- Home
- Skills
- Frontend & Web Apps
- nex-chrome-extension-pipeline
More screenshots
Works with the AI Agents you already use
Nex Chrome Extension Pipeline
Turns a one-line idea into a complete Manifest V3 Chrome extension using the no-build vanilla pattern behind 23 shipped extensions.
$79
nex-chrome-extension-pipeline
Example session with this skill installed
I want to build an extension that scans the current page for email addresses and lets me export them to a CSV file from a popup.
- Read your context and instructions
- Compiled the nex-chrome-extension-pipeline
- Generated the data export
I'll scaffold this as a Scraper Archetype. Here is your nex-email-scanner project:
manifest.json: IncludesactiveTabandstoragepermissions.content.js: Scans DOM for regex-matched emails.popup.html: Dark-themed UI with "Scrape" and "Download CSV" buttons.
popup.html
CSV · data export
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
What it does
- Scaffolds the canonical MV3 layout from a one-line idea: manifest.json, background service worker, content script, popup (HTML, CSS, JS), options page, PRIVACY-POLICY.html, STORE-LISTING.txt, and icons at 16, 48, and 128 px generated with the included Pillow script.
- Classifies your idea into one of seven archetypes (overlay, scraper, autofill, side-panel-app, devtools, content-rewriter, action-on-click) and shapes files and permissions accordingly.
- Teaches the no-build dev loop: chrome://extensions, Load unpacked, edit and reload, with no npm install and no bundler.
- Covers the packaging pipeline: zip for the Chrome Web Store, crx for self-hosting, plus the store-listing checklist and permission justifications.
- Ships the real source of a shipped extension (nex-accent) in assets/reference/ as the working layout to copy from.
Why use this
Manifest V3 has enough sharp edges (stateless service workers, permission review, no remote code) that a first extension usually dies in setup. This pipeline encodes the vanilla JS plus HTML plus CSS pattern that shipped 23 extensions in production at Nex AI, so every decision from archetype to store submission is already made. The dev loop is edit, reload, test; a working extension is a day of work, not a week.
See it in action
Prompt:
I have an idea for a browser extension: one click saves the current tab's title and URL to my Notion. Where do I start?
Result:
Archetype: 7 (action-on-click). No popup needed. nex-tab-to-notion/ manifest.json # permissions: activeTab, storage background.js # chrome.action.onClicked -> Notion API call settings.html # Notion API key + database ID settings.js # stored in chrome.storage.sync icons/icon16.png icon48.png icon128.png PRIVACY-POLICY.html # matches the manifest permissions STORE-LISTING.txt # short description, single-purpose statement Dev loop: 1. chrome://extensions -> Developer mode -> Load unpacked 2. Edit any file, click the reload arrow on the card 3. zip -r nex-tab-to-notion.zip nex-tab-to-notion/ and upload
Use cases
- Scaffold a new MV3 extension from scratch without a build step.
- Pick the right archetype and minimum-viable permissions for an idea.
- Package and submit an existing extension to the Chrome Web Store, with privacy policy and listing text.
- Run a rapid-ship cadence: one small extension per day.
Known limitations
- Chrome-first: Firefox and Safari extensions need different polyfills, tooling, and store flows.
- Manifest V3 only; it does not generate MV2.
- The vanilla no-build pattern is deliberate; if you want a framework popup, only the side-panel archetype includes a build-step migration recipe.
FAQ
What exactly is in the download?
SKILL.md, README.md, assets/reference/ with the full nex-accent source, five reference docs (the-seven-archetypes.md, manifest-v3-permissions.md, service-worker-lifecycle.md, store-submission-checklist.md, 21-extensions-cadence.md), manifest.json, CHANGELOG.md, and LICENSE.md.
Which agents does it work with?
Claude Code, Claude Cowork, Cursor, Codex CLI, and any agent that reads the SKILL.md format.
Do I need anything else?
Chrome with Developer mode, and Python with Pillow if you use the icon generator. A Chrome Web Store developer account only when you publish.
Does it help me choose permissions?
Yes. The archetype decides the permission set, and the skill enforces minimum-viable permissions (activeTab over <all_urls> where possible) with justifications ready for store review.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Frontend & Web Apps.
- Chrome/Manifest V3 focus only (not Firefox/Safari)
- No built-in React/Vite support (Vanilla JS focus)
- Requires Python/Pillow for local icon generation script
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 3 months ago
Permissions
No special permissions declared or detected