| name | qa-test-cases |
| description | Turns a feature input (ticket + acceptance criteria, existing cases, a screenshot, observed app behavior, or a recorded walkthrough) into test cases or lighter test scenarios. Use when a tester needs to generate test coverage from any of the "five roads" inputs. Carried from Day 1 of the QA Foundational training; the road-1 input for Day 2. |
| argument-hint | [ticket file, image, or description of the input] |
QA Test Cases
Core principle: You are the oracle. AI is the amplifier. AI drafts coverage fast from whatever input you give it. The tester decides what is real, what is missing, and what is worth writing down.
This skill produces test cases OR scenarios from one input "road." It does not assume the ticket is the whole truth. Every input is a different lens, and no single road finds everything (see reference/test-design-context.md).
Inputs this skill accepts (the five roads)
- Feature ticket + acceptance criteria - a markdown ticket or pasted AC. The documented happy path.
- Existing test cases - generate additional cases (for gap analysis, prefer the
/qa-gap-analysis skill).
- Screenshot of the app - a pasted image. Generate from what is actually on screen.
- Observed app behavior - drive the running app using the
/playwright-cli skill and generate from real states and validation messages. Do not use MCP playwright tools (mcp__playwright__*) as a substitute - always use playwright-cli bash commands. If this path is chosen, to give visibility into the process go ahead and run a background command so we can see what the agent is doing. Then invoke the skill to load its context before navigating. you may save screenshots and walkthrough captures into the directory (e.g. ). Embed these in any HTML report generated from it.
