Make any AI your personal stylist (the .md trick)
By Bohuslav Poláček · · 4 min read

AI chatbots give famously generic style advice. Ask ChatGPT what to wear and you get a horoscope: "a well-fitted blazer is versatile." Thanks.
The problem is not the AI. It is that the AI knows nothing about you. Fix that with one small file and the advice flips from horoscope to weirdly specific.
The missing ingredient: a machine-readable you
Every Wearly Labs analysis ships with a Markdown (.md) profile. It is a plain text file that contains your style as data:
- Your color season, with verdicts on 50 colors including hex codes.
- Your best white, your version of black, your metal.
- Your body type and a map of cuts: what works, what works with conditions, what to leave on the rack.
- Your preferred styles and your hard no's.
Markdown matters because AI models read it natively. No screenshots to squint at, no login, no API. A text file you attach to a chat. It works in whatever assistant you already use, and it keeps working if you switch.
Set it up once, use it forever
ChatGPT: create a Project called "My Style", attach the .md file to it. Every chat inside the project knows your profile.
Claude: same move. New Project, attach the file, done.
Gemini: create a Gem with the profile pasted in as instructions.
No projects in your app? Just attach the file at the start of a chat. Thirty seconds instead of five.
Then paste this starter prompt:
`` This is my personal style profile from Wearly Labs. Act as my personal shopping assistant. Whenever I share a product, a photo, or ask what to buy, check it against my color palette, my body type and recommended cuts, and my preferred styles. Tell me clearly whether it works for me and why, and suggest a better alternative if it doesn't. Keep my hard no's in mind at all times. ``
Five prompts that earn their keep
- The link check. Paste any product link or screenshot: "Does this work for me?" You get a verdict against your palette and cuts, with reasons, not vibes.
- The fitting room. "I'm in Zara right now. Photo attached, what should I grab?" Works surprisingly well from a messy changing-room mirror shot of the rack.
- The capsule pack. "Five pieces for a week in Lisbon in June, from my palette, mix and match."
- The closet audit. Photograph a shelf: "Which of these earn their place, which don't, and why?" Brace yourself.
- The gift decoder. Attach someone else's profile: "A birthday sweater for her, under 100 euro, three options." Two profiles in one household pays for itself fast.
What it will not do
Honesty round. The AI cannot see how a specific garment sits on your specific body from a product photo, so treat fit predictions as educated guesses. And it only knows what is in the profile: if your report says coral is a top color, the AI will keep pushing coral until you tell it you already own four coral things. It is a very keen assistant.
The quiet part: no lock-in
Most style apps want a subscription between you and every answer. The .md profile is the opposite bet. It is your file. It lives in your inbox, works in any AI, and does not need us after purchase. We would rather be the analysis you buy once than the app you forget to cancel.
FAQ
Which AI works best?
All the major ones read it fine. Use whichever you already pay for or the free tier you like. The profile does the heavy lifting, not the model.
Can I edit the file?
Yes, it is plain text. Add "no wool, it itches" or update your sizes. Your edits become part of every future answer.
Does it work with voice assistants?
In apps where a Project holds your file, yes: ask out loud in the store and the answer respects your profile.
Is my data safe in there?
The profile contains color codes, cut names, and style tags. No photos, no measurements you did not choose to share. Read it yourself, it is a text file.

