chrome-developer

Develop Chrome MV3 extensions with service workers and WebGPU ML pipelines.

16|2|Updated Mar 10, 2026
One-click install
npx skills add https://github.com/jshearin01/agent-skills --skill chrome-developer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: chrome-developer
Source: https://github.com/jshearin01/agent-skills/tree/main/chrome-developer
Command: npx skills add https://github.com/jshearin01/agent-skills --skill chrome-developer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @huggingface/transformers, @mlc-ai/web-llm, idb, onnxruntime-web, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Chrome developers face a fragmented learning curve when integrating MV3, WebGPU, WebNN, WASM, IndexedDB, and related browser capabilities into production-grade extensions and apps.

Core Features & Use Cases

  • Advanced Chrome platform mastery: MV3 service workers, Offscreen Documents, declarativeNetRequest, and performance profiling.
  • Client-side ML workflows: WebGPU/WebNN pipelines, WebAssembly inference, and in-browser model caching.
  • End-to-end extension development: references, patterns, and debugging strategies for chrome extensions, DevTools workflows, and extension distribution.

Quick Start

Bootstrap a minimal MV3 Chrome extension that uses a service worker and WebGPU-based in-browser ML to validate setup.

Frequently Asked Questions about chrome-developer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build an MV3 Chrome extension with a service worker?

Building an MV3 Chrome extension requires a service worker for background logic and specific manifest configurations. This Skill provides concrete patterns and code samples for service workers, offscreen documents, and declarativeNetRequest.

Can I run WebGPU compute tasks and in-browser ML pipelines inside a Chrome extension?

Yes, you can run WebGPU compute tasks and in-browser ML pipelines within Chrome extensions. This Skill provides patterns for WebGPU/WebNN pipelines, WebAssembly inference, and in-browser model caching.

What is the best way to cache ML models locally using IndexedDB in Chrome?

Caching ML models locally in Chrome uses IndexedDB stores for persistent client-side data. This Skill offers references for implementing IndexedDB stores and integrating them with in-browser ML frameworks.

Does WebLLM work with WebGPU for on-device AI workflows in Chrome?

WebLLM works with WebGPU for executing on-device AI workflows in Chrome. This Skill includes dependencies like @mlc-ai/web-llm and onnxruntime-web to establish WebGPU compute tasks and on-device AI workflows.

How do I use offscreen documents for DOM operations in MV3 extensions?

Offscreen documents handle DOM operations and API interactions that service workers cannot perform in MV3 extensions. This Skill provides concrete patterns and code samples for implementing offscreen documents.

What are the limitations of using service workers in Chrome MV3 extensions?

Service workers in Chrome MV3 extensions have lifecycle limitations, becoming inactive when idle, which impacts persistent background tasks. This Skill provides debugging strategies and references to navigate these constraints.