browser-check — browser-check install browser-check, hono-practice, community, browser-check install, ide skills, Chrome MCP connection, app testing with browser-check, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Perfect for Frontend Agents needing automated browser functionality checks through Chrome MCP. browser-check is a skill that facilitates Chrome MCP-based app testing, verifying not just display but also operation accuracy.

Features

Verifies app functionality using Chrome MCP
Connects to target apps via mcp__claude-in-chrome__tabs_context_mcp
Creates new tabs with mcp__claude-in-chrome__tabs_create_mcp
Navigates to target URLs using mcp__claude-in-chrome__navigate
Supports port confirmation for apps like frontend (v1) and backend API

# Core Topics

nnsi nnsi
[1]
[0]
Updated: 2/28/2026

Agent Capability Analysis

The browser-check skill by nnsi 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. Optimized for browser-check install, Chrome MCP connection, app testing with browser-check.

Ideal Agent Persona

Perfect for Frontend Agents needing automated browser functionality checks through Chrome MCP.

Core Value

Empowers agents to verify app functionality by leveraging Chrome MCP for accurate operation checks, streamlining the testing process with vite.config.ts port identification and automated tab creation using mcp__claude-in-chrome__tabs_context_mcp and mcp__claude-in-chrome__tabs_create_mcp.

Capabilities Granted for browser-check

Automating browser checks for frontend applications
Validating app functionality through Chrome MCP
Streamlining testing processes with automated port identification and tab creation

! Prerequisites & Limits

  • Requires Chrome MCP setup
  • Limited to Chrome browser
  • Needs access to vite.config.ts for port confirmation
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

browser-check

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

SKILL.md
Readonly

ブラウザ動作確認

Chrome MCPを使った動作確認の標準手順。「表示されている」だけでなく「操作が正しく動く」まで検証する。

手順

Step 1: 対象アプリのポート確認

確認対象のvite.config.tsを読んでポートを特定する。推測しない。

アプリポート
frontend (v1)1357
frontend-v22460
backend API3456

Step 2: Chrome MCP接続

1. mcp__claude-in-chrome__tabs_context_mcp で現在のタブ情報を取得
2. 接続失敗時はユーザーに「Chrome拡張の再接続をお願いします」と依頼
3. mcp__claude-in-chrome__tabs_create_mcp で新しいタブを作成
4. mcp__claude-in-chrome__navigate で対象URLにアクセス

Step 3: ページ表示確認

1. mcp__claude-in-chrome__computer action=screenshot でスクリーンショット取得
2. mcp__claude-in-chrome__read_page で要素の存在を確認
3. mcp__claude-in-chrome__read_console_messages pattern="error|Error|ERR" でコンソールエラーチェック

Step 3.5: モバイルビューポート確認(UI変更時は必須)

UI変更を含む場合、375px幅でのレイアウトを確認する:

  1. mcp__claude-in-chrome__resize_window で幅375px、高さ812pxにリサイズ
  2. スクリーンショットで表示確認
  3. 特に注意: ヘッダの中央寄せ、モーダル表示位置、フォームボタンの可視性、autoFocusによるキーボード占有

Step 4: 操作検証(これが重要)

「表示されている」だけでは動作確認とは言えない。以下を実施する:

  1. 作成フロー: ボタンクリック → フォーム入力 → 送信 → 結果表示を確認
  2. 編集フロー: 既存データの編集 → 保存 → 反映を確認
  3. 削除フロー: 削除ボタン → 確認UI表示 → 実行 → 一覧から消えることを確認
  4. ネットワーク確認: mcp__claude-in-chrome__read_network_requests でAPIコールの成否を確認

Step 5: 結果報告

各ページ/フローごとに以下を報告:

  • スクリーンショット(成功時)
  • コンソールエラーの有無
  • ネットワークリクエストの成否
  • 操作検証の結果

Step 4補足: 空データだけで確認しない

  • 新規ユーザー(データ0件)だけでなく、既存データがある状態でも確認する
  • 特にグラフ・統計・プログレス表示は、データがないと正常に見えてバグを見逃す
  • フォーム系は送信まで確認する(表示されている≠動く)

注意事項

  • ポートを間違えない(v1: 1357, v2: 2460)。必ずStep 1で確認する
  • 小さい要素はzoomで拡大して確認する
  • フォーム送信ボタンのクリックが効かない場合はEnterキーで代替
  • confirm()は使っていないはずだが、もし出たらセッションがブロックされるので注意
  • サブエージェントにはChrome MCPのアクセス権がない。ブラウザ確認は並列化できない

FAQ & Installation Steps

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

? Frequently Asked Questions

What is browser-check?

Perfect for Frontend Agents needing automated browser functionality checks through Chrome MCP. browser-check is a skill that facilitates Chrome MCP-based app testing, verifying not just display but also operation accuracy.

How do I install browser-check?

Run the command: npx killer-skills add nnsi/hono-practice/browser-check. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for browser-check?

Key use cases include: Automating browser checks for frontend applications, Validating app functionality through Chrome MCP, Streamlining testing processes with automated port identification and tab creation.

Which IDEs are compatible with browser-check?

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 browser-check?

Requires Chrome MCP setup. Limited to Chrome browser. Needs access to vite.config.ts for port confirmation.

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 nnsi/hono-practice/browser-check. 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 browser-check immediately in the current project.

Related Skills

Looking for an alternative to browser-check 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