Build with AI

Import your wardrobe with AI.

Adding clothes one by one is slow. Instead, hand your whole wardrobe to any AI and let it do the typing. Copy the prompt below, tell the AI what you own — a list, a description, or photos — and paste its answer straight back here. Then, once your clothes are in, the same chat can build you outfits and write care guides tailored to your setup — that's round two, below.

1 · Copy the prompt

Paste this into ChatGPT, Claude, Gemini — any chat AI — then tell it about your wardrobe. List your clothes, describe them, or attach photos. It replies with a JSON file built to Drobe's format.

You are helping me import my wardrobe into Drobe (drobe.day), a private wardrobe-planning app. Your job is to turn my clothes into ONE JSON file I can paste straight into Drobe's importer.

HOW TO WORK
- If I haven't given you my wardrobe yet, ask for it. I might paste a list, describe things in prose, or share photos — work from whatever I give you, one JSON item per garment.
- For each garment, fill in every field you can reasonably infer from the item type and typical materials (a wool overcoat is warm, wind-resistant and fairly formal; a linen shirt is light, airy and for hot days). If you genuinely can't tell a field, just leave it out — never invent wild values.
- One entry per distinct garment. Collapse several identical pieces into a single entry (you can note the count in the name, e.g. "Black Socks ×5"); for the same style in different colours, give each a shared "groupName" so they group into one tile.
- Reply with ONLY the JSON, inside a single code block, with no explanation before or after. I will copy it verbatim.

OUTPUT SHAPE
{
  "app": "wardrobe-planner",
  "version": 1,
  "items": [ /* one object per garment — see EACH ITEM */ ]
}

EACH ITEM (only id, name, category and colours are required):
{
  "id": "navy-merino-crew",          // REQUIRED, must be UNIQUE across the file. lowercase-hyphenated.
  "name": "Navy Merino Crew",        // REQUIRED. Short, human name.
  "category": "knitwear",            // REQUIRED. Exactly one of the CATEGORIES below.
  "brand": "Uniqlo",                 // optional
  "subcategory": "crew neck",        // optional free text — but see SUBCATEGORY HINTS.
  "groupName": "Merino Crew",        // optional — shared label for the same garment in different colours (they collapse into one tile)
  "colours": [                       // REQUIRED. First entry is the main colour.
    { "hex": "#20304a", "role": "primary" },
    { "hex": "#d8d2c4", "role": "accent" }
  ],
  "materials": "100% merino wool",   // optional free text
  "formality": 3,                    // optional, 1 (very casual) to 5 (formal)
  "weight": "mid",                   // optional: light | mid | heavy
  "breathability": "medium",         // optional: low | medium | high (airflow — linen/mesh = high)
  "silhouette": "regular",           // optional: slim | regular | relaxed | oversized
  "pattern": "solid",                // optional: solid | texture | graphic | print | stripe | check
  "role": "workhorse",               // optional: workhorse | statement | base | layer | accent
  "tempMinC": 2,                     // optional, coldest outdoor temp (Celsius) it's comfortable in
  "tempMaxC": 16,                    // optional, warmest outdoor temp (Celsius) it's comfortable in
  "rainproof": 0,                    // optional, 0 (none) to 3 (fully waterproof)
  "windproof": 1,                    // optional, 0 (none) to 3 (fully windproof)
  "hasLeather": false,               // optional boolean
  "leatherTone": "brown",            // optional: brown | black | tan (only when hasLeather is true)
  "notes": "A gift — wears soft."    // optional free text
}

CATEGORIES (pick the single best fit — use these exact values):
  headwear   - hats, caps, beanies
  outerwear  - coats, jackets, shells, parkas, macs
  midlayer   - overshirts, fleeces, gilets, light zip-ups
  knitwear   - jumpers, cardigans, hoodies, sweatshirts
  top        - t-shirts, shirts, polos, blouses
  bottom     - trousers, jeans, chinos, shorts, skirts
  footwear   - shoes, boots, trainers, sandals, loafers
  gloves     - gloves, mittens
  accessory  - belts, scarves, watches, jewellery, sunglasses, ties
  bag        - bags, backpacks, holdalls, totes
  underwear  - socks, boxers, base layers, vests

SUBCATEGORY HINTS (so Drobe places items in the right outfit slot):
- Socks: use category "underwear" AND subcategory "socks".
- Belt: category "accessory", subcategory "belt".
- Scarf: category "accessory", subcategory "scarf".
- Watch or bracelet: category "accessory", subcategory "watch" (or "bracelet").
- Necklace: category "accessory", subcategory "necklace".
- Sunglasses: category "accessory", subcategory "sunglasses".

COLOURS
- Give a hex for every distinct colour. "role" is "primary" (the dominant colour — list it FIRST), "accent" (a clear secondary colour), or "trim" (piping, soles, buttons, contrast stitching). Most items just have one primary. Drobe works out the colour's name, family and shade from the hex automatically, so you only need the hex and the role.

TEMPERATURE
- tempMinC / tempMaxC are the outdoor temperature range (Celsius) the item is comfortable to wear in. Rough guide: t-shirt 16 to 34, light jumper 6 to 18, heavy coat -12 to 8, jeans -6 to 24, shorts 20 to 40. Give sensible ranges; skip them if unsure.

CARE (optional — add it when you know or can infer the fabric):
  "cleaning": {
    "machineTempC": 30,              // 30, 40 or 60, or null if not machine washable
    "cycle": "normal",              // normal | delicate | wool | hand_wash
    "dryMethod": "air_dry",         // tumble_low | air_dry | flat_dry | drip_dry
    "iron": "medium",               // none | low | medium | high
    "dryCleanOnly": false,
    "washWith": "darks",            // darks | lights | similar | alone
    "washFrequencyWears": 3,        // wash after roughly this many wears
    "specialNotes": "Wash inside out to protect the print."
  }

RULES
- Never include images, photo URLs, timestamps, or createdAt/updatedAt — Drobe adds those. Items show as a coloured tile until I add a photo myself.
- Keep every "id" unique across the whole file.
- Output the JSON only, in one code block. No preamble, no sign-off.

2 · Paste the result & import

Copy the JSON the AI gives back and paste it here. Everything happens in your browser — nothing is uploaded. Round-two replies (outfits, care guides) paste into this same box — use “Add to my wardrobe”.

3 · Round two — outfits & care

With your clothes imported, stay in the same chat — the AI already knows your whole wardrobe, so now you can put it to work. Each prompt below starts with a “my situation” block: edit it before sending. That's the part people miss — the AI can tailor everything to you: the occasions you actually dress for, whether you own a steamer or an iron, how you dry and store things. Paste each reply back into the box above with “Add to my wardrobe” selected.

Ask for outfit ideas

A second opinion on what goes together — complete looks across the temperature range, tagged by occasion. They land on your Outfits page, ready to wear or tweak.

Now build me a set of outfits from the wardrobe you just catalogued.

MY SITUATION (I'll edit this): I mostly dress for [casual everyday / office / evenings out]. My style leans [minimal / classic / sporty / bold]. Occasions I actually need covered: [errands, work, dinners, walks…].

Suggest complete, coherent looks — combinations that genuinely work together in colour, formality and warmth. Spread them across the temperature range (proper cold looks through to hot-weather ones) and my occasions. Reply with ONLY this JSON in one code block:

{
  "app": "wardrobe-planner",
  "version": 1,
  "items": [],
  "outfits": [
    {
      "name": "Weekend Errands",          // REQUIRED, unique, short
      "items": ["navy-merino-crew", "stone-chinos", "brown-suede-loafers"],  // the item ids (or exact names) from my wardrobe file
      "tempMinC": 6,                       // coldest temp the look suits (°C)
      "tempMaxC": 16,                      // warmest temp
      "tags": ["casual", "everyday"],      // lowercase occasion tags
      "notes": "Roll the chinos; no socks with the loafers."   // one styling tip
    }
  ]
}

RULES
- Only reference items that exist in my wardrobe (the ids/names from the file you produced earlier).
- Keep "items" as the empty array shown — my clothes are already imported.
- 8–15 outfits is a good number. Every outfit needs at least a top/bottom/footwear spine (or equivalent).
- JSON only, one code block, no commentary.

Ask for care guides — tailored to your setup

Generic care advice assumes kit you may not own. Tell the AI you've got a steamer but no iron, a drying rack but no tumble dryer, and every guide comes back written for your reality. Works best when your items have materials filled in — the AI writes to the fabric. Guides attach to each item and show on its page and in Care.

Now write care guides for my wardrobe, tailored to MY setup — not generic advice.

MY SETUP (I'll edit this before sending):
- Washing: [machine at home / shared machine / launderette] — cycles I use: [normal, delicate, wool]
- Finishing: [steamer only — no iron / iron only / both / neither]
- Drying: [rack indoors / outdoor line / tumble dryer / flat space for knits]
- Storage: [wardrobe with hangers + drawers / open rail / vacuum bags for off-season]

Group my items by fabric and care needs (all the merino together, the suede shoes together, etc.) and write one guide per group. Tailor every instruction to my setup above — if I only have a steamer, tell me how to steam, not iron; if I have no tumble dryer, don't suggest one. Use the materials you know from my wardrobe; where material is unknown, say what to check on the label. Reply with ONLY this JSON in one code block:

{
  "app": "wardrobe-planner",
  "version": 1,
  "items": [],
  "careGuides": [
    {
      "title": "Merino Knitwear",         // REQUIRED
      "items": ["Navy Merino Crew"],      // the EXACT item names from my wardrobe this guide covers
      "body": "**Washing.** Cool wool cycle with wool detergent. **Drying.** Reshape and dry flat on the rack — never hang wet. **Finishing.** A quick pass with the steamer relaxes creases. **Storage.** Fold in the drawer; cedar nearby for moths."
    }
  ]
}

RULES
- Cover EVERY item — each item name appears in exactly one guide.
- Item names must match my wardrobe exactly.
- Keep "items" (top level) as the empty array shown — my clothes are already imported.
- Plain paragraphs; wrap section labels like **Washing.** in double asterisks. JSON only, one code block.

What a file looks like

Everything the importer understands in one file: two items — a shirt and boots — plus the outfit and care guide that round two produces. On an item only id, name, category and colours are required; everything else is optional. Outfits reference items by id (or exact name); care guides by name.

{
  "app": "wardrobe-planner",
  "version": 1,
  "items": [
    {
      "id": "white-oxford-shirt",
      "name": "White Oxford Shirt",
      "category": "top",
      "brand": "Kamakura",
      "subcategory": "oxford shirt",
      "colours": [{ "hex": "#f3f1ea", "role": "primary" }],
      "materials": "100% cotton oxford",
      "formality": 3,
      "weight": "mid",
      "breathability": "medium",
      "pattern": "solid",
      "role": "workhorse",
      "tempMinC": 8,
      "tempMaxC": 26,
      "cleaning": {
        "machineTempC": 40,
        "cycle": "normal",
        "dryMethod": "drip_dry",
        "iron": "medium",
        "washWith": "lights",
        "washFrequencyWears": 2
      }
    },
    {
      "id": "brown-suede-chelsea",
      "name": "Brown Suede Chelsea Boots",
      "category": "footwear",
      "brand": "Loake",
      "subcategory": "chelsea boot",
      "colours": [
        { "hex": "#6b4a2f", "role": "primary" },
        { "hex": "#1c1c1c", "role": "trim" }
      ],
      "materials": "Suede upper, leather sole",
      "formality": 3,
      "hasLeather": true,
      "leatherTone": "brown",
      "tempMinC": -2,
      "tempMaxC": 18,
      "rainproof": 1,
      "notes": "Brush after wet days; re-proof each autumn."
    }
  ],
  "outfits": [
    {
      "name": "Smart Autumn Casual",
      "items": ["white-oxford-shirt", "brown-suede-chelsea"],
      "tempMinC": 6,
      "tempMaxC": 18,
      "tags": ["smart-casual"],
      "notes": "Shirt tucked, sleeves rolled once."
    }
  ],
  "careGuides": [
    {
      "title": "Suede Footwear",
      "items": ["Brown Suede Chelsea Boots"],
      "body": "**Brushing.** Use a suede brush to lift the nap once dry. **Wet days.** Let them dry away from heat, stuff with paper, then brush. **Protection.** Re-apply suede protector spray each autumn."
    }
  ]
}

Polish it after

An AI gets you most of the way in seconds; a minute of tidying makes the wardrobe truly yours. Open any item to:

  • Add a photo. Imported pieces show as a clean colour tile. On the item's page, replace it with a real photo — upload one or paste an image URL — and Drobe re-samples the colour straight from it.
  • Refine the colour. The AI's colour is a close guess from a hex. Use the colour picker on the edit page to set the exact shade, or add the accent and trim colours a description tends to miss — it sharpens colour matching and the palette strips.
  • Check the details. Temperature range, formality and category drive every outfit and care suggestion. Nudge anything that reads off on the edit page.

What Drobe understands

Categories

headwear
hats, caps, beanies
outerwear
coats, jackets, shells, parkas
midlayer
overshirts, fleeces, gilets
knitwear
jumpers, cardigans, hoodies
top
t-shirts, shirts, polos
bottom
trousers, jeans, shorts, skirts
footwear
shoes, boots, trainers, sandals
gloves
gloves, mittens
accessory
belts, scarves, watches, jewellery, sunglasses
bag
bags, backpacks, totes
underwear
socks, boxers, base layers

Socks use underwear with subcategory socks; belts, scarves, watches and sunglasses use accessory with a matching subcategory, so Drobe drops each into the right outfit slot.

Optional attributes

formality
1 (very casual) – 5 (formal)
weight
light · mid · heavy
breathability
low · medium · high
silhouette
slim · regular · relaxed · oversized
pattern
solid · texture · graphic · print · stripe · check
role
workhorse · statement · base · layer · accent
rainproof / windproof
0 (none) – 3 (fully)
tempMinC / tempMaxC
comfortable outdoor range, in °C
colour role
primary · accent · trim

Good to know

Do I need photos?

No. A list or a plain description is enough. AI-added items show as a clean colour tile — you can add a photo to any of them later from the item's page.

Outfits and care notes too?

Yes — as round two. Once your clothes are imported, two follow-up prompts in the same chat get you ready-to-wear outfits and care guides written for your setup. Import each reply with “Add”.

Is anything uploaded?

No. Drobe is local-first: parsing and importing happen entirely in this browser, and your wardrobe never leaves your device. Only your conversation with the AI happens on their service.

Add or replace?

“Add” merges the items in alongside what you already have (matching ids update in place). “Replace” wipes the wardrobe first — take a backup from Settings if you're unsure.

Big wardrobe?

Do it in batches — ask the AI for 20–30 items at a time and import each with “Add”. Long replies can get cut off, and because ids are stable, re-importing a batch never creates duplicates.

Which AI works?

Any capable chat model — ChatGPT, Claude, Gemini, and others. The prompt spells out the exact format, so the model doesn't need to know anything about Drobe.