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

shopify-seo-fix

Skill0 starsChanged 2 months agoMITView on GitHub

Rewrite Shopify product, collection or blog copy to fix what a check found, preserving the owner's voice and inventing nothing. Use for: optimise this, rewrite it, fix the copy, make it better for search, make it AI friendly.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Run the check first if it has not been run in this conversation.

    line 10
  2. Very specific:

    Read the voice block in the brand profile before writing a word.

    line 18
  3. Distinctive:

    If a line is already good, keep it verbatim.

    line 21
  4. Distinctive:

    Every number, material, size, lead time and provenance claim must trace to the brand profile or the live store.

    line 26

≈ “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

Fix

Repair what failed. Leave everything else alone.

  1. Run the check first if it has not been run in this conversation.
  2. Fix in this order: factual errors, then clarity for the shopper, then search, then AI citability. A search improvement that muddies the sentence is not an improvement.
  3. Change as little as possible. If one clause fixes a finding, change one clause.
  4. Re-run the check on your own output. Report what moved and what did not.

Preserving voice

Read the voice block in the brand profile before writing a word. Match its rhythm, its vocabulary and its level of formality. Where the owner has a phrase they use for something, use their phrase.

If a line is already good, keep it verbatim. Rewriting working copy to prove effort is the most common failure of this kind of tool.

Facts

Every number, material, size, lead time and provenance claim must trace to the brand profile or the live store. If the draft asserts something you cannot verify, do not repeat it and do not quietly drop it either. Flag it and ask.

Adding a true, specific fact usually beats any wording change. Assistants cite specifics and skip adjectives.

Output

Return the full revised copy, not a patch. Then a short list of what changed and why, one line each. Then anything still failing, stated plainly. Then stop and wait.

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