skills.rest
RaphaEnterprises-AI
RaphaEnterprises-AIOFFICIAL
Explore all skills by this author →
GitHub

e2e-testing-agent

Automate end-to-end testing workflows for full-stack applications with Playwright and LangGraph.

4|2|Updated Dec 30, 2025
Search Tags:#automation#CI/CD#Claude#Playwright#end-to-end#self-healing#ai-testing
One-click install
npx skills add https://github.com/RaphaEnterprises-AI/argus-backend --skill e2e-testing-agent
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: e2e-testing-agent
Source: https://github.com/RaphaEnterprises-AI/argus-backend/tree/main/skills/e2e-testing
Command: npx skills add https://github.com/RaphaEnterprises-AI/argus-backend --skill e2e-testing-agent

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a framework for building autonomous E2E testing agents and orchestrating AI-powered testing pipelines, reducing manual test authoring and speeding up feedback loops.

Core Features & Use Cases

  • AI-driven orchestration: Leverages Claude's Computer Use API and LangGraph to coordinate UI, API, and database tests.
  • Hybrid automation: Combines Playwright-based actions with visual verification for robust test results.
  • Self-healing: Automatically detects and repairs flaky selectors and timing issues to keep tests resilient.
  • CI/CD integration: Simplifies integration into pipelines and multi-agent testing workflows.

Quick Start

Use this skill to bootstrap an autonomous end-to-end testing agent for your full-stack application. Install dependencies and run the agent against your codebase.

Frequently Asked Questions about e2e-testing-agent

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate end-to-end testing for a full-stack application without writing manual tests?▼

You can automate end-to-end testing by deploying an autonomous agent that uses Claude's Computer Use API and LangGraph to orchestrate Playwright actions, visual verification, and database validations, eliminating the need for manual test authoring.

How does self-healing test automation handle flaky selectors and timing issues?▼

Self-healing test automation automatically detects and repairs flaky selectors and timing issues by combining AI-driven visual verification with Playwright automation, ensuring your E2E tests remain resilient against UI changes without requiring constant manual updates.

Can I integrate AI-driven E2E testing agents into my CI/CD pipeline?▼

Yes, you can integrate AI-driven E2E testing agents into your CI/CD pipeline. The framework supports multi-agent test orchestration for UI, API, and database validations, simplifying the deployment of autonomous testing workflows directly within your continuous integration processes.

Do I need Python and Playwright to use autonomous E2E testing orchestration?▼

Yes, you need a Python environment with dependencies including anthropic, langgraph, playwright, httpx, and pydantic. You must also configure an API key and use MCP-based Playwright integration to run the structured test specification framework.

What is the best way to coordinate UI, API, and database tests using AI agents?▼

The best way to coordinate UI, API, and database tests is using LangGraph orchestration combined with Claude's Computer Use API. This multi-agent approach manages hybrid Playwright automation and visual verification to execute comprehensive full-stack validations.

Why are my Playwright E2E tests failing due to UI changes and how can I fix them?▼

Playwright E2E tests fail due to UI changes because traditional selectors break easily. You can fix this by implementing a self-healing testing agent that automatically detects and repairs flaky selectors and timing issues, keeping your test suite resilient.

Related Skills

Explore More Software Engineering Skills→
youdotcom-ossyoudotcom-oss
59

ydc-openai-agent-sdk-integration

Integrate You.com MCP tools into OpenAI Agents SDK applications.

Official
Intermediate
whichguywhichguy

concurrent-evolution

Coordinate eight concurrent sub-agent tests and generate a Sovereign Tournament Report.

Community
Advanced
robotlearning123robotlearning123

denario

Automate scientific research workflows from data analysis to LaTeX paper writing.

Community
Advanced
MartinNevlahaMartinNevlaha
1

e2e

Orchestrate Playwright Test Agents for end-to-end test generation and healing.

Community
Advanced