qa

Automate web app QA sessions with Playwright MCP and multi-mode testing.

Updated Feb 9, 2026
One-click install
npx skills add https://github.com/Xza85hrf/claude-code-agent-kit --skill qa-xza85hrf
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: qa
Source: https://github.com/Xza85hrf/claude-code-agent-kit/tree/main/.claude/skills/quality/qa
Command: npx skills add https://github.com/Xza85hrf/claude-code-agent-kit --skill qa-xza85hrf

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

QA teams waste time and miss issues when tests are manual or flaky; this skill automates systematic web app QA sessions to catch regressions early.

Core Features & Use Cases

  • Multi-mode QA: diff, full, quick, regression.
  • Health scores & reports: structured reports and screenshots.
  • Session hooks: start/stop logs to track QA activity.

Quick Start

Run the qa skill against a project to start an automated QA session.

Frequently Asked Questions about qa

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

FAQPage Schema
How do I automate web QA with Playwright to catch regressions before release?

Automate web QA with Playwright by running methodical testing sessions across local, staging, and CI environments to catch regressions early. It orchestrates multi-mode execution and generates structured reports with automated screenshots for comprehensive bug detection.

Can I run quick smoke checks and full explorations during a single automated QA session?

Yes, automated QA sessions support multi-mode execution including quick smoke checks, full explorations, diff-based testing, and regression comparisons. You can adapt testing depth based on specific single-page app validation needs.

Does this Playwright QA automation work for modern single-page apps in CI pipelines?

Yes, Playwright QA automation applies to modern single-page apps across local development, CI pipelines, and staging environments. It tests diff-based changes and regressions directly within your continuous integration workflow.

What is health scoring in web e2e-testing and how does it report results?

Health scoring in web e2e-testing evaluates application stability during automated QA sessions and outputs structured reports. It combines automated screenshots and session start/stop hooks to provide trackable, auditable health metrics.

How do I track QA activity and audit test coverage across different staging environments?

Track QA activity and audit coverage using session hooks that generate start and stop logs. These hooks monitor automated QA sessions across staging environments, ensuring systematic validation and traceable bug detection.