qa-ac-analysis

name	qa-ac-analysis
description	Reads a ticket's acceptance criteria and surfaces gaps, ambiguity, unstated assumptions, and missing cases - then ranks what to test by risk (severity x priority). Use before writing any tests, to interrogate the spec. Day 1 acceptance-criteria + risk block of the QA Foundational training.
argument-hint	[ticket file or pasted acceptance criteria]

QA Acceptance-Criteria Analysis

Core principle: AI is a spec reader before it's a test writer. Point it at the acceptance criteria first and let it ask the questions a careful tester would - then you judge which questions matter. This is shift-left: find holes before code, or before you waste tests on the wrong things.

Input: a ticket + acceptance criteria (a markdown file or pasted text). Output: a list of gaps/ambiguities, then a risk ranking of what to test first.

This is not the same as /qa-gap-analysis (which audits an existing test suite). This skill interrogates the requirements.

Live vs Proposed - know which mode you are in

• Live feature (already built): verify each gap against the running app. For each AI claim decide - product bug, wrong expectation, or genuine spec gap?
• Proposed feature (not built): pure analysis, nothing to observe. The only check is judgment about the spec. Do not assert app behavior you cannot see.

State the mode before you start.

Workflow

Pre-flight checks

Run these before starting any work:

# 1. Verify playwright-cli is installed
playwright-cli --version


playwright-cli install --skills


node -e