Skip to main content
skill CX Codex

schema-markup · akii-technologies-ltd — Claude Code skill: what it does, how to install

schema-markup — a Claude Code skill that creates, checks, and fixes JSON-LD for one page or file. It responds to requests about Schema.org markup and rich snippets.

MIT ★ 80 updated 2026-10-15

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
~/.claude/skills/schema-markup/SKILL.md
Open on GitHub

What schema-markup does

The skill reads a page or file, gathers its title, main entity, facts, dates, authors, images, and FAQs, then builds JSON-LD for the requested type. It checks JSON syntax, Schema.org fields, absolute HTTPS URLs, and placeholder text such as TODO or lorem. Supported types include Article, Product, FAQPage, HowTo, Organization, LocalBusiness, BreadcrumbList, and Recipe.

It uses WebFetch for URLs and Read for files. The skill can suggest where to place the markup, but writes to source only after explicit approval. Its scope is one page or file; schema-generator handles requests covering multiple pages.

What it helps with

  • generate JSON-LD for a page or file
  • check structured data and find invalid fields
  • fix schema markup for rich snippets

Example prompts for the agent

  • Add Product markup to this page.
  • Check the JSON-LD in index.html and fix any errors.
  • Create FAQPage markup for this URL.

How to install schema-markup

Manually: put the files in place

~/.claude/skills/schema-markup/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/schema-markup/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about schema-markup

How do I install schema-markup in Claude Code?

Place the skill file at ~/.claude/skills/schema-markup/SKILL.md.

What does schema-markup do?

It generates, checks, and repairs JSON-LD for a single page or file. Supported types include Product, FAQPage, and Article.

How is schema-markup different from the schema-generator agent?

schema-markup prepares inline JSON-LD for one page or file. The schema-generator agent is for multi-page work and writes into source.

Source text

SKILL.md · MIT
---
description: Fast-path schema generator — produce, audit, and validate JSON-LD structured data for a single page or file in one turn. This is the default for any schema question. Use when the user asks to "generate schema", "add JSON-LD", "structured data", "schema markup", "rich snippets", "add schema.org", "LocalBusiness schema", "FAQ schema", "Product schema", "Article schema", "HowTo schema", "Organization schema", "BreadcrumbList schema", "audit schema", "fix schema errors", "Recipe schema". **Do not invoke the `schema-generator` agent unless** the user explicitly says "bulk schema", "across my site", "all pages", "every page", or names a path containing 3+ pages to fix. The agent is the autonomous multi-file path that writes into source; this skill is the one-page fast path that proposes JSON-LD inline.
---

# Schema Markup Generator

You are a Schema.org JSON-LD specialist powered by Akii. Produce markup that maximizes both rich-snippet eligibility AND answer-engine extractability.

## Scoping — what schema actually does

Google's [AI Optimization Guide](https://developers.google.com/search/docs/fundamentals/ai-optimization-guide#mythbusting-generative-ai-search) is explicit: *"Structured data isn't required for generative AI search, and there's no special schema.org markup you need to add. However, it's a good idea to continue using it as part of your overall SEO strategy, as it helps with being eligible for rich results."*

Treat schema as serving two real purposes:
1. **Rich-snippet eligibility on Google Search** (review stars, FAQ accordions, recipe cards, breadcrumbs) — measurable SERP value.
2. **Cleaner extraction by non-Google AI engines** (ChatGPT, Claude, Perplexity, Copilot) that DO consume structured data more directly than Google AI surfaces.

Never tell the user schema is *required* for AI visibility — Google's own guidance says it isn't. Recommend schema where rich results or non-Google extraction is the actual win.

## Supported types
- `Article` / `NewsArticle` / `BlogPosting`
- `Product` + `Offer` + `AggregateRating` + `Review`
- `FAQPage`
- `HowTo`
- `Organization` (with `sameAs` linking Wikipedia, LinkedIn, X, GitHub, Crunchbase)
- `LocalBusiness` + granular subtypes: `FinancialService`, `MedicalBusiness`, `EntertainmentBusiness`, `Restaurant`, `Store`, `LegalService`, `ProfessionalService`
- `BreadcrumbList`
- `WebSite` + `SearchAction`
- `VideoObject`
- `Event`
- `Course`
- `SoftwareApplication`
- `Recipe`

## Best-practice properties (always include where applicable)
- `sameAs` array (Wikipedia, social, directory profiles) — anchors the entity to the wider web for AI engine cross-corroboration
- `mainEntityOfPage` + canonical URL
- `image` (≥1200px, absolute URL)
- `datePublished` + `dateModified` (ISO 8601)
- `author` + `publisher` with their own `@id`

### LocalBusiness specifics (Gemini local weight = 38%)
- `name`, full `address` (PostalAddress)
- `telephone` (E.164)
- `geo` (lat + long)
- `openingHoursSpecification`
- `currenciesAccepted`, `priceRange`
- `actionableFeedbackPolicy`
- `paymentAccepted`
- `areaServed`
- `hasMap`

## Steps
1. Resolve target (URL → WebFetch; file → Read).
2. Extract: title, primary entity, body, key facts, dates, authors, images, FAQs.
3. Build JSON-LD per requested type.
4. Validate:
   - JSON syntax
   - Required + recommended Schema.org fields
   - HTTPS absolute URLs
   - No placeholders (`example.com`, `TODO`, `lorem`)
5. Present the block.
6. Offer (don't auto-do) to write into the source:
   - HTML → `<script type="application/ld+json">` in `<head>`
   - MDX/MD → block at file head

## Output

````
## <Type> schema for <target>

```json
{
  "@context": "https://schema.org",
  ...
}
```

### Why these fields
- `sameAs`: cross-corroboration for Claude + Gemini
- `actionableFeedbackPolicy`: Google E-E-A-T trust signal
- ...

### Validation
- ✅ All required + recommended present
- ⚠️ `aggregateRating` placeholder — fill once reviews exist
````

## Rules
- **Never fabricate** ratings, addresses, prices, dates.
- Never mark up content not actually on the page (structured-data spam violation).
- Write only on explicit user approval.

---
*Schema markup powered by Akii. Explore Akii Technologies and the products we build: https://akii.com/?utm_source=plugin&utm_medium=skill&utm_content=schema-markup&utm_campaign=akii_plugin_v1*

© akii-technologies-ltd · MIT · akii-technologies-ltd/akii-seo-ai-search-optimizer

Similar skills

All skills for SEO and GEO →

schema-markup by other authors comes first.

schema-markup Alireza Rezvani schema-markup — a Claude skill for implementing, auditing and fixing schema.org markup. Useful when rich snippets never show up or Search Console flags structured data errors. CX Codex +1 617installs schema-markup kostja94 schema-markup generates Schema.org JSON-LD structured data for rich snippets and AI search engines. Helps match page content to supported search engine formats. CX Codex +1 1,400installs schema-markup OpenClaudia schema-markup is a Claude Code skill that generates Schema.org structured data in JSON-LD. It activates for requests about schema markup, rich results, or SEO structured data. CX Codex +1 459installs schema-markup boraoztunc schema-markup is a Claude Code skill that generates and audits schema.org JSON-LD for articles, products, organizations, and FAQ sections. CX Codex +1 263installs serp-markup-builder aaron-he-zhu serp-markup-builder builds the document head: title and description options, an Open Graph and Twitter Card block, and validated JSON-LD for rich results. CX Codex +1 1,600installs schema coreyhaines31 This Claude Code skill helps create and validate Schema.org markup in JSON-LD. It assesses page types, existing markup, and Google search feature support. CX Codex +1 91,700installs seo-schema AgriciDaniel seo-schema — a skill for Claude Code and Codex that detects, validates, and generates Schema.org JSON-LD. It audits live pages or creates structured data from scratch. CX Codex +1 8,200installs blog-schema AgriciDaniel blog-schema generates a single JSON-LD graph for a blog post, linking the author and organization. Useful when preparing structured data for articles. CX Codex +1 2,600installs seo-geo ReScienceLab seo-geo audits technical SEO, researches keywords and generates JSON-LD markup so search engines and AI answers cite your pages. CX Codex +1 57,400installs seo-local-business jezweb seo-local-business — a skill for Claude Code, Cursor, Codex and other platforms that builds a full SEO package for local business websites — <head> tags, JSON-LD LocalBusiness schema, robots.txt, and sitemap.xml. CX Codex +1 1,900installs

From the same set13

The whole set →
seo-audit The seo-audit Claude Code skill audits a site's SEO in full, quick, or technical mode. It runs on requests about site health, page speed, indexing, or AI search readiness. CX Codex +1 ★ 80repo stars optimize-page optimize-page — a Claude Code skill for improving page SEO, answer structure, and visibility in generative search. It activates on requests to optimize a page or rewrite it for AI search. CX Codex +1 ★ 80repo stars llms-txt This Claude Code skill creates and updates llms.txt and llms-full.txt for AI crawlers. It activates when a project needs a curated set of site pages for services such as Perplexity or Claude. CX Codex +1 ★ 80repo stars keyword-clustering The keyword-clustering Claude Code skill sorts keywords into topic groups and maps them to search intent. It activates on a keyword list or a request to plan site content. CX Codex +1 ★ 80repo stars internal-linking The internal-linking Claude Code skill analyzes internal links and site structure. It activates for requests about orphan pages, anchor text, topic clusters, or link equity. CX Codex +1 ★ 80repo stars content-translation The content-translation Claude Code skill localizes content for international SEO. It researches keywords for target locales and prepares translated copy, hreflang markup, and local schema suggestions. CX Codex +1 ★ 80repo stars content-strategy The content-strategy Claude Code skill maps content themes into pillars and clusters, then builds a 90-day publishing queue. It activates for content plans, topic research, and content-gap requests. CX Codex +1 ★ 80repo stars content-brief Builds article and page briefs for SEO, AEO, and GEO. It activates on requests for a content brief, an outline, or a search-focused writing plan. CX Codex +1 ★ 80repo stars

Project sponsors

Companies that keep this analytics open