skywalkskills

CatalogueDelivery Documentation & QA

H4Ready

QA Flow Automation

Drives a workflow in the browser, records each step, and writes the report.

What it examines

  • The scenario you name, step by step
  • Bugs found along that path, with a screenshot
  • A pause for approval before anything is fixed
  • A Playwright spec so the next run does not start from zero

What you get back

A QA report with screenshots, and a Playwright spec for the next run.

Dependencies

  • An AI coding agent that reads SKILL.md files, such as Claude Code, Codex or Gemini CLI
  • Browser control for your agent (these skills are written for the claude-in-chrome tools) and Google Chrome, for the first run of a flow
  • A web app you can reach in a browser, such as a dev or staging URL, with a test login. Start any local servers first.
  • Playwright, for repeat runs from the saved spec: npx playwright test
  • Git, if you want it to draft a commit or pull request. It always asks first.

How it works

You describe a flow, choose Dev or Tester mode and give it the environment. If a Playwright spec for that flow already exists, it runs that cheap path first.

Otherwise it drives the flow in Chrome, takes a screenshot at every step, and reports each bug. In Dev mode it pauses for your approval before fixing anything.

It writes a self-contained PDF report with the screenshots embedded and saves a Playwright spec, so the next run is cheap. It never commits or pushes without asking.

Setup

  1. Unzip the download. Copy the skill folder into your agent's skills folder (for Claude Code, .claude/skills/ or ~/.claude/skills/).
  2. Start the app you want to test and have its URL and a test login ready. Set up browser control for your agent (the claude-in-chrome extension, if you use Claude Code), and Playwright if you want repeat runs.
  3. Restart your agent, then run the skill by its folder name, for example /run-qa-flow-automation.
  4. Tell it what to test, the mode, the environment and where to save the report.

Run it with your agent

Copy the prompt, fill in the parts in square brackets, and paste it into your agent.

Prompt

Run the run-qa-flow-automation skill. Flow to test: [description or ticket]. Mode: [Dev or Tester]. Environment: [URL]. This is a [first run or a re-verify]. Save the report to [path]. Ask me before you commit or push anything.

What is inside

The files that make up this skill, as your agent reads them.

packages/h4-qa-flow-automation

skill › SKILL.md

Sign in to download

Use the email and password you signed up with.