page-compare — community playground.playwright-cli, community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Perfect for Web Automation Agents needing visual comparison of web pages. page-compare is a skill that captures and compares screenshots of web pages to identify visual differences using playwright-cli.

Features

Captures screenshots of web pages using playwright-cli
Visually compares screenshots to analyze differences
Supports multiple URL inputs for comparison
Utilizes playwright-cli open command for browser automation
Executes playwright-cli goto command for page navigation
Takes screenshots using playwright-cli screenshot command
hmu332233 hmu332233
[0]
[0]
Updated: 3/8/2026

Agent Capability Analysis

The page-compare skill by hmu332233 is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Perfect for Web Automation Agents needing visual comparison of web pages.

Core Value

Empowers agents to visually compare web pages using playwright-cli for browser automation, capturing screenshots and analyzing differences via visual inspection, enabling efficient debugging and testing of web applications using protocols like HTTP and HTML.

Capabilities Granted for page-compare

Automating visual regression testing
Debugging web page layout issues
Comparing web page updates across different environments

! Prerequisites & Limits

  • Requires playwright-cli installation
  • Limited to web pages accessible via HTTP/HTTPS
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

page-compare

Install page-compare, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

page-compare Skill

웹 페이지들의 스크린샷을 찍고 시각적으로 비교하여 차이점을 분석합니다.

사용법

/page-compare <URL1> <URL2> [URL3] ...

예시:

/page-compare https://playground-playwright-cli.vercel.app/page-a.html https://playground-playwright-cli.vercel.app/page-b.html https://playground-playwright-cli.vercel.app/page-c.html

동작 방식

  1. 브라우저 실행: playwright-cli open 명령으로 브라우저를 엽니다.

  2. 각 페이지 스크린샷 캡처:

    • 각 URL에 대해:
      • playwright-cli goto <URL> 로 페이지 이동
      • playwright-cli screenshot --full-page --filename=page-N.png 로 전체 페이지 스크린샷 저장
      • N은 1부터 시작하는 순번
  3. 브라우저 종료: playwright-cli close 로 브라우저를 닫습니다.

  4. 이미지 비교 분석:

    • Read 도구로 각 스크린샷 이미지 파일을 읽습니다.
    • Claude의 멀티모달 능력을 활용하여 시각적 차이를 분석합니다.
  5. 결과 리포트 제공:

    • 페이지들이 시각적으로 동일한지 또는 다른지 판단
    • 차이점이 있다면 구체적으로 설명 (레이아웃, 색상, 텍스트, 이미지 등)
    • 각 페이지의 주요 특징 요약

지시사항

사용자가 이 skill을 호출하면:

  1. 제공된 URL 목록을 파싱합니다.
  2. playwright-cli로 브라우저를 열고 각 URL의 스크린샷을 캡처합니다.
  3. 모든 스크린샷 이미지를 읽어서 시각적으로 비교합니다.
  4. 다음 형식으로 결과를 보고합니다:
## 페이지 비교 결과

### 캡처된 페이지
- 페이지 1: <URL1>
- 페이지 2: <URL2>
- 페이지 3: <URL3> (있는 경우)

### 시각적 비교 분석
[각 페이지의 주요 시각적 특징 설명]

### 동일성 판단
- **결과**: 동일함 / 차이 있음
- **차이점** (있는 경우):
  - 레이아웃: [설명]
  - 색상/스타일: [설명]
  - 콘텐츠: [설명]
  - 기타: [설명]

### 요약
[전체 비교 결과 요약]

참고사항

  • 스크린샷은 현재 작업 디렉토리에 저장됩니다.
  • --full-page 옵션을 사용하여 페이지 전체를 캡처합니다 (viewport만이 아닌).
  • 페이지 로딩 시간을 고려하여 스크린샷 전에 충분한 대기 시간을 둘 수 있습니다.
  • 동적 콘텐츠(애니메이션, 타임스탬프 등)로 인한 사소한 차이는 무시하고 주요 시각적 차이에 집중합니다.

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is page-compare?

Perfect for Web Automation Agents needing visual comparison of web pages. page-compare is a skill that captures and compares screenshots of web pages to identify visual differences using playwright-cli.

How do I install page-compare?

Run the command: npx killer-skills add hmu332233/playground.playwright-cli. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for page-compare?

Key use cases include: Automating visual regression testing, Debugging web page layout issues, Comparing web page updates across different environments.

Which IDEs are compatible with page-compare?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for page-compare?

Requires playwright-cli installation. Limited to web pages accessible via HTTP/HTTPS.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add hmu332233/playground.playwright-cli. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use page-compare immediately in the current project.

Related Skills

Looking for an alternative to page-compare or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI