Extension Dev logo

Extension Dev

Community
quangpl
extension-dev

Detect Chrome extension framework/stack, find proper docs, implement features, and debug across service worker, content script, and popup contexts.

Overview

Publisherquangpl
Repositorybrowser-extension-skills
Skill nameextension-dev
Stars
65
Forks
10
Bundled files
5
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by quangpl on GitHub. Read the source before you install it.

Installation

Install the Extension Dev AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/quangpl/browser-extension-skills/tree/main/skills/extension-dev
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/quangpl/browser-extension-skills.git /tmp/browser-extension-skills
mkdir -p .claude/skills
cp -r /tmp/browser-extension-skills/skills/extension-dev .claude/skills/extension-dev
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Extension Dev in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Extension Dev on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Extension Dev is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Extension Dev

🚀 Upgrade to Premium Get the Premium version at https://app.extensionbooster.net/dashboard/services/extension-ai-kit

Detect the stack, find docs, implement the feature, debug. Do NOT just explain — execute the workflow.

Workflow (Execute This)

Step 1: Detect framework and UI stack

Run detection (see references/framework-detection.md):

bash
ls wxt.config.ts crxjs.config.ts vite.config.ts manifest.json 2>/dev/null
cat package.json | grep -E '"wxt|crxjs|crxjs|react|vue|svelte"'
File foundFramework
wxt.config.tsWXT
package.json has crxjsCRXJS
vite.config has @crxjsCRXJS
manifest.json in root, none aboveVanilla

Step 2: Fetch framework docs and style guides

Use docs-seeker skill or web search to find proper docs for the detected stack.

Extension framework docs:

UI framework docs (fetch based on detected framework):

Code style guides (always follow):

Step 3: Implement the feature

Follow framework conventions:

  • WXT: add entrypoints in entrypoints/, configure wxt.config.ts
  • CRXJS: add pages/tabs/contents, use CSUI for content UI
  • CRXJS: standard Vite + manifest-based setup
  • Vanilla: edit manifest.json, add JS files directly

For Chrome API usage, check references/chrome-api-quick-reference.md. For messaging between contexts, check references/message-passing-patterns.md.

Step 4: Debug

See references/debugging-guide.md for context-specific DevTools access.

Quick map:

ContextHow to inspect
Service workerchrome://extensions → "inspect" link
Content scriptPage DevTools → Console → select extension context
PopupRight-click popup → Inspect
Options / Side panelOpen page → F12

Step 5: Hot reload setup

FrameworkCommandNotes
WXTpnpm devFull HMR, auto-reloads extension
CRXJSpnpm devHMR for popup/content
CRXJSvite devVite HMR
VanillaManualReload at chrome://extensions

Chrome API Quick Reference (Top 20)

APIPurposePermission
chrome.tabsQuery, create, update tabstabs
chrome.windowsManage browser windowswindows
chrome.storage.localPersist data locallystorage
chrome.storage.syncSync data across devicesstorage
chrome.storage.sessionSession-only datastorage
chrome.actionToolbar icon, popup, badge—
chrome.contextMenusRight-click menu itemscontextMenus
chrome.sidePanelSide panel UIsidePanel
chrome.notificationsDesktop notificationsnotifications
chrome.scriptingInject scripts/CSS into pagesscripting
chrome.runtimeMessaging, lifecycle, manifest—
chrome.webRequestIntercept/modify network requestswebRequest
chrome.declarativeNetRequestBlock/redirect requests declarativelydeclarativeNetRequest
chrome.webNavigationTrack page navigation eventswebNavigation
chrome.identityOAuth2, Google Sign-Inidentity
chrome.alarmsSchedule periodic tasksalarms
chrome.commandsKeyboard shortcutscommands
chrome.cookiesRead/write cookiescookies
chrome.historyBrowser history accesshistory
chrome.bookmarksRead/write bookmarksbookmarks

Message Passing (Quick Pattern)

One-time (popup → service worker):

ts
// sender
const response = await chrome.runtime.sendMessage({ type: "GET_DATA" });

// receiver (background)
chrome.runtime.onMessage.addListener((msg, sender, reply) => {
  if (msg.type === "GET_DATA") {
    reply({ data: "..." });
    return true;
  }
});

Content script → service worker: same pattern, return true for async. Tab-targeted (background → content):

ts
chrome.tabs.sendMessage(tabId, { type: "ACTION" });

Full patterns in references/message-passing-patterns.md.


References

  • references/framework-detection.md — detect WXT/CRXJS/CRXJS/vanilla, dev commands
  • references/framework-styleguides.md — UI framework docs, style guides, extension framework docs
  • references/chrome-api-quick-reference.md — 30+ APIs with permissions and doc links
  • references/message-passing-patterns.md — all messaging patterns with TypeScript examples
  • references/debugging-guide.md — DevTools per context, common errors, tips

Related Skills

  • extension-create — scaffold new extension with WXT
  • extension-manifest — generate/validate manifest.json
  • extension-test — write and run extension tests
  • extension-analyze — analyze existing extension codebase

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Extension Dev AI skill do?

Detect Chrome extension framework/stack, find proper docs, implement features, and debug across service worker, content script, and popup contexts.

Why use Extension Dev on TypingMind?

Because you install it once and use it with any model. Extension Dev is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Extension Dev in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/quangpl/browser-extension-skills/tree/main/skills/extension-dev. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Extension Dev?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Extension Dev?

As many as you like. As long as a model supports skills, you can use Extension Dev with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Extension Dev AI skill free?

Yes. It is published on GitHub by quangpl under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇