agent coding skill risk: low

AI E2E Web Testing with YAML Scenarios

The prompt describes AWT, a tool that lets AI coding tools create declarative YAML scenarios for browser-based end-to-end testing executed via Playwright with visual matching, OCR,…

SKILL 1 file

SKILL.md

Download

---
name: awt-e2e-testing
description: "AI-powered E2E web testing — eyes and hands for AI coding tools. Declarative YAML scenarios, Playwright execution, visual matching (OpenCV + OCR), platform auto-detection (Flutter/React/Vue), learning DB. Install: npx skills add ksgisang/awt-skill --skill awt -g"
---
# 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
- Main repo: https://github.com/ksgisang/AI-Watch-Tester
- Skill repo: https://github.com/ksgisang/awt-skill
- Cloud demo: https://ai-watch-tester.vercel.app

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.

ROLES & RULES

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.

EXPECTED OUTPUT

Format

markdown

Constraints

include installation command
list features and limitations

CAVEATS

Missing context

Exact YAML schema or example scenario structure
How the AI should invoke or format calls to the AWT tool

Ambiguities

The phrase 'Stop and ask for clarification if required inputs...' does not specify what those inputs are or how the AI should detect their absence.

QUALITY

OVERALL: 0.60
CLARITY: 0.85
SPECIFICITY: 0.75
REUSABILITY: 0.25
COMPLETENESS: 0.65

IMPROVEMENT SUGGESTIONS

Add a short 'Usage' section with a minimal valid YAML example.
Replace the generic limitation paragraph with concrete trigger conditions and output format expectations.

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.