How does it handle complex test results?

It uses a specialized Summarizer Subagent to process raw JSON results and screenshots, providing a concise 'verdict' to the main agent to avoid context clutter.

Does it require manual server management?

No, the skill includes logic to automatically start your dev server (e.g., npm run dev) and wait for a ready signal before running tests.

Can I define project-wide testing rules?

Yes, if a .godag/quality.md file exists in your project root, the skill will inherit global defaults for ports, server commands, and quality bars.

When does the Browser Test skill activate?

It activates automatically when a task scope includes UI components, layouts, frontend routes, navigation flows, or API endpoints that return HTML.

Which testing framework does this skill use?

This skill utilizes Playwright to generate and execute browser-based acceptance tests, focusing on modern web standards and accessibility-based locators.

GoDag Browser Test

Name: GoDag Browser Test
Author: blueif16

byblueif16

0•

ブラウザ自動化

Automates the generation and execution of Playwright-based browser acceptance tests for UI and frontend features.

The Browser Test skill streamlines the quality assurance process by automatically creating Playwright test scripts directly from natural language acceptance criteria. It activates when code changes involve UI components, navigation routes, or user-facing API responses, ensuring that visual and functional regressions are caught early. By managing local dev servers, executing headless tests, and utilizing a specialized summarizer subagent to analyze failures, it provides a robust end-to-end verification loop that keeps the main developer context clean while providing deep insights into test results.

主な機能

010 GitHub stars

02Smart locator selection using getByRole and accessibility-based selectors for resilient tests

03Intelligent failure analysis using a summarizer subagent to distill complex test logs

04Project-wide quality standard inheritance via .godag/quality.md configurations

05Automatic Playwright script generation from natural language acceptance steps

06Automated local dev server lifecycle management including health checks

ユースケース

01Automated regression testing for critical user-facing API responses and network health

02Verifying UI component rendering and layout changes across different routes

03Testing end-to-end user flows like OAuth authentication and form submissions

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add blueif16/amazing-claude-code-plugins browser-test

For use in Claude.ai and ChatGPT

主な機能

010 GitHub stars

02Smart locator selection using getByRole and accessibility-based selectors for resilient tests

03Intelligent failure analysis using a summarizer subagent to distill complex test logs

04Project-wide quality standard inheritance via .godag/quality.md configurations

05Automatic Playwright script generation from natural language acceptance steps

06Automated local dev server lifecycle management including health checks

ユースケース

01Automated regression testing for critical user-facing API responses and network health

02Verifying UI component rendering and layout changes across different routes

03Testing end-to-end user flows like OAuth authentication and form submissions

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add blueif16/amazing-claude-code-plugins browser-test

For use in Claude.ai and ChatGPT