By az9713
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
Use this to skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to `--slim` mode (MCP configuration).
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions "largest contentful paint", "page load speed", "CWV", or wants to improve how fast their hero image or main content renders.
Diagnoses and resolves memory leaks in JavaScript/Node.js applications. Use when a user reports high memory usage, OOM errors, or wants to analyze heapsnapshots or run memory leak detection tools like memlab.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
This is a personal learning fork of ChromeDevTools/chrome-devtools-mcp. It adds a plain-English tutorial and a real-world demo that walk you through the tool from zero — no prior knowledge of Chrome, DevTools, MCP, or the CLI required.
New here? Start with
demo-health-check/↓
If terms like MCP server, Chrome DevTools Protocol, performance trace, or Lighthouse feel unfamiliar — you're not alone, and you're in the right place.
This fork adds two self-contained demos — together they cover 26 of 29 chrome-devtools-mcp tools.
demo-health-check/ — Website health audit (CNN.com)| File | What it is | Start here if… |
|---|---|---|
demo-health-check/quickstart.md | A hands-on project: produce a real Website Health Report using 7 of the 29 tools, with 6 copy-paste prompts | You want to learn by doing |
demo-health-check/cnn-case-study/report.md | A complete health report for CNN.com — Core Web Vitals, 52 third-party vendors, 3,906ms of layout thrashing, cache issues, console errors | You want to see what output looks like |
demo-health-check/cnn-case-study/walkthrough.md | Step-by-step annotated walkthrough: every tool used, every input/output, every obstacle — the full story behind the report | You want to understand how it works |
demo-health-check/reference.md | Complete reference for all 29 tools, architecture, connection modes, daemon/CLI, and configuration | You want the full picture |
demo-shopping/ — Agentic shopping workflow (saucedemo.com)An AI agent runs a complete e-commerce purchase flow autonomously: login → browse → multi-tab comparison → cart → mobile emulation → checkout → order confirmation. Covers the 18 interaction tools not used in Demo 1.
| File | What it is |
|---|---|
demo-shopping/report.md | Findings: broken telemetry, React event quirk, heap memory baseline, $140.34 order |
demo-shopping/walkthrough.md | Full annotated walkthrough of all 18 tools with inputs, outputs, and obstacles |
demo-shopping/order-confirmation.png | Screenshot of "Thank you for your order!" |
demo-shopping/memory-before-checkout.heapsnapshot | 6.7 MB V8 heap dump — open in Chrome DevTools → Memory |
use-cases.md50+ agentic workflows across QA, performance, SEO, e-commerce, research, security, and personal productivity — with the specific tools each one uses and why CDP beats alternatives.
chrome-devtools-mcp gives your AI assistant (Claude, Gemini, Cursor, Copilot…) the ability to control and inspect a real Chrome browser. Instead of just reading and writing text files, your AI can:
You interact with it through plain English — "Check the performance of this page" — and the AI figures out which of the 29 tools to call.
The demo was designed for someone who has never opened Chrome DevTools, never used an MCP server, and has only just started using an AI coding assistant. Every concept is explained from first principles before it is used.
chrome-devtools-mcp lets your coding agent (such as Gemini, Claude, Cursor or Copilot)
control and inspect a live Chrome browser. It acts as a Model-Context-Protocol
(MCP) server, giving your AI coding assistant access to the full power of
Chrome DevTools for reliable automation, in-depth debugging, and performance analysis.
npx claudepluginhub az9713/chrome-devtools-mcp --plugin chrome-devtools-mcpProduction-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Full agentic layer framework implementing the Codebase Singularity concept - enabling AI agents to operate your codebase autonomously through planning, building, reviewing, and fixing workflows. Implements Class 1-3 with orchestration capabilities.
Thread-Based Engineering examples - demonstrates Base, Parallel, Chained, Fusion, Big, Long, and Zero-Touch thread patterns for agentic coding
Design fluency for frontend development. 1 skill with 23 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Plugin that includes the Figma MCP server and Skills for common workflows