
Web Verify
Use after a user-visible UI edit to verify your OWN change on an isolated loopback server.
Install
npx skills add kirodotdev/KiroCrew --skill web-verify -g -a claude-code -y- Repository
- kirodotdev/KiroCrew4.7k
- Category
- Design
- Updated
- 3d ago
- License
- Apache-2.0
- Context cost
- Mediumabout 2,703 tokens
- Runs scripts
- Yes, review before use
What it does
Use after a user-visible UI edit to verify your OWN change on an isolated loopback server. Capture, read and show real screenshots. Backends: playwright-cli (live Browser panel), agent-browser (annotated frames, pixel diff, a11y), or scripted Playwright. Not web-preview or external-page web-browse.
Web Verify: look at your own front-end change
Tests prove the code runs; they do not prove the pixels are right. A passing
vitest run is compatible with a clipped label, a wrapped flex row, a blank panel
behind a gate, or an empty state that never mounts. When you change UI, open it
and look at it, then put the frame in chat so the user sees the same thing you
did.
This is the self-verification path: the screenshot is evidence, not decoration. It is view-only (navigate plus screenshot); clicking and typing through a flow uses the same CLI with more verbs. Keep the frame count bounded (see below). Restraint here is about context cost, not permission.
Three ways to capture, and name the one you used
Not a backend here: the browser MCP tool. Its screenshot op renders in
the Browser panel and hands you no image file to read, and it refuses loopback
unless the operator listed that exact host:port in
the dashboard's local-origins setting (every URL in this skill is loopback). So
playwright-cli is the local-verification path by design, not by preference.


