Agent skill

Browser Debugging

by vibeeval in vibeeval/vibecosystem

Chrome DevTools MCP ile browser debugging. An agent skill from vibeeval/vibecosystem.

MITAuto-check passedDevelopment

Install Browser Debugging

skills CLI
$ npx skills add vibeeval/vibecosystem --skill browser-debugging -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install vibeeval/vibecosystem browser-debugging --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/vibeeval/vibecosystem.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/browser-debugging .claude/skills/browser-debugging && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
browser-debugging
GitHub stars
531
Token cost
~2.6k tokens
SKILL.md length
320 words
Files
1
Skills in repo
144
Repo updated
First seen
Licence
MIT

At a glance

Chrome DevTools MCP ile browser debugging. An agent skill from vibeeval/vibecosystem.

  • Tasks that involve Debugging
  • SKILL.md covers Chrome DevTools MCP Setup, Console Log Okuma ve Analiz, Network Request Izleme and Performance Profiling, plus 3 more sections
  • Calls npm and npx
  • Tasks that involve Browser testing

What it does

Browser Debugging is an agent skill from vibeeval/vibecosystem. Chrome DevTools MCP ile browser debugging. Console, network, performance, DOM analizi.

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Debugging and Browser testing. It works with Model Context Protocol and Chrome DevTools. The repository describes itself as: AI software team for Claude Code - 138 agents, 295 skills, 73 hooks. Self-learning, multi-agent swarm, autonomous skill evolution. The licence is MIT.

When your agent uses it

  • Tasks that involve Debugging
  • Tasks that involve Browser testing

Example prompts

  • “/browser-debugging”

Requirements

  • Node.js

What it can do on your machine

Read from SKILL.md and the folder at commit 3b763b1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm
    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm and npx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Browser Debugging loads about 2.6k tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 320 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~26
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from vibeeval/vibecosystem at commit 3b763b1, republished under its MIT licence (© vibeeval). 320 words, ~2,641 tokens.

Download SKILL.mdSave it as .claude/skills/browser-debugging/SKILL.md (or your agent's skills folder).
name
browser-debugging
description
Chrome DevTools MCP ile browser debugging. Console, network, performance, DOM analizi.

Browser Debugging (Chrome DevTools MCP)

Chrome DevTools MCP Setup

Kurulum
bash
# NPM ile
npm install -g @anthropic/chrome-devtools-mcp

# veya npx ile (kurulum gerektirmez)
npx @anthropic/chrome-devtools-mcp
MCP Config (~/.mcp.json)
json
{
  "mcpServers": {
    "chrome-devtools": {
      "command": "npx",
      "args": ["-y", "@anthropic/chrome-devtools-mcp"],
      "env": {
        "CHROME_DEVTOOLS_PORT": "9222"
      }
    }
  }
}
Chrome'u Debug Modunda Baslat
bash
# macOS
/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome \
  --remote-debugging-port=9222 \
  --user-data-dir=/tmp/chrome-debug

# Linux
google-chrome --remote-debugging-port=9222 --user-data-dir=/tmp/chrome-debug

# Headless mod
google-chrome --headless --remote-debugging-port=9222

Console Log Okuma ve Analiz

Console Mesajlarini Yakala
devtools.get_console_logs({
  level: "error",     // log | warn | error | info | debug
  limit: 50,
  clear_after: false
})
Console Mesaj Analizi
SeviyeAnlamAksiyon
errorRuntime hatasiHEMEN fix et
warnPotansiyel sorunIncele, gerekiyorsa fix
infoBilgi mesajiDebug icin kullan
logDebug outputTemizle (production'da olmamali)
Yaygin Console Hatalari
// TypeError: Cannot read properties of undefined
→ Null check eksik, optional chaining kullan: obj?.prop

// CORS error
→ Backend'de Access-Control-Allow-Origin header eksik

// Uncaught Promise rejection
→ async/await'te try/catch eksik

// React: Each child should have a unique key
→ map() icinde key={unique_id} ekle

// React: Maximum update depth exceeded
→ useEffect dependency array'de sonsuz dongu

Network Request Izleme

Request'leri Listele
devtools.get_network_requests({
  url_filter: "/api/",
  method: "POST",
  status_code: 500,
  limit: 20
})
Request Detayi
devtools.get_request_detail({
  request_id: "req-123",
  include_body: true,
  include_headers: true
})
Network Analiz Tablosu
MetrikIyiKotuKontrol
TTFB<200ms>600msServer response suresi
Download<100ms>500msPayload buyuklugu
Total time<500ms>2sButun pipeline
Payload size<100KB>1MBCompression, pagination
Request count<50/sayfa>100/sayfaBatching, caching
Yaygin Network Sorunlari
Status 401 → Token expired, auth flow kontrol et
Status 403 → Permission eksik, RBAC kontrol et
Status 404 → URL yanlis, routing kontrol et
Status 429 → Rate limited, backoff ekle
Status 500 → Server error, backend log'lara bak
Status 502 → Proxy/gateway sorunu, infra kontrol et
CORS error → Preflight (OPTIONS) basarisiz
Mixed content → HTTPS sayfada HTTP request

Performance Profiling

Performance Snapshot
devtools.get_performance_metrics({
  include_timing: true,
  include_memory: true
})
Core Web Vitals Olcumu
devtools.evaluate_expression({
  expression: `
    new PerformanceObserver((list) => {
      for (const entry of list.getEntries()) {
        console.log(entry.name, entry.value || entry.startTime);
      }
    }).observe({ type: 'largest-contentful-paint', buffered: true });
  `
})
Performance Metrikleri
MetrikHedefOlcum
LCP<2.5sEn buyuk elementin renderlanma suresi
FID/INP<100msIlk input'a tepki suresi
CLS<0.1Gorsel kayma skoru
FCP<1.8sIlk icerigin gorundugu an
TTI<3.8sTamamen interaktif olma suresi
TBT<200msMain thread bloklanma suresi
Performance Anti-Patterns
1. Layout thrashing: DOM oku/yaz/oku/yaz (batch et)
2. Forced reflow: offsetHeight gibi prop'lar reflow tetikler
3. Unoptimized images: WebP/AVIF kullan, lazy load et
4. Render blocking CSS: Critical CSS inline, gerisi async
5. Long tasks: 50ms+ main thread task'lari parcala
6. Excessive DOM: 1500+ node varsa virtual scroll kullan

DOM Inspection

Element Sec ve Incele
devtools.query_selector({
  selector: "#main-content .card",
  include_styles: true,
  include_attributes: true
})
DOM Tree
devtools.get_dom_tree({
  depth: 3,
  root_selector: "#app"
})
Element Sayisi Kontrol
devtools.evaluate_expression({
  expression: "document.querySelectorAll('*').length"
})
// 1500+ ise performance sorunu
Computed Styles
devtools.get_computed_styles({
  selector: ".problematic-element",
  properties: ["display", "position", "z-index", "overflow"]
})

JavaScript Debugging

Expression Evaluate Et
devtools.evaluate_expression({
  expression: "JSON.stringify(window.__NEXT_DATA__, null, 2)"
})
State Inspection (React)
devtools.evaluate_expression({
  expression: `
    // React DevTools hook
    const fiber = document.querySelector('#root')._reactRootContainer?._internalRoot?.current;
    JSON.stringify(fiber?.memoizedState, null, 2);
  `
})
Event Listener Kontrolu
devtools.evaluate_expression({
  expression: `
    const el = document.querySelector('.button');
    getEventListeners(el);
  `
})
Breakpoint Yonetimi
// Conditional breakpoint
devtools.set_breakpoint({
  url: "main.js",
  line: 42,
  condition: "user.role === 'admin'"
})

// DOM breakpoint
devtools.set_dom_breakpoint({
  selector: "#dynamic-content",
  type: "subtree-modifications"  // subtree-modifications | attribute-modifications | node-removal
})

Memory Leak Tespiti

Heap Snapshot
devtools.take_heap_snapshot({
  include_summary: true
})
Memory Timeline
devtools.get_memory_info()
// Response: { jsHeapSizeLimit, totalJSHeapSize, usedJSHeapSize }
Memory Leak Tespiti Adimlari
1. Baslangic heap snapshot al
2. Suphelenen aksiyonu yap (navigate, modal ac/kapa)
3. GC tetikle (devtools uzerinden)
4. Ikinci heap snapshot al
5. Comparison view'da "Detached" DOM node'lari ara
6. Retained size buyuk olan objeleri incele
Yaygin Memory Leak Sebepleri
SebepCozum
Event listener temizlenmemisuseEffect return cleanup
setInterval temizlenmemisclearInterval in cleanup
Detached DOMremoveChild + null referans
Closure capturingWeakRef veya scope daralt
Global degisken birikimiScope'a al, gereksizini sil
WebSocket kapatilmamisclose() in cleanup

CSS Debugging

CSS Coverage
devtools.get_css_coverage({
  url_filter: "styles.css"
})
// Kullanilmayan CSS oranini goster
Layout Sorunlari
// Overflow tespiti
devtools.evaluate_expression({
  expression: `
    [...document.querySelectorAll('*')].filter(el => {
      return el.scrollWidth > el.clientWidth || el.scrollHeight > el.clientHeight;
    }).map(el => ({
      tag: el.tagName,
      class: el.className,
      overflow: { w: el.scrollWidth - el.clientWidth, h: el.scrollHeight - el.clientHeight }
    }));
  `
})
Z-index Debugging
devtools.evaluate_expression({
  expression: `
    [...document.querySelectorAll('*')]
      .filter(el => getComputedStyle(el).zIndex !== 'auto')
      .map(el => ({
        tag: el.tagName,
        class: el.className,
        zIndex: getComputedStyle(el).zIndex,
        position: getComputedStyle(el).position
      }))
      .sort((a, b) => Number(b.zIndex) - Number(a.zIndex));
  `
})
CSS Anti-Patterns
Anti-PatternDogru Yol
!important kullanimiSpecificity'yi artir
Inline styleClass/utility kullan
Magic number z-indexz-index scale tanimla
Fixed px font sizerem/em kullan
* selectorSpesifik selector

Lighthouse Audit

Programmatic Lighthouse
devtools.run_lighthouse({
  url: "http://localhost:3000",
  categories: ["performance", "accessibility", "best-practices", "seo"],
  form_factor: "mobile"  // mobile | desktop
})
Lighthouse Skor Hedefleri
KategoriMinimumHedef
Performance7090+
Accessibility80100
Best Practices80100
SEO80100
Accessibility Kontrolleri
devtools.evaluate_expression({
  expression: `
    // Eksik alt text
    [...document.querySelectorAll('img:not([alt])')].length;
  `
})

devtools.evaluate_expression({
  expression: `
    // Eksik label
    [...document.querySelectorAll('input:not([aria-label]):not([id])')].length;
  `
})

Real-Time Browser State Inspection

Page State
devtools.get_page_info()
// Response: url, title, status, loading_state
Tab Yonetimi
// Tum tab'lari listele
devtools.list_targets()

// Tab'a baglan
devtools.attach_to_target({ target_id: "target-123" })
Screenshot
devtools.take_screenshot({
  format: "png",
  quality: 80,
  full_page: true
})
devtools.get_cookies({
  url: "http://localhost:3000"
})
Local/Session Storage
devtools.evaluate_expression({
  expression: `
    ({
      localStorage: Object.keys(localStorage).reduce((acc, key) => {
        acc[key] = localStorage.getItem(key);
        return acc;
      }, {}),
      sessionStorage: Object.keys(sessionStorage).reduce((acc, key) => {
        acc[key] = sessionStorage.getItem(key);
        return acc;
      }, {})
    })
  `
})

Debug Workflow

Sistematik Debug Adimlari
1. REPRODUCE
   - Console log'lari oku (error seviyesi)
   - Network request'leri incele (4xx/5xx)
   - Screenshot al (goruntuyu dogrula)

2. ISOLATE
   - DOM inspect et (element var mi, dogru mu)
   - CSS kontrol et (gorunum sorunu mu)
   - JS evaluate et (state dogru mu)
   - Network filtrele (hangi request basarisiz)

3. DIAGNOSE
   - Performance profil al (yavas mi)
   - Memory kontrol et (leak var mi)
   - Lighthouse calistir (genel skor)

4. FIX & VERIFY
   - Kodu duzelt
   - Browser'da tekrar kontrol et
   - Console temiz mi
   - Network basarili mi
   - Performance iyilesti mi

Entegrasyon: browser-use MCP

Mevcut browser-use MCP ile birlikte kullanim:

browser-use: Sayfa navigasyon, form doldurma, tikla, icerik cek
chrome-devtools: Console, network, performance, DOM, memory analizi

Workflow:
1. browser-use ile sayfaya git
2. chrome-devtools ile console error kontrol
3. chrome-devtools ile network analiz
4. browser-use ile interaksiyon yap
5. chrome-devtools ile performance olc

© vibeeval, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/browser-debugging of vibeeval/vibecosystem.

Open the folder on GitHubat commit 3b763b1

Compare with similar skills

Browser Debugging next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Browser Debugging compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Browser Debugging this skillvibeeval/vibecosystem531—~2.6kAutomated safety check: PassMIT
Extension Puppeteer Debuggingmengxi-ream/read-frog10k—~2kAutomated safety check: NotesGPL-3.0
Chrome Devtools MCPmanagedcode/dotnet-skills486—~2.2kAutomated safety check: PassMIT
Team Frontend Debugcatlog22/Claude-Code-Workflow2.1k—~2.8kAutomated safety check: NotesMIT
Chrome Devtoolstech-leads-club/agent-skills7k—~1.3kAutomated safety check: PassMIT
Steam Cdpjinzhongjia/decky-music122—~1.3kAutomated safety check: PassMIT

Similar skills

  • Extension Puppeteer Debugging

    mengxi-ream/read-frog

    Debug the built Read Frog extension in real Chrome. An agent skill from mengxi-ream/read-frog.

    10k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check: notes
  • Chrome Devtools MCP

    managedcode/dotnet-skills

    Use Chrome DevTools MCP from .NET agents and .NET-focused repos to inspect, debug, and automate Chrome through an MCP client.

    486 GitHub stars~2.2k tokensUpdated today
    DevelopmentAuto-check passed
  • Team Frontend Debug

    catlog22/Claude-Code-Workflow

    Frontend debugging team using Chrome DevTools MCP. An agent skill from catlog22/Claude-Code-Workflow.

    2.1k GitHub stars~2.8k tokensUpdated 3 mo ago
    Testing & QAAuto-check: notes
  • Chrome Devtools

    tech-leads-club/agent-skills

    Browser debugging, performance profiling, and automation via Chrome DevTools MCP.

    7k GitHub stars~1.3k tokensUpdated 17 days ago
    Testing & QAAuto-check passed
  • Steam Cdp

    jinzhongjia/decky-music

    Drive and inspect the running Steam client UI over the Chrome DevTools Protocol (CEF remote debugging, port 8080) — list targets, evaluate JS probes, navigate routes, click elements, dispatch keys…

    122 GitHub stars~1.3k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Browser Setup

    clacky-ai/openclacky

    Configure the browser tool for Clacky. An agent skill from clacky-ai/openclacky.

    1.2k GitHub stars~3.1k tokensUpdated today
    DevelopmentAuto-check: notes

More from vibeeval/vibecosystem

All 144 skills in this repo
  • Agent Benchmark

    vibeeval/vibecosystem

    Framework for measuring and tracking agent response quality over time.

    531 GitHub stars~2.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Differential Review

    vibeeval/vibecosystem

    Security-focused differential code review with blast radius analysis, risk-adaptive depth (DEEP/FOCUSED/SURGICAL), git history correlation, and structured finding format.

    531 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed
  • Factcheck Guard

    vibeeval/vibecosystem

    A skill your agent uses when making any factual claim about the codebase — existence, absence, or behavior.

    531 GitHub stars~2.2k tokensUpdated 1 mo ago
    Auto-check passed
  • Fp Check

    vibeeval/vibecosystem

    Systematic false positive verification for security findings.

    531 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed
  • N8n Workflows

    vibeeval/vibecosystem

    n8n otomasyon workflow'lari. An agent skill from vibeeval/vibecosystem.

    531 GitHub stars~3.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Notepad System

    vibeeval/vibecosystem

    A skill your agent uses when context compression is imminent, when resuming a session, or when preserving critical decisions across long tasks.

    531 GitHub stars~1.7k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Browser Debugging

What does Browser Debugging do?

Chrome DevTools MCP ile browser debugging. An agent skill from vibeeval/vibecosystem. Browser Debugging is an agent skill from vibeeval/vibecosystem. Chrome DevTools MCP ile browser debugging.

When should I use Browser Debugging?

Browser Debugging fits situations like: tasks that involve Debugging; tasks that involve Browser testing.

How do I install Browser Debugging in Claude Code?

Run `npx skills add vibeeval/vibecosystem --skill browser-debugging -a claude-code`. Or copy the skill folder (skills/browser-debugging in vibeeval/vibecosystem) into .claude/skills/browser-debugging in your project. Claude Code loads it when a task matches its description.

How do I install Browser Debugging in Codex?

Run `npx skills add vibeeval/vibecosystem --skill browser-debugging -a codex`. Or copy the skill folder (skills/browser-debugging in vibeeval/vibecosystem) into .agents/skills/browser-debugging in your project. Codex loads it when a task matches its description.

Can I use Browser Debugging in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add vibeeval/vibecosystem --skill browser-debugging -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/browser-debugging, .gemini/skills/browser-debugging, .github/skills/browser-debugging and .opencode/skills/browser-debugging in your project.

What does Browser Debugging need to run?

Going by SKILL.md and its folder, Browser Debugging needs the command-line tools its instructions call (npm and npx). Our summary lists: Node.js.

Does Browser Debugging access the network?

SKILL.md contains no URLs. Its commands use npm and npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Browser Debugging safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Browser Debugging use?

Browser Debugging is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Browser Debugging use?

About 2.6k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Browser Debugging?

Skills that share tags, products or a category with Browser Debugging: Extension Puppeteer Debugging (mengxi-ream/read-frog, 10k stars), Chrome Devtools MCP (managedcode/dotnet-skills, 486 stars), Team Frontend Debug (catlog22/Claude-Code-Workflow, 2.1k stars) and Chrome Devtools (tech-leads-club/agent-skills, 7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Browser Debugging?

vibeeval (a GitHub user) maintains it in vibeeval/vibecosystem, which has 531 GitHub stars. The repository holds 144 skills in this directory. The repository was last updated on August 8, 2026.

Source: vibeeval/vibecosystem on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.