skills.rest
andregusman-raiz
andregusman-raizCOMMUNITY
Explore all skills by this author →
GitHub

ag-testar-manual

Automate exploratory QA testing of web applications via Playwright MCP.

19|4|Updated Mar 7, 2026
Search Tags:#reports#qa#playwright#browser-automation#manual-testing#exploratory-testing#test-management
One-click install
npx skills add https://github.com/andregusman-raiz/a-gusman-claude --skill ag-testar-manual
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ag-testar-manual
Source: https://github.com/andregusman-raiz/a-gusman-claude/tree/main/skills/ag-testar-manual
Command: npx skills add https://github.com/andregusman-raiz/a-gusman-claude --skill ag-testar-manual

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables exploratory QA testing of web applications by controlling a browser via Playwright MCP, turning manual exploration into repeatable checks.

Core Features & Use Cases

  • AI-assisted browser control for real-time exploratory testing without manual scripting.
  • Capture screenshots, console errors, accessibility issues, and generate a structured manual test report.
  • Use Case: After deployment, perform exploratory checks on critical flows to verify stability and user experience across browsers and devices.

Quick Start

Open the application with Playwright MCP, perform exploratory browser testing as a real user, and generate the structured manual test report at tests/reports/manual-test-[date].md.

Frequently Asked Questions about ag-testar-manual

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

FAQPage Schema
How do I automate exploratory QA testing with Playwright?▼

You can perform exploratory QA testing with Playwright by using AI-assisted browser control to interact with web applications like a real user. This approach turns manual exploration into repeatable checks without requiring manual scripting.

Can I capture console errors and accessibility issues during browser automation?▼

Yes, browser automation sessions can capture console errors and accessibility issues alongside screenshots. This collects frontend stability and compliance data during real-time exploratory testing.

How do I generate a structured manual test report after an exploratory session?▼

To generate a structured manual test report, perform exploratory checks on critical flows and save the results. The output is a formal markdown report with reproducible steps, screenshots, and captured errors.

Does Playwright browser automation work for post-deployment stability checks?▼

Yes, Playwright browser automation works for post-deployment stability checks by performing exploratory testing on critical user flows. It verifies application stability and user experience across browsers and devices.

What is the best way to run deterministic testing workflows for manual exploratory sessions?▼

The best way to run deterministic testing workflows for manual exploratory sessions is using AI-assisted browser control. This ensures reproducible steps and generates a formal manual test report for each session.

Related Skills

Explore More Software Engineering Skills→
zb-sszb-ss
1

test-live

Run interactive Playwright MCP browser tests against a live web application.

Official
Intermediate
lklimeklklimek
1

triage-findings

Classify code review findings in a browser and update report.json.

Community
Advanced
kk20300113-pngkk20300113-png

land-and-deploy

Merge pull requests and verify production health via canary checks.

Community
Advanced
UnicornUnicorn

e2e-test-agent

Generate end-to-end test suites for web and full-stack applications.

Official
Advanced