smartui-skill — Claude Code skill: what it does, how to install
This skill prepares SmartUI visual regression tests for screenshot comparison. Use it to check pages and components across browsers and viewports.
MIT 237 installs ★ 393 updated 2026-10-13
npx skills add LambdaTest/agent-skills --skill smartui-skill -a claude-codeWhat smartui-skill does
smartui-skill generates SmartUI setup for visual testing. It connects screenshot comparison with Playwright, Selenium, Cypress, or Puppeteer and can prepare runs for CLI or Storybook. The skill covers JavaScript, TypeScript, and Java projects.
It creates smartui.config.json with browser, viewport, and render-wait settings, then runs tests through npx smartui exec. The first run supplies baseline images; later runs compare new captures with them, while changes are reviewed in the SmartUI dashboard. The CLI path needs PROJECT_TOKEN; cloud Selenium or Playwright runs also use LT_USERNAME and LT_ACCESS_KEY.
To add it to Claude Code, run npx skills add LambdaTest/agent-skills --skill smartui-skill -a claude-code; the skill file is placed at ~/.claude/skills/smartui-skill/SKILL.md. Without PROJECT_TOKEN, the CLI route cannot authenticate with the cloud service.
What it helps with
- compare page screenshots with a baseline
- check responsive UI across browsers and viewports
- run Playwright visual tests through SmartUI
- set up screenshot checks for Storybook components
- review and approve visual diffs
Example prompts for the agent
- Set up SmartUI visual regression tests for this Playwright project.
- Create
smartui.config.jsonfor Chrome, Firefox, and Safari with several viewports. - Run the Storybook snapshots through SmartUI and compare the component changes.
How to install smartui-skill
1Skills CLI (Vercel)
npx skills add LambdaTest/agent-skills --skill smartui-skill -a claude-code2Manually: put the files in place
~/.claude/skills/smartui-skill/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/smartui-skill/
1Skills CLI (Vercel)
npx skills add LambdaTest/agent-skills --skill smartui-skill -a codex2Manually: put the files in place
.agents/skills/smartui-skill/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add LambdaTest/agent-skills --skill smartui-skill -a cursor2Manually: put the files in place
.cursor/skills/smartui-skill/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install LambdaTest/agent-skills smartui-skill2Manually: put the files in place
.github/skills/smartui-skill/SKILL.md1Skills CLI (Vercel)
npx skills add LambdaTest/agent-skills --skill smartui-skill -a gemini-cli2Platform CLI
gemini skills install https://github.com/LambdaTest/agent-skills --path smartui-skillManually: put the files in place
.devin/skills/smartui-skill/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add LambdaTest/agent-skills --skill smartui-skill -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about smartui-skill
How do I install smartui-skill in Claude Code?
Run npx skills add LambdaTest/agent-skills --skill smartui-skill -a claude-code, then use ~/.claude/skills/smartui-skill/SKILL.md.
What does smartui-skill do?
It generates SmartUI configuration for screenshot-based visual regression tests and supports runs with Playwright, Selenium, Cypress, or Puppeteer. New captures are checked against baseline images.
What is required for a SmartUI CLI run?
Set PROJECT_TOKEN for the CLI workflow. Cloud Selenium or Playwright runs also require LT_USERNAME and LT_ACCESS_KEY.
Source text
SKILL.md · MIT
---
name: smartui-skill
description: >
Generates SmartUI visual regression test configurations for screenshot
comparison on TestMu AI cloud. Framework-agnostic — works with Playwright,
Selenium, Cypress, Puppeteer. Use when user mentions "SmartUI", "visual
regression", "screenshot comparison", "visual testing". Triggers on:
"SmartUI", "visual regression", "screenshot comparison", "pixel diff",
"visual testing LambdaTest".
languages:
- JavaScript
- TypeScript
- Java
category: visual-testing
license: MIT
metadata:
author: TestMu AI
version: "1.0"
---
# SmartUI Visual Regression Skill
## Core Patterns
### Playwright + SmartUI SDK
```javascript
const { chromium } = require('playwright');
const { smartuiSnapshot } = require('@lambdatest/smartui-cli');
(async () => {
const browser = await chromium.launch();
const page = await browser.newPage();
await page.goto('https://example.com');
await smartuiSnapshot(page, 'Homepage');
await page.goto('https://example.com/login');
await smartuiSnapshot(page, 'Login Page');
await browser.close();
})();
```
### Selenium + SmartUI
```java
// Take SmartUI screenshot
((JavascriptExecutor) driver).executeScript(
"smartui.takeScreenshot=Login Page"
);
```
### CLI Execution
```bash
# Install
npm install @lambdatest/smartui-cli@latest --save-dev
# Configure
npx smartui config:create smartui.config.json
# Execute
npx smartui exec -- node test.js
# or with Playwright
npx smartui exec -- npx playwright test
```
### smartui.config.json
```json
{
"web": {
"browsers": ["chrome", "firefox", "safari"],
"viewports": [[1920, 1080], [1366, 768], [375, 812]]
},
"waitForPageRender": 5000,
"waitForTimeout": 1000
}
```
### SmartUI with Storybook
```bash
npx smartui storybook http://localhost:6006 --config smartui.config.json
```
### Approval Workflow
1. First run creates baseline screenshots
2. Subsequent runs compare against baseline
3. Differences highlighted in dashboard
4. Approve/reject changes in LambdaTest SmartUI dashboard
5. Approved screenshots become new baseline
### Anti-Patterns
| Bad | Good | Why |
|-----|------|-----|
| No viewport config | Multiple viewports | Responsive issues |
| No wait for render | `waitForPageRender` | Incomplete screenshots |
| Screenshot everything | Key pages/components | Noise reduction |
| No approval process | Review diffs in dashboard | Catch regressions |
### Cloud Authentication
Set environment variables:
```bash
export PROJECT_TOKEN="your-smartui-project-token" # From SmartUI dashboard
export LT_USERNAME="your-username" # For Selenium/Playwright cloud
export LT_ACCESS_KEY="your-access-key" # For Selenium/Playwright cloud
```
**CLI approach** (uses `PROJECT_TOKEN`):
```bash
npx smartui exec -- npx playwright test
```
**Selenium Cloud approach** (uses `LT_USERNAME`/`LT_ACCESS_KEY`):
```java
// Capabilities include SmartUI options
HashMap<String, Object> ltOptions = new HashMap<>();
ltOptions.put("user", System.getenv("LT_USERNAME"));
ltOptions.put("accessKey", System.getenv("LT_ACCESS_KEY"));
ltOptions.put("build", "SmartUI Build");
ltOptions.put("smartUI.project", "My SmartUI Project");
ChromeOptions options = new ChromeOptions();
options.setCapability("LT:Options", ltOptions);
WebDriver driver = new RemoteWebDriver(
new URL("https://hub.lambdatest.com/wd/hub"), options);
```
## Quick Reference
| Task | Command |
|------|---------|
| Install | `npm install @lambdatest/smartui-cli@latest` |
| Init config | `npx smartui config:create smartui.config.json` |
| Run | `npx smartui exec -- <test command>` |
| Storybook | `npx smartui storybook <url>` |
| Dashboard | `https://smartui.lambdatest.com` |
## Deep Patterns
For advanced patterns, debugging guides, CI/CD integration, and best practices,
see `reference/playbook.md`.
© TestMu AI · MIT · LambdaTest/agent-skills