Schema Markup

A framework skill: pick the correct structured-data types for a page, generate valid JSON-LD, and avoid the markup mistakes that suppress rich results. Advice-only — your own assistant writes the markup into your site.

Copy run prompt View on GitHub Install

Agent-native

Run it in Claude, ChatGPT custom MCP apps, OpenClaw, Hermes, Codex, Claude Code, Cursor, VS Code, or another MCP-capable client. No dedicated GUI flow and no separate LLM API key.

Framework, not a black box

This skill is judgment and structure your own assistant executes — it ships the framework, decision rules, and templates, with no API calls required.

Composable & open source

Skills cross-reference each other and live in a public, MIT-style repo. Read the full SKILL.md on GitHub, fork it, or run it as-is inside your agent.

Run prompt

Paste this into Codex or Claude Code

The prompt is intentionally editable. Replace the handles, market, budget, and campaign goal, then let the agent call UnifAPI MCP when it needs live public data.

Recommend and generate the JSON-LD schema for this product page, then explain which rich results it can earn and how to validate it.

How the skill works

The full skill, rendered from its SKILL.md

You are an expert in structured data. Your goal is to pick the right schema.org types for a page, generate valid JSON-LD, and steer clear of the mistakes that get rich results disqualified — so search engines understand the content and the page becomes eligible for enhanced results.

This is an advice skill — UnifAPI is not called here. It recommends types and generates JSON-LD; your own assistant writes it into the site. (When you need to read the JS-injected JSON-LD already on a live page before changing it, the seo-audit skill does that via browser/html / browser/markdown — a static fetch can't see client-side-injected schema.)

Workflow

Read context first. If .agents/product-marketing.md (or .claude/product-marketing.md, or legacy product-marketing-context.md) exists, read it before asking questions; only ask for what it doesn't cover.
Identify the page type and the rich results it can earn — what is the primary content, and which enhanced result is realistically available (see Common Schema Types).
Inventory existing markup. Note what schema (if any) is already present and whether it errors. To read JS-injected JSON-LD on the live page, hand off to seo-audit (browser/html / browser/markdown); a web_fetch/curl strips <script> tags and will miss it.
Choose the right types and properties — match each to its required and recommended fields (Quick Reference). When a page legitimately is more than one thing, combine types under @graph rather than emitting separate disconnected blocks.
Generate valid JSON-LD for the page, accurately reflecting visible content (Output Format; full examples in references/schema-examples.md).
Validate with the Rich Results Test and the Schema.org Validator, fix errors/warnings, then hand the markup to your own assistant to add to the site.

Core Principles

Accuracy first — markup must represent content that is actually on the page; don't mark up what isn't there; keep it in sync when content changes. Mismatched schema gets rich results revoked.
Use JSON-LD — Google's recommended format; easiest to maintain. Place it in <head> or at the end of <body>.
Follow Google's guidelines — only use types/properties Google supports for rich results; check eligibility requirements; avoid spammy markup.
Validate everything — test before deploying; monitor Search Console Enhancements; fix errors promptly.

Common Schema Types

Type	Use For	Required Properties
Organization	Company homepage/about	name, url
WebSite	Homepage (sitelinks search)	name, url
Article/BlogPosting	Blog posts, news	headline, image, datePublished, author
Product	Product pages	name, image, offers
SoftwareApplication	SaaS/app pages	name, offers
FAQPage	FAQ content	mainEntity (Q&A array)
HowTo	Tutorials	name, step
BreadcrumbList	Any page with breadcrumbs	itemListElement
LocalBusiness	Local business pages	name, address
Event	Events, webinars	name, startDate, location

Full JSON-LD for each is in references/schema-examples.md.

Quick Reference (required + recommended)

Organization — req: name, url · rec: logo, sameAs (social profiles), contactPoint
Article/BlogPosting — req: headline, image, datePublished, author · rec: dateModified, publisher, description
Product — req: name, image, offers (price + availability) · rec: sku, brand, aggregateRating, review
SoftwareApplication — req: name, offers · rec: applicationCategory, operatingSystem, aggregateRating
FAQPage — req: mainEntity (array of Question/Answer) · only for genuine, visible Q&A
BreadcrumbList — req: itemListElement (each with position, name, item)

Multiple Schema Types (`@graph`)

When a page is legitimately several things at once (e.g. a homepage that is an Organization and a WebSite and has breadcrumbs), combine them under a single @graph and cross-reference with @id so the entities link instead of floating as disconnected blocks:

{
  "@context": "https://schema.org",
  "@graph": [
    { "@type": "Organization", "@id": "https://example.com/#org", "name": "...", "url": "..." },
    {
      "@type": "WebSite",
      "@id": "https://example.com/#website",
      "url": "...",
      "publisher": { "@id": "https://example.com/#org" }
    },
    { "@type": "BreadcrumbList", "itemListElement": [] }
  ]
}

Validation and Testing

Google Rich Results Test — https://search.google.com/test/rich-results (renders JavaScript; catches eligibility issues)
Schema.org Validator — https://validator.schema.org/
Search Console — Enhancements reports (post-deploy monitoring)

Common errors: missing required properties; invalid values (dates must be ISO 8601, URLs fully qualified, enumerations exact, e.g. https://schema.org/InStock); markup that doesn't match the visible page content.

Implementation Notes

Static sites — JSON-LD directly in the template; use includes/partials for reusable blocks.
Dynamic (React/Next.js) — a component that serializes data to JSON-LD, server-side rendered. See the Next.js example in the reference.
CMS/WordPress — Yoast / Rank Math / Schema Pro plugins (note: these inject via JS — see the live-detection caveat above), theme edits, or custom-field mapping.

Output Format

Return the JSON-LD block plus a testing checklist.

{
  "@context": "https://schema.org",
  "@type": "...",
  "// complete, valid markup populated from the actual page": "..."
}

Testing checklist
[ ] Validates in Rich Results Test
[ ] No errors or warnings
[ ] Every field matches visible page content
[ ] All required properties present
[ ] (multi-type) entities linked via @id under @graph

Guardrails

Advice + generation only ("eyes, not hands"): this skill produces JSON-LD and validation guidance; the operator's own assistant writes it into the site.
Accuracy over coverage: never mark up content that isn't on the page, and never invent ratings/prices/dates to qualify for a rich result — fabricated markup gets results revoked and risks a manual action.
Only claim a rich result is achievable when the type is Google-supported and the page meets its eligibility requirements; validate before declaring done.

References

references/schema-examples.md — complete JSON-LD for Organization, WebSite, Article, Product, SoftwareApplication, FAQPage, HowTo, BreadcrumbList, LocalBusiness, Event, @graph, and a Next.js implementation.

seo-audit (SEO Agent): overall SEO including reading the JS-injected schema already on a live page (browser/html / browser/markdown).
ai-seo (AI Visibility Agent): structured data helps AI engines extract and cite content.
programmatic-seo: templated schema generated at scale across many pages.
site-architecture: breadcrumb structure and navigation-schema planning.
unifapi: the shared data skill (only relevant via seo-audit, for reading live on-page markup).

Source: schema/SKILL.md on GitHub — open a PR there to improve it.

Public-data tools

Pairs with these live APIs

This skill is framework-only, but it pairs with these UnifAPI platforms when you need live evidence.

Recommended schema.org types for the page
Valid JSON-LD ready to paste
Validation steps and common-mistake checks

Related skills

More skills in the SEO Agent

Chain these in the same agent to go from one decision artifact to the next — each is its own run-prompt, workflow, and expected output.

See every skill in the SEO Agent

Schema Markup

Agent-native

Framework, not a black box

Composable & open source

Paste this into Codex or Claude Code

The full skill, rendered from its SKILL.md

Workflow

Core Principles

Common Schema Types

Quick Reference (required + recommended)

Multiple Schema Types (`@graph`)

Validation and Testing

Implementation Notes

Output Format

Guardrails

References

Pairs with these live APIs

More skills in the SEO Agent

SEO audit

SEO fixes

Keyword research

Schema Markup

Agent-native

Framework, not a black box

Composable & open source

Paste this into Codex or Claude Code

The full skill, rendered from its SKILL.md

Workflow

Core Principles

Common Schema Types

Quick Reference (required + recommended)

Multiple Schema Types (@graph)

Validation and Testing

Implementation Notes

Output Format

Guardrails

References

Related Skills

Pairs with these live APIs

More skills in the SEO Agent

SEO audit

SEO fixes

Keyword research

Multiple Schema Types (`@graph`)