Stats
Actions
Tags
From setup-ai
QA a web app/UI in a real browser — navigate flows, verify state, catch console/network errors, take screenshots as evidence. Use when asked to QA, test the site, verify a deployment, or confirm a UI feature works end-to-end.
How this skill is triggered — by the user, by Claude, or both
Slash command
/setup-ai:qa-browserThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Verify the app actually works by driving it, not by reading code.
Verify the app actually works by driving it, not by reading code.
npm run dev and read the port) or a
deployed/preview URL the user gives.browse/gstack
skill, or Claude-in-Chrome). Don't pixel-click if a DOM-aware tool exists.Per issue: what you did → what happened → what was expected → screenshot/console evidence. End with a ship/no-ship call. If everything passed, say so with the flows you covered.
npx claudepluginhub linder3hs/setup-ai --plugin setup-aiBlocks Edit/Write/Bash actions until Claude investigates importers, data schemas, and user instructions. Improves output quality by forcing concrete facts before edits.