← ClaudeAtlas

browser-checklisted

Drive a real browser and come back with a MEASUREMENT rather than an impression - deterministic waits instead of sleeps, console errors and >=400 responses as counts, computed styles dumped to JSON when appearance is disputed. Use when work touches UI, when a review must verify one, or when fidelity-gate asks for its measurement.
jjanczur/tyran · ★ 48 · Code & Development · score 77
Install: claude install-skill jjanczur/tyran
# Browser check — proving a UI works, in numbers > Three places in this plugin order a browser pass — the conductor's quality > gates, the reviewer, the implementer — and `fidelity-gate` asks for computed > styles on top. None of them said how. This is the how, and it exists so that > "I checked it in the browser" stops being a sentence and starts being a > counter someone else can re-run. **A browser pass is a measurement.** It returns numbers: pages visited, links resolved, console errors, failed responses. `Looks fine`, `renders correctly` and `no obvious issues` are REJECTED by the evidence contract exactly like a test report with no output, and for the same reason — nothing in them can be wrong. ## Before you promise a run 1. **The browser exists.** `npx playwright --version`, and install only chromium (`npx playwright install chromium`) — a full browser install is several GB for two extra engines nobody asked for. 2. **The server is up and SERVING WHAT YOU THINK.** Fetch one known URL and check the status before automating anything. A dev server that is still compiling, or is serving a stale build on a port you forgot to kill, produces a page of failures that have nothing to do with your change. 3. **Build first when the target is a static site.** Testing the dev server and shipping the build tests two different programs. ## Waits are deterministic — never a sleep Wait for a *condition*: a response, a selector, a network-idle state, a font ready