Skip to content
SkillModel-led2,301 tokens in use

seo-shopify

Crawl every page of a Shopify store you administer with its Crawler Access signature, then run the standard SEO audit on the saved crawl files.

31,134 stars on the repository MIT LicenseAgriciDaniel/claude-seo · extensions/shopify/skills/seo-shopify
/plugin marketplace add AgriciDaniel/claude-seo /plugin install claude-seo@agricidaniel-claude-seo
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing seo-shopify costs

87tokens idle
2,301tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetectedwrites filesdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure15/25
  • Examples12/15
  • Output15/15
  • Size13/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 47
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 70

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community72
  • Maturity32
  • Momentum40

seo-shopify replaces the crawl step of the seo-audit skill for Shopify stores. Shopify rate-limits storefront crawling and seo-audit caps link-following at 500 pages. A merchant can mint a Crawler Access signature in the store admin, and the skill replays it to crawl the complete nested sitemap without a cap.

Everything after the crawl, including business detection, scoring and the report files, stays as seo-audit defines it.

What You Get

  • A precheck that returns signed or fallback mode with a reason
  • A resumable crawl of the whole sitemap
  • A summary file with status counts, duplicate titles, thin pages, schema coverage and latency
  • A stratified page sample per template for the content and schema agents
  • The usual full audit report and action plan, with crawl size and any truncation stated

Common Use Cases

  • Audit a large Shopify catalogue without hitting rate limits
  • Check that a signature is valid for the host before a crawl
  • Resume an interrupted crawl of a big store
  • Run an e-commerce audit on the saved crawl data

What Makes It Unique

It lists hard limits first: only stores you administer, one signature per host, roughly 90 days of validity, and robots.txt always respected. It also keeps the credential away from reports and subagents and sends it only to the https origin it was issued for.

Under The Hood

The skill runs two bundled Python scripts through the claude-seo launcher: a precheck that reads .shopify-env, and a crawler that fetches the sitemap tree and pages from the storefront. The signature goes only to its own https host, redirects are recorded and not followed, and sitemap size, response size, concurrency and delay are bounded. It writes summary, sample and page record files to a crawl folder and tells you to keep .shopify-env out of git.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers