test

Execute behavioral tests simulating user interactions across CLI, web, and API interfaces.

Updated Mar 9, 2026
One-click install
npx skills add https://github.com/justinpbarnett/claude --skill test-justinpbarnett
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: test
Source: https://github.com/justinpbarnett/claude/tree/main/skills/test
Command: npx skills add https://github.com/justinpbarnett/claude --skill test-justinpbarnett

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill ensures your application functions as expected by simulating real user interactions, catching bugs that automated unit tests might miss.

Core Features & Use Cases

  • Behavioral Testing: Simulates user actions via CLI, web UI (Playwright), or API calls.
  • Environment Discovery: Automatically finds and uses existing local configurations and credentials.
  • Bug Fixing: Attempts to fix issues found during testing, reporting success or failure.
  • Use Case: After deploying a new feature, use this Skill to test the entire user flow from login to feature usage, ensuring a seamless experience.

Quick Start

Run the test skill to validate the application's core functionality based on recent code changes.

Frequently Asked Questions about test

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

FAQPage Schema
How do I run behavioral tests that simulate real human user interactions across my application?

Running behavioral tests simulates real user interactions across CLI, web, and API interfaces to catch bugs automated unit tests miss. The process analyzes code changes, builds test plans covering happy paths and edge cases, and uses local configurations without mocking. Playwright is required for web UI testing.

Why choose behavioral testing over standard unit testing for validating application behavior?

Behavioral testing catches bugs standard unit tests miss by simulating real human user interactions across CLI, web, and API interfaces. It builds comprehensive test plans including happy paths and edge cases from code changes, adhering to strict no-mocking policies using actual local configurations.

Do I need Playwright installed to test web UI interactions with this approach?

You need Playwright installed to execute behavioral tests against web UI interfaces. The testing approach requires Playwright specifically for browser automation, discovers existing local environment configurations automatically, and adheres to strict no-mocking policies during CLI, web, and API testing.

Can I use this testing method to automatically fix bugs discovered during the simulation?

This testing method attempts to fix bugs discovered during the behavioral simulation across CLI, web, and API interfaces. After analyzing code changes and building test plans, it executes tests, attempts to fix identified issues automatically, and reports success or failure for each bug fix.

How does the testing process handle local environment configurations and credentials?

The testing process handles local environment configurations through automatic environment discovery, finding and using existing local credentials without mocking. It builds test plans from code changes, executes behavioral tests across interfaces, and attempts to fix issues found during the simulation.

Does the testing approach support mocking for API and web interface validations?

The testing approach does not support mocking due to strict no-mocking policies. It validates API and web interfaces by discovering and using actual local environment configurations and credentials to simulate real human user interactions, ensuring behavioral tests reflect true application behavior.