| name | seo-schema |
| description | Shopify structured data audit sub-skill. Validates JSON-LD presence and correctness for Product, Organization, BreadcrumbList, and FAQ schema types. Use when user runs /seo schema or when seo-audit delegates schema checks.
|
SEO Schema Audit
Structured data sub-skill for Shopify stores. Validates JSON-LD presence and field completeness
for Product, Organization, BreadcrumbList, and FAQPage schema types. Aggregates results by check
across pages and reports a category score.
Category weight: Schema = 15% (0.15) of overall SEO Health Score.
Quick Reference
| Command | What it does |
|---|
/seo schema <url> | Run structured data checks against a Shopify store |
| (via seo-audit) | seo-audit spawns audit-schema agent directly — this sub-skill is not used |
Context Intake
This skill is invoked directly via /seo schema <url>.
When invoked directly:
- If store URL not provided, read
~/.claude/skills/seo/profiles/karved.json and use preset
- Run
python3 ~/.claude/skills/seo/scripts/crawl_store.py <url> to generate crawl data before proceeding
- Save output as
seo-audit-crawl.json in the current directory
- Then proceed to Execution Logic
Note: When invoked by seo-audit, this sub-skill is NOT used — seo-audit spawns the audit-schema agent directly.
Execution Logic
- If invoked directly (not from seo-audit):
a. If store URL not provided, read
~/.claude/skills/seo/profiles/karved.json and use preset
b. Run python3 ~/.claude/skills/seo/scripts/crawl_store.py <url> to generate seo-audit-crawl.json
- Spawn agent
audit-schema via Task tool with prompt:
"Run schema SEO audit on {store_url}. Crawl data at {cwd}/seo-audit-crawl.json"
- Agent writes
seo-schema-findings.md — present results to user
All check definitions, scoring logic, and output format are defined in the agent.
If invoked by seo-audit, this sub-skill is NOT used — seo-audit spawns the agent directly.
Quality Gates
This skill inherits all quality gates from seo/SKILL.md. Do NOT redefine or soften them. The audit-schema agent applies severity levels locked by the quality gates.
Key inherited gates relevant to schema checks (for reference, not redefinition):
- Missing Product schema on product pages = High (quality gate floor — actual check uses Critical for required field validation when Product schema is entirely absent, High when required offer fields are missing)
Reference Files
Load these on-demand as needed — do NOT load all at startup.
Path resolution: All references are installed at ~/.claude/skills/seo/references/.
references/scoring-system.md — Weighted scoring algorithm, severity multipliers (Critical=5.0, High=3.0, Medium=1.5, Low=0.5), grade thresholds. Schema category weight = 0.15.references/schema-templates.md — JSON-LD templates with field validation checklists for Product, Organization, BreadcrumbList; Shopify Liquid field sources for each schema property
The agent loads its own references during execution.
