| name | seo-content |
| description | Shopify content quality audit sub-skill. Evaluates content depth, keyword coverage, thin pages, and content freshness signals. Use when user runs /seo content or when seo-audit delegates content checks.
|
SEO Content Audit
Content quality sub-skill for Shopify stores. Evaluates thin pages, keyword coverage, and content freshness.
Category weight: Content = 20% (0.20) of overall SEO Health Score.
Quick Reference
| Command | What it does |
|---|
/seo content <url> | Run content quality checks against a Shopify store |
| (via seo-audit) | seo-audit spawns audit-content agent directly — this sub-skill is not used |
Context Intake
This skill is invoked directly via /seo content <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-content 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-content via Task tool with prompt:
"Run content SEO audit on {store_url}. Crawl data at {cwd}/seo-audit-crawl.json"
- Agent writes
seo-content-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-content agent applies severity levels locked by the quality gates.
Key inherited gates (for reference, not redefinition):
- Thin content < 300 words on product/collection pages = High
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 thresholdsreferences/drinkware-keywords.md — Primary keyword list for content coverage check (head terms: custom tumblers, custom drinkware, personalized tumblers, promotional drinkware)references/benchmarks.md — Content benchmarks for scoring context (optional, load only when needed for threshold context)
The agent loads its own references during execution.
