schema-markup

Trigger phrases

Phrases that activate this skill when typed to Claude Code:

• schema markup
• structured data
• JSON-LD
• rich snippets
• FAQ schema

What it does

schema-markup is a Claude Code skill from Corey Haines’s marketing-skills repo. It turns Claude into a structured-data implementer who picks the right schema type per page (FAQ, Product, Article, HowTo, Review, Breadcrumb, Organization, ItemList for comparisons) and produces JSON-LD that validates against Google’s Rich Results Test. The skill activates when you mention “schema markup”, “structured data”, “JSON-LD”, “rich snippets”, or “FAQ schema”.

The output of a session is a JSON-LD block per page type: validated against schema.org and Rich Results, with required and recommended properties populated, ready to drop into the page head or layout component.

When to use it

Reach for it when:

• You have FAQs, products, or articles and aren’t getting rich results
• You’re optimizing for AI Overviews and ChatGPT — schema is a lever there too
• You inherited schema that was wrong or out-of-date

When not to reach for it:

• The page itself isn’t ranking — schema amplifies, doesn’t create rank
• Your CMS injects schema automatically; check before duplicating

Install

The skill is distributed via Corey Haines’s marketing-skills repo. Install via the repo’s recommended path — copy the schema-markup SKILL.md into your project’s .claude/skills/schema-markup/ directory, or use the repo’s plugin install if you’ve set it up.

Once installed, the skill activates on the trigger phrases above. The first time it runs, it will check for .agents/product-marketing-context.md (or .claude/product-marketing-context.md) — populating that file with your product context first dramatically improves output quality across all of Haines’s marketing skills.

What a session looks like

A typical session has three phases:

1. Schema-type selection. Per page type, the right schema(s). Comparison pages get ItemList, FAQs get FAQPage, products get Product + AggregateRating, blog gets Article + author Person.
2. JSON-LD generation. Required and recommended properties populated, no fabricated reviews, no spammy AggregateRating without real data — schema spam is penalized.
3. Validation step. A copy-pastable URL to Google’s Rich Results Test, plus the warnings and recommendations from validation.

The discipline that makes it work: schema you can defend. Fake reviews and inflated AggregateRating values eventually trigger manual actions; the skill writes only what you can substantiate.

Receipts

Honest reporting on what schema-markup produces and where it has limits:

Where it works well:

• The schema-per-page-type matrix saves the “which schema for this page?” decision fatigue
• Validation step catches errors before they ship
• AI extraction (ChatGPT, Perplexity citations) benefits noticeably from clean schema

Where it backfires:

• Schema is necessary but not sufficient — bad content with great schema still won’t rank
• Some CMS platforms inject conflicting schema; manual audit needed before deploy

Pattern that works: start with FAQ and Article schema on existing top-traffic pages. They’re the easiest to implement and produce visible rich-result wins fastest.

Source and attribution

Originally written by Corey Haines. The canonical SKILL.md and any supporting files live in the schema-markup folder of his marketing-skills repository.

License: MIT. You can install, adapt, and redistribute the skill, with attribution preserved.

This page documents the skill from a practitioner’s perspective. For the formal spec and any updates, defer to the source repo.