of 100
Updated last month
Version 13.1.1
Models
claudegpt 4ogemini 1 5 prodeepseek v3
Add to Favorites

Why it matters

Execute AI-designed YAML test scenarios in a real browser using Playwright. This skill enables AI coding tools to perform end-to-end testing with human-like interaction, visual matching, and OCR.

Outcomes

What it gets done

01

Translate YAML test scenarios into executable Playwright scripts.

02

Perform end-to-end testing using visual matching and OCR.

03

Auto-detect platforms like Flutter, React, Vue, and Angular.

04

Diagnose and explain test failures with investigation checklists.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/ag-awt-e2e-testing | bash

Overview

AWT - AI-Powered E2E Testing (Beta)

AWT enables AI coding tools to interact with web applications through a real browser. It executes end-to-end tests defined in declarative YAML scenarios, leveraging Playwright for human-like interaction. It supports visual matching and OCR, and can auto-detect platforms like Flutter, React, Next.js, Vue, Angular, and Svelte. The toolchain can execute tests and explain failures for AI coding workflows. It integrates with 5 AI providers and uses SQLite for a learning database of failure-fix patterns. Use AWT when you require AI-assisted end-to-end testing through a real browser, especially when test flows rely on visual matching or OCR instead of stable DOM selectors. It is suitable for platform auto-detection across various frameworks. AWT is also beneficial for AI coding workflows needing failure explanation and diagnosis. Do not use this skill when the task falls outside the described scope. Do not treat its output as a substitute for environment-specific validation, testing, or expert review. Stop and ask for clarification if required inputs, permissions, safety boundaries, or success

What it does

AWT gives AI coding tools the ability to see and interact with web applications through a real browser. Your AI designs YAML test scenarios; AWT executes them with Playwright.

When to use - and when NOT to

  • You need AI-assisted end-to-end testing through a real browser with declarative YAML scenarios.
  • The test flow depends on visual matching, OCR, or platform auto-detection instead of stable DOM selectors.
  • You want an E2E toolchain that can both execute tests and explain failures for AI coding workflows.

Do not use this skill when the task falls outside the described scope. Do not treat its output as a substitute for environment-specific validation, testing, or expert review. Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

What works now

  • YAML scenarios → Playwright with human-like interaction
  • Visual matching: OpenCV template + OCR (no CSS selectors needed)
  • Platform auto-detection: Flutter, React, Next.js, Vue, Angular, Svelte
  • Structured failure diagnosis with investigation checklists
  • Learning DB: failure→fix patterns in SQLite
  • 5 AI providers: Claude, OpenAI, Gemini, DeepSeek, Ollama
  • Skill Mode: no extra AI API key needed

Integrations

  • AI Providers: Claude, OpenAI, Gemini, DeepSeek, Ollama. The skill operates in a mode where no extra AI API key is needed.
  • Testing Framework: Playwright.
  • Database: SQLite for learning failure-fix patterns.

Who it's for

This skill is for AI coding workflows.

To install the skill, use the following command:

npx skills add ksgisang/awt-skill --skill awt -g
Source README

AWT - AI-Powered E2E Testing (Beta)

npx skills add ksgisang/awt-skill --skill awt -g

AWT gives AI coding tools the ability to see and interact with web applications through a real browser. Your AI designs YAML test scenarios; AWT executes them with Playwright.

When to Use

  • You need AI-assisted end-to-end testing through a real browser with declarative YAML scenarios.
  • The test flow depends on visual matching, OCR, or platform auto-detection instead of stable DOM selectors.
  • You want an E2E toolchain that can both execute tests and explain failures for AI coding workflows.

What works now

  • YAML scenarios → Playwright with human-like interaction
  • Visual matching: OpenCV template + OCR (no CSS selectors needed)
  • Platform auto-detection: Flutter, React, Next.js, Vue, Angular, Svelte
  • Structured failure diagnosis with investigation checklists
  • Learning DB: failure→fix patterns in SQLite
  • 5 AI providers: Claude, OpenAI, Gemini, DeepSeek, Ollama
  • Skill Mode: no extra AI API key needed

Links

Built with the help of AI coding tools - and designed to help AI coding tools test better.

Actively developed by a solo developer at AILoopLab. Feedback welcome!

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.