chrome-mcp-testing — for Claude Code chrome-mcp-testing, whos-next, community, for Claude Code, ide skills, mcp_io_github_chr, mcp_io_github_chr_fill, mcp_io_github_chr_click, take_snapshot, mcp_io_github_chr_evaluate_script

v1.0.0

이 스킬 정보

적합한 상황: Ideal for AI agents that need chrome mcp testing. 현지화된 요약: # Chrome MCP Testing Use this skill when running browser tests with Chrome MCP tools. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

기능

Chrome MCP Testing
Use this skill when running browser tests with Chrome MCP tools.
End-to-end verification of frontend flows
Fast repro of UI bugs in local dev
Regression checks around authentication and core user journeys

# 핵심 주제

JulianCissen JulianCissen
[0]
[0]
업데이트: 4/19/2026

Skill Overview

Start with fit, limitations, and setup before diving into the repository.

적합한 상황: Ideal for AI agents that need chrome mcp testing. 현지화된 요약: # Chrome MCP Testing Use this skill when running browser tests with Chrome MCP tools. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

이 스킬을 사용하는 이유

추천 설명: chrome-mcp-testing helps agents chrome mcp testing. Chrome MCP Testing Use this skill when running browser tests with Chrome MCP tools. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

최적의 용도

적합한 상황: Ideal for AI agents that need chrome mcp testing.

실행 가능한 사용 사례 for chrome-mcp-testing

사용 사례: Applying Chrome MCP Testing
사용 사례: Applying Use this skill when running browser tests with Chrome MCP tools
사용 사례: Applying End-to-end verification of frontend flows

! 보안 및 제한 사항

  • 제한 사항: Useful fallbacks (evaluate script only — for reading state, not for input):
  • 제한 사항: Requires repository-specific context from the skill documentation
  • 제한 사항: Works best when the underlying tools and dependencies are already configured

About The Source

The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Labs 데모

Browser Sandbox Environment

⚡️ Ready to unleash?

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

Boot Container Sandbox

FAQ 및 설치 단계

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

? 자주 묻는 질문

chrome-mcp-testing은 무엇인가요?

적합한 상황: Ideal for AI agents that need chrome mcp testing. 현지화된 요약: # Chrome MCP Testing Use this skill when running browser tests with Chrome MCP tools. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

chrome-mcp-testing은 어떻게 설치하나요?

다음 명령을 실행하세요: npx killer-skills add JulianCissen/whos-next/chrome-mcp-testing. Cursor, Windsurf, VS Code, Claude Code와 19개 이상의 다른 IDE에서 동작합니다.

chrome-mcp-testing은 어디에 쓰이나요?

주요 활용 사례는 다음과 같습니다: 사용 사례: Applying Chrome MCP Testing, 사용 사례: Applying Use this skill when running browser tests with Chrome MCP tools, 사용 사례: Applying End-to-end verification of frontend flows.

chrome-mcp-testing 와 호환되는 IDE는 무엇인가요?

이 스킬은 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 와 호환됩니다. 통합 설치에는 Killer-Skills CLI를 사용하세요.

chrome-mcp-testing에 제한 사항이 있나요?

제한 사항: Useful fallbacks (evaluate script only — for reading state, not for input):. 제한 사항: Requires repository-specific context from the skill documentation. 제한 사항: Works best when the underlying tools and dependencies are already configured.

이 스킬 설치 방법

  1. 1. 터미널 열기

    프로젝트 디렉터리에서 터미널 또는 명령줄을 여세요.

  2. 2. 설치 명령 실행

    npx killer-skills add JulianCissen/whos-next/chrome-mcp-testing 를 실행하세요. CLI가 IDE 또는 에이전트를 자동으로 감지하고 스킬을 설정합니다.

  3. 3. 스킬 사용 시작

    스킬이 이제 활성화되었습니다. 현재 프로젝트에서 chrome-mcp-testing을 바로 사용할 수 있습니다.

! Source Notes

This page is still useful for installation and source reference. Before using it, compare the fit, limitations, and upstream repository notes above.

Upstream Repository Material

The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Upstream Source

chrome-mcp-testing

# Chrome MCP Testing Use this skill when running browser tests with Chrome MCP tools. This AI agent skill supports Claude Code, Cursor, and Windsurf

SKILL.md
Readonly
Upstream Repository Material
The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.
Upstream Source

Chrome MCP Testing

Use this skill when running browser tests with Chrome MCP tools.

When to Apply

  • End-to-end verification of frontend flows
  • Fast repro of UI bugs in local dev
  • Regression checks around authentication and core user journeys

Preferred Tooling

Use Chrome MCP browser tools with the mcp_io_github_chr prefix for navigation, script evaluation, and interaction.

Interaction Priority Order

  1. mcp_io_github_chr_fill (uid) — most reliable for Angular inputs. Always triggers Angular's change detection correctly and enables bound send/submit buttons.
  2. mcp_io_github_chr_click (uid) — most reliable for buttons and interactive elements. Use take_snapshot first to discover stable uids.
  3. mcp_io_github_chr_evaluate_script — use for reading state, waiting, combining multiple steps, or actions where uid tools are insufficient. Do NOT use for setting Angular input values — new Event('input', { bubbles: true }) does not reliably trigger Angular change detection and leaves send/submit buttons disabled.

Get uids via take_snapshot before any click or fill:

javascript
1// 1. Snapshot to discover uids 2await mcp_io_github_chr_take_snapshot(); 3// 2. Fill input by uid 4await mcp_io_github_chr_fill({ uid: '3_8', value: 'my answer' }); 5// 3. Click button by uid 6await mcp_io_github_chr_click({ uid: '3_9' });

Test Setup

  1. Navigate to the app root (e.g. http://localhost:4200).
  2. Navigate to the login route and select the desired dev user.
  3. Wait explicitly after navigation or login for the app shell to settle before assertions.
  4. Use take_snapshot after each navigation to get fresh uids before interacting.

Login example:

javascript
1await mcp_io_github_chr_navigate_page({ type: 'url', url: 'http://localhost:4200/login' }); 2await mcp_io_github_chr_take_snapshot(); 3// Find the dev user button uid in the snapshot, then click it 4await mcp_io_github_chr_click({ uid: '<dev-user-button-uid>' }); 5await mcp_io_github_chr_evaluate_script({ 6 function: () => new Promise(resolve => setTimeout(() => resolve(window.location.href), 2000)) 7});

Reliable Selectors and DOM Patterns

  • Dev-auth user buttons are rendered as buttons in the snapshot — use uid-based click after snapshot.
  • Material input controls: uid-stable in snapshot, including current value state. Inspect snapshot to verify current value after interactions.
  • Elements with stable aria-label attributes can be targeted via evaluate_script as a fallback for reading state.

After every navigation or significant DOM change, call take_snapshot to refresh uids before further interactions.

Useful fallbacks (evaluate_script only — for reading state, not for input):

javascript
1const pageText = document.body.innerText; 2const section = document.querySelector('[aria-label*="your label"]'); 3const text = section ? section.innerText.slice(-400) : '';

Optimization Guidelines

  • Prefer uid-based click/fill over all other interaction methods.
  • Call take_snapshot before every significant interaction to ensure uids are fresh.
  • Use evaluate_script only for read operations (page text, current URL), waits, or actions that genuinely require scripting.
  • When debugging odd behavior, stop at the first unexpected outcome and record the exact action plus observed state before continuing.

Fast Failure Reporting Template

When you detect unexpected behavior, report:

  • Step number in journey
  • Action performed (navigation, fill value, click target)
  • Response or state change observed
  • Expected vs. actual result
  • Whether the issue appears interaction-related, state-sync-related, or rendering-only

End-to-End Smoke Script Pattern

javascript
1// 1. Login 2await mcp_io_github_chr_navigate_page({ type: 'url', url: 'http://localhost:4200/login' }); 3await mcp_io_github_chr_take_snapshot(); 4// Find dev user button uid from snapshot, then: 5await mcp_io_github_chr_click({ uid: '<dev-user-button-uid>' }); 6await mcp_io_github_chr_evaluate_script({ 7 function: () => new Promise(r => setTimeout(() => r(window.location.href), 2000)) 8}); 9 10// 2. Navigate to target page 11await mcp_io_github_chr_navigate_page({ type: 'url', url: 'http://localhost:4200/<your-route>' }); 12await mcp_io_github_chr_take_snapshot(); 13 14// 3. Interact (fill inputs, click buttons) 15await mcp_io_github_chr_fill({ uid: '<input-uid>', value: 'my value' }); 16await mcp_io_github_chr_click({ uid: '<button-uid>' }); 17await mcp_io_github_chr_evaluate_script({ 18 function: () => new Promise(r => setTimeout(() => r(window.location.href), 2000)) 19}); 20 21// 4. Read and assert state 22await mcp_io_github_chr_evaluate_script({ 23 function: () => document.body.innerText.slice(-400) 24});

관련 스킬

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

모두 보기

openclaw-release-maintainer

Logo of openclaw
openclaw

현지화된 요약: 🦞 # OpenClaw Release Maintainer Use this skill for release and publish-time workflow. It covers ai, assistant, crustacean workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

333.8k
0
인공지능

widget-generator

Logo of f
f

현지화된 요약: Generate customizable widget plugins for the prompts.chat feed system # Widget Generator Skill This skill guides creation of widget plugins for prompts.chat . It covers ai, artificial-intelligence, awesome-list workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf

149.6k
0
인공지능

flags

Logo of vercel
vercel

현지화된 요약: The React Framework # Feature Flags Use this skill when adding or changing framework feature flags in Next.js internals. It covers blog, browser, compiler workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

138.4k
0
브라우저

pr-review

Logo of pytorch
pytorch

현지화된 요약: Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review . It covers autograd, deep-learning, gpu workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

98.6k
0
개발자