agentleFS
Sign inStart free
Sheldon-desouzaSheldon-desouza/claude-shopify-seo/skills/shopify-seo-check/SKILL.md

shopify-seo-check

Skill0 starsChanged 2 months agoMITView on GitHub

Audit Shopify product, collection or blog copy against search, AI-assistant and brand-accuracy rules without changing it. Use for: check this copy, is this SEO friendly, will AI find this, audit my product description, review my blog post.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the draft, change nothing, and report what holds and what does not.

    line 8
  2. Very specific:

    Do not rewrite anything. That is /shopify-seo fix.

    line 27
  3. Distinctive:

    Do not invent a numeric score.

    line 28
  4. Distinctive:

    Do not flag house style as an error.

    line 29
  5. Distinctive:

    Do not pad the report. If three things are wrong, report three things.

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Check

Read the draft, change nothing, and report what holds and what does not.

  1. Load brand/<brand>.json. Every factual claim in the draft is checked against it.
  2. Work through reference/checks.md in order. Each item returns pass, warn or fail.
  3. Where you can, verify against the live store rather than the draft's own claims. If the Shopify MCP is connected, read the real price, stock state and variants instead of trusting the text.

Reporting

Group findings under the three audiences: the shopper, search, AI assistants. Within each, lead with fails, then warns. For every finding give the line it came from and what to do about it.

State the fact-check separately and first, because it outranks everything else. A description that scores well on every SEO measure and names the wrong fabric is worse than useless.

Finish with one sentence on whether this is publishable as it stands.

Do not

  • Do not rewrite anything. That is /shopify-seo fix.
  • Do not invent a numeric score. Counts of pass, warn and fail are enough.
  • Do not flag house style as an error. If the brand profile says the owner writes long sentences, long sentences are not a finding.
  • Do not pad the report. If three things are wrong, report three things.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free