Claude AI

Schema Markup Audit Claude Skill

This skill audits a website's structured data and produces an actionable SEO report. It extracts JSON-LD, Microdata, and RDFa from pages, validates the markup against schema.org and Google rich result requirements, and finds missing, invalid, or incomplete schema, then recommends concrete fixes.

What The Skill Checks

  • Invalid JSON-LD parse errors, missing required properties for declared types, and key page types with no schema at all, each reported with the exact page, schema type, and property.
  • Missing recommended properties for rich results, schema that describes content not actually on the page, conflicting or duplicate schema blocks, and deprecated types or properties.
  • Missing Organization and WebSite schema on the homepage, mixed JSON-LD and Microdata duplicates of the same entity, and missing optional enhancements like sameAs and BreadcrumbList.

How The Skill Is Packaged

The skill follows the standard Claude Agent Skill structure: a SKILL.md file with YAML frontmatter and workflow instructions, a references/ folder with the full audit check definitions and report template, and a scripts/ folder with Python scripts that extract structured data from pages and validate the resulting inventory. Every report can be exported to a shareable Word .docx or a flat .csv of findings via the bundled md_to_docx.py and findings_to_csv.py scripts. Install it with npx claude-seo-skills install schema-markup-audit, or copy the skill folder into your Claude skills directory; Claude invokes it automatically when a request matches its description.

Skill Files

Every file in the skill is embedded below directly from the Claude-SEO-Skills repository, so you can review exactly what the skill instructs Claude to do before installing it.

SKILL.md

The skill definition: frontmatter, inputs to collect, the six-step audit workflow, and the resources the skill relies on.

Audit Checks Reference (references/audit-checks.md)

Full definitions, severities, and rationale for every audit check, plus required and recommended properties per schema type.

Report Template (references/report-template.md)

The output structure the skill follows when writing the final audit report.

Schema Extractor Script (scripts/extract_schema.py)

Crawls a live site or local HTML folder within the configured page limits and extracts all JSON-LD, Microdata, and RDFa into a JSON inventory.

Schema Validator Script (scripts/validate_schema.py)

Runs the audit checks against the schema inventory JSON and outputs the structured audit report data.