Before and after
| Before | After | Why |
|---|---|---|
| Dark Roast, Cold Brew Coffee, Oat Milk | Dark Roast Cold Brew Coffee - Oat Milk | one separator |
| House Blend Coffee (12oz Ground) | House Blend Ground Coffee (12 oz) | type before size, unit format |
| Born To Roam Tee | Born to Roam Tee | title case |
| Ranger Shearling - Brown | Ranger Shearling Boot - Brown | product type added (taken from the store's own product type, "Boots") |
| Studio x Partner Court Sneaker - Bone | Studio x Partner Court Sneaker - Bone | double space |
Swipe the table to see more.
On one 147-product coffee and merch catalogue it changed 13 titles and left 134 alone.
See it run

What it does
A free workflow that gives your whole Shopify catalogue one consistent title pattern and hands you a CSV you can import as is.
It works out the pattern most of your titles already follow. Then it fixes only the titles that break it:
- promo words in titles (
NEW,SALE,Last Call,🔥) - ALL CAPS
- mixed separators (
|,,,–) - sizes that should be variants
- inconsistent units (
12ozand12 oz) - a missing product type
It leaves your product names, brand styling, trademarks and model numbers alone. It also leaves alone titles that are already fine.
Give it a store URL, a collection URL, or a product export CSV.
The evidence
TESTED badge. Run on at least three real examples and scored against a written standard, with the record on file.3 real catalogues, up to 490 products.
Tested on 3 real public Shopify catalogues, up to 490 products. Final scores: 10, 9 and 10 out of 10.
Limits
It changes only the product title. It doesn't write SEO titles, meta descriptions or product descriptions. The paid pack's SEO fixer and description rewriter do those.
Questions
Refunds and contact
If it does not do the job, ask and we refund you within 30 days. Reply to your receipt, or use the contact page.
Which assistants does it work with?
Works in ChatGPT, Claude, Gemini and most other AI assistants: paste in the text, or load the files if your assistant supports them. Setup steps are under For technical users. We run our release tests on Claude. Use your assistant's strongest model: in our tests, a small, fast model added facts that were not in the source data. The helper scripts need Python 3 (standard library only). Reading a live store needs web access; otherwise attach your product export CSV.
For technical users
Using it with an AI assistant
- Unzip the free download. It holds the free skill folders, including
product-title-cleaner, ready-made zips for claude.ai in aclaude-aifolder, and a README. Or copy the folder from GitHub. - Put the
product-title-cleanerfolder where your assistant looks for skills. The generic path is.agents/skills/(ornpx skills addfrom a folder). Tool-specific paths:- Claude Code:
~/.claude/skills/(or.claude/skills/inside one project) - OpenAI Codex, Gemini CLI, Cursor and others:
.agents/skills/or the skills folder their docs name - claude.ai: Customize, Skills, then the plus button, Create skill, Upload a skill, and upload the zip from the
claude-aifolder without unzipping it (code execution must be on in Settings, Capabilities) - ChatGPT or any chatbot: open the skill's
prompt.md, paste it into the chat, then paste your own text or link - Steps for each tool, with links to its official docs: how to install skills
- Claude Code:
- Ask for the job in plain words. The skill loads by itself.
Jobs that go with this
- Quick check: can AI shopping assistants read your store? (Free): Six checks of what a shopper and Google can see on your store, compared with 99 other stores.
- Reply to reviews without promising what you can't give (Free): A reply for every review, matched to its tone, with the risky ones flagged for you.
- Rewrite thin product descriptions without made-up claims ($5): Clearer product descriptions plus the page title and short summary shoppers see in Google, for one product or a whole collection.