Create and manage Shopify pages, blog posts, navigation menus, redirects, and SEO metadata via the Admin API or browser automation. Use whenever the user wants to add a page to a Shopify store, write a Shopify blog post, update the storefront navigation, manage redirects, or tune SEO metadata on a Shopify site.
npx skills add https://github.com/jezweb/claude-skills --skill shopify-content
Create and manage Shopify store content — pages, blog posts, navigation menus, and SEO metadata. Produces live content in the store via the Admin API or browser automation.
read_content, write_content scopes (use shopify-setup skill)read_online_store_navigation, write_online_store_navigation scopes| Content Type | API Support | Method |
|-------------|-------------|--------|
| Pages | Full | GraphQL Admin API |
| Blog posts | Full | GraphQL Admin API |
| Navigation menus | Limited | Browser automation preferred |
| Redirects | Full | REST Admin API |
| SEO metadata | Per-resource | GraphQL on the resource |
| Metaobjects | Full | GraphQL Admin API |
curl -s https://{store}/admin/api/2025-01/graphql.json \
-H "Content-Type: application/json" \
-H "X-Shopify-Access-Token: {token}" \
-d '{
"query": "mutation pageCreate($page: PageCreateInput!) { pageCreate(page: $page) { page { id title handle } userErrors { field message } } }",
"variables": {
"page": {
"title": "About Us",
"handle": "about",
"body": "<h2>Our Story</h2><p>Content here...</p>",
"isPublished": true,
"seo": {
"title": "About Us | Store Name",
"description": "Learn about our story and mission."
}
}
}
}'
Page body accepts HTML. Keep it semantic:
<h2> through <h6> for headings (the page title is <h1>)<p>, <ul>, <ol> for body text<a href="..."> for linksShopify blogs have a two-level structure: Blog (container) > Article (post).
Find or create a blog:
{
blogs(first: 10) {
edges {
node { id title handle }
}
}
}
Most stores have a default blog called "News". Create articles in it:
mutation {
articleCreate(article: {
blogId: "gid://shopify/Blog/123"
title: "New Product Launch"
handle: "new-product-launch"
contentHtml: "<p>We're excited to announce...</p>"
author: { name: "Store Team" }
tags: ["news", "products"]
isPublished: true
publishDate: "2026-02-22T00:00:00Z"
seo: {
title: "New Product Launch | Store Name"
description: "Announcing our latest product range."
}
image: {
src: "https://example.com/blog-image.jpg"
altText: "New product collection"
}
}) {
article { id title handle }
userErrors { field message }
}
}
Navigation menus have limited API support. Use browser automation:
https://{store}.myshopify.com/admin/menusAlternatively, use the GraphQL menuUpdate mutation if the API version supports it:
mutation menuUpdate($id: ID!, $items: [MenuItemInput!]!) {
menuUpdate(id: $id, items: $items) {
menu { id title }
userErrors { field message }
}
}
URL redirects use the REST API:
curl -s https://{store}/admin/api/2025-01/redirects.json \
-H "Content-Type: application/json" \
-H "X-Shopify-Access-Token: {token}" \
-d '{
"redirect": {
"path": "/old-page",
"target": "/new-page"
}
}'
SEO fields are on each resource (product, page, article). Update via the resource's mutation:
mutation {
pageUpdate(page: {
id: "gid://shopify/Page/123"
seo: {
title: "Updated SEO Title"
description: "Updated meta description under 160 chars."
}
}) {
page { id title }
userErrors { field message }
}
}
Query back the content to confirm:
{
pages(first: 10, reverse: true) {
edges {
node { id title handle isPublished createdAt }
}
}
}
Provide the admin URL and the live URL for the user to review:
https://{store}.myshopify.com/admin/pageshttps://{store}.myshopify.com/pages/{handle}For simple content (About, Contact, FAQ), use pages. For structured, repeatable content (team members, testimonials, locations), use metaobjects — they have typed fields and can be queried programmatically.
Every blog post should have:
Use publishDate on articles for scheduled publishing. Pages publish immediately when isPublished: true.
For many pages (e.g. location pages, service pages), use a loop with rate limiting:
for page in pages_data:
create_page(page)
sleep(0.5) # Respect rate limits
references/content-types.md — API endpoints, metaobject patterns, and browser-only operationsGenerate marketing screenshots of your app using Playwright. Use when the user wants to create screenshots for Product Hunt, social media, landing pages, or documentation.
| Capture desktop, app windows, or pixel regions across OS platforms. Useful for marketing screenshots, design reviews, and bug reports.
| Generate marketing screenshots with Playwright. Useful for landing-page hero shots, App Store screenshots, and changelog visuals.
Audit cross-platform attribution, conversion definitions, reporting windows, GA4, AdServices and AdAttributionKit, MMPs, browser and server events, offline conversions, and platform reconciliation. Use for attribution audit, attribution models, conversion windows, requests to add or total Meta and Google conversions, incompatible reporting-window aggregation, GA4 attribution, MMP review, AppsFlyer, Adjust, Branch, Singular, or cross-platform discrepancies.
Expert blueprint for idle/clicker games including big number handling (mantissa + exponent system), exponential growth curves (cost_growth_factor 1.15x), generator systems (auto-producers), offline progress calculation, prestige systems (reset for permanent multipliers), number formatting (K/M/B suffixes, scientific notation). Use for incremental games, idle games, or cookie clicker derivatives. Trigger keywords: idle_game, big_number, exponential_growth, generator_system, offline_progress, prestige_system, number_formatting.
Generate marketing screenshots of your app using Playwright. Use when the user wants to create screenshots for Product Hunt, social media, landing pages, or documentation.
Generate marketing screenshots of your app using Playwright. Use when the user wants to create screenshots for Product Hunt, social media, landing pages, or documentation.
Control the user's real Safari browser on macOS using AppleScript and screencapture. This skill should be used when the user asks to interact with Safari, browse websites, read web pages, automate browser tasks, take screenshots of web content, or when any task would benefit from seeing or interacting with what's in their browser. Triggers on keywords like "safari", "browser", "web page", "open tab", "screenshot the page", "read this site", "browse", "click on", "fill in the form".
Take jezweb/shopify-content from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.