Control Ui

When you need to reproduce a UI bug or verify a visual change with actual evidence, this skill wires up browser automation against your local dev server or Electron app. It reuses whatever Playwright, Cypress, or CDP tooling already lives in the repo instead of adding new dependencies. You get screenshots, accessibility snapshots, console logs, performance profiles, and network traces. The interaction loop is methodical: capture state, perform one action, capture again, compare. It shines when you're chasing layout shifts, focus bugs, or anything that only breaks in a real rendering engine. The guardrails around selector stability and page identification keep you from flaky coordinate clicks and wrong-tab mistakes.

skills.sh installs: 2.5K
GitHub stars: 15.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add cursor/plugins --skill control-ui --agent claude-code

Installs into .claude/skills of the current project.

Files

Control UI

Use local browser automation to verify UI behavior with evidence. First reuse the repo's own Playwright, browser, or Electron harness if it exists; otherwise assemble a temporary local harness around the app's dev server or Chromium debug port.

What It Is Used For

Reproducing UI bugs that depend on real browser focus, keyboard input, scrolling, resizing, or rendering.
Verifying visual or accessibility changes with screenshots and snapshots.
Checking local web, IDE, or Electron behavior before shipping.
Capturing console logs, network logs, CPU profiles, traces, or heap snapshots.
Creating before/after evidence for verify-this.