live-qa

Automate end-to-end UI QA from localhost with Playwright and map-judge evaluation.

Updated Mar 12, 2026
One-click install
npx skills add https://github.com/arvidfcjarfalla-prog/atlas --skill live-qa
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: live-qa
Source: https://github.com/arvidfcjarfalla-prog/atlas/tree/main/.claude/skills/live-qa
Command: npx skills add https://github.com/arvidfcjarfalla-prog/atlas --skill live-qa

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables end-to-end UI QA by simulating a user from localhost, driving prompts, rendering maps, collecting screenshots, and evaluating results with a map-judge.

Core Features & Use Cases

  • End-to-end UI testing from localhost by issuing live prompts to the running app and capturing visual results.
  • Automated scenario generation, Playwright-based interactions, and deterministic evaluation with map-judge.
  • Useful after frontend/UI changes, manifest updates, or AI pipeline tweaks to validate the full user workflow.

Quick Start

Trigger a live QA session by saying /live-qa and follow the prompts to generate test scenarios, run them end-to-end, and review the map-judge results.

Frequently Asked Questions about live-qa

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

FAQPage Schema
How do I automate end-to-end UI QA testing from a localhost dev server?▼

Automating end-to-end UI QA from localhost involves simulating a user by issuing live prompts to a running app, capturing screenshots via Playwright, and evaluating rendered maps with a map-judge.

Do I need a specific port running to validate UI workflows with Playwright?▼

Yes, validating UI workflows requires a running dev server on port 3000 and a live prompts workflow to generate test scenarios and produce actionable results.

What is a map-judge evaluation in end-to-end testing?▼

A map-judge evaluation in end-to-end testing is a deterministic method to assess rendered maps collected during UI interactions, ensuring visual results meet expected quality standards.

How do I run Playwright test scenarios against my local frontend changes?▼

Running Playwright test scenarios against local frontend changes requires triggering a live QA session, which generates scenarios, executes them on your localhost app, and reviews the map-judge results.

When should I use automated localhost QA for UI feature verification?▼

Use automated localhost QA for UI feature verification after manifest changes, AI pipeline updates, or UI regressions to validate the full user workflow end-to-end.

Can I validate AI pipeline tweaks using end-to-end UI testing?▼

Yes, you can validate AI pipeline tweaks using end-to-end UI testing by simulating user interactions from localhost, driving prompts, and evaluating the rendered map results.