Testing-Agent
🥈SilverAI-powered browser automation framework that combines Google Gemini LLM with Playwright for intelligent web testing. Features smart element detection, context-aware decision making, and natural language goal execution for strong web automation.
1040Updated 3mo ago
Intermediate30min to implementautomation
Saves ~240 min per use
Quick InstallView Source
git clone https://github.com/Mushfiqur6087/Testing-Agent.gitWorks with:
Claude
Overview
About This Skill
Testing Agent is an autonomous browser test execution engine that runs enriched test cases against live web applications. It coordinates five specialized agents—TraversalPlanner, InteractionAgent, ExecutionOutcomeValidator, and AdaptivePlanner—to intelligently execute test steps, capture before/after DOM states, and validate outcomes using LLM vision. The framework automatically orders test cases by phase (public, authenticated, destructive), handles prerequisite checks between tests, and recovers from session drift. It supports any LLM provider via LiteLLM (OpenAI, Anthropic, Gemini, OpenRouter, Azure) and produces structured test run summaries with detailed pass/fail verdicts and execution evidence.
How to Use
Install dependencies with pip install -r requirements.txt and playwright install chromium. Set your LLM API key in env/.env (OpenAI, Anthropic, Gemini, or OpenRouter supported). Run test_agent_main.py with an enriched test case JSON dataset to execute the full multi-agent pipeline and generate test_run_summary.json results.
Use Cases
Execute automated web test suites with intelligent step ordering and state validation
Validate application behavior changes with before/after DOM snapshots and LLM vision
Run enriched test cases from AutoTestGenX with adaptive prerequisite checking
Handle complex test scenarios including authentication, session management, and state recovery
Tags
Setup & Installation
Quick Install
No install command available. Check the GitHub repository for manual installation instructions.
Alternative Install (Git Clone)
git clone https://github.com/Mushfiqur6087/Testing-AgentRequirements
- Claude Code or compatible AI agent
- Works with: Claude
Quick Start Guide
1
Install the Skill
Copy the install command above and run it in your terminal.
2
Open Your AI Agent
Launch Claude Code, Cursor, or your preferred AI coding agent.
3
Try It Out
Use the prompt template or examples below to test the skill.
4
Customize
Adapt the skill to your specific use case and workflow.
Usage Examples
Prompt Template
Create a test script using the Testing-Agent framework to verify the checkout process on [WEBSITE]. The test should include the following steps: [STEPS]. Ensure the script handles dynamic elements and validates the final order confirmation page.
Example Output
# Test Script for [WEBSITE] Checkout Process
## Test Steps
- Navigate to [WEBSITE] homepage
- Add [PRODUCT] to cart
- Proceed to checkout
- Enter test user details: [USER_DETAILS]
- Validate order confirmation page
## Expected Results
- All steps should complete without errors
- Order confirmation page should display correct order details
## Notes
- Test script should handle dynamic elements
- Validate final order confirmation page
## Test Script
```javascript
const { TestingAgent } = require('testing-agent');
const agent = new TestingAgent();
agent
.navigate('https://[WEBSITE].com')
.click('Add to Cart', { selector: '.add-to-cart-button' })
.click('Proceed to Checkout', { selector: '.checkout-button' })
.fillForm('Checkout Form', {
name: '[USER_NAME]',
email: '[USER_EMAIL]',
address: '[USER_ADDRESS]',
payment: '[PAYMENT_METHOD]'
})
.assertContainsText('Order Confirmation', 'Thank you for your order')
.run();
```Apply to these tools
Browse all tools
Gemini
Google's multimodal AI model and assistant
Automa
Automate your browser workflows effortlessly
Element
Smart cloud calling for sales teams
Microsoft Teams
Get more done every day with Microsoft Teams – powered by AI
Respell
Agentic AI Workflow platform
Notion
Connected workspace for docs, wikis, and projects
Compatible MCP servers
Browse all MCP servers
Find the right skills for your stack
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan