AskWisely.ai

Product Descriptions at Catalogue Scale

Write 200 product descriptions that do not all sound identical.

Bulk generation produces 200 descriptions with the same three adjectives. Search engines and customers both notice.

That is the gap this drop closes. It is a content & writing skill built for Kimi, and it takes about ten minutes to set up the first time. After that it runs in under a minute.

Who should use it

E-commerce teams launching or migrating a catalogue.

How it works

The skill file does five things, in this order.

1. Feed the spec sheet. Real attributes. Made-up benefits are how you get returns.

2. Define the buyer per category. Who buys this and what they are comparing it against.

3. Vary structure deliberately. Rotate through four opening patterns so the catalogue reads human.

4. Bake in the search terms. Naturally placed, including the Arabic query variants.

5. Generate the structured data. Product schema fields output alongside the copy.

What comes back

Descriptions in EN and AR, meta titles, and Product schema fields per SKU.

The mistake to avoid

Give it four approved example descriptions written by a human and tell it to rotate between their structures. Style transfer from real examples beats any adjective instruction.

Running it

Paste the prompt block into a new Kimi chat and attach your files in the same message. Kimi's long context means you should upload everything at once rather than in batches, splitting the input is what causes it to lose cross-references between documents.

Where this fits

On its own, one skill saves an hour a week. The compounding happens when three or four of them run in sequence on the same input, the same transcript that produces a scope of work also produces the follow-up email and the project brief. That is the point at which it stops being a prompt and starts being an internal tool. If you want that wired into the systems your team already uses, that is the work 67 Digital does.

In the file

Write product descriptions for this catalogue.

Rules:
- Every benefit must trace to a real attribute in the spec sheet. Never invent
  materials, origins, certifications, or performance claims.
- Rotate between these four opening structures so no two consecutive products
  read the same: sensory detail / the problem it solves / a use occasion /
  a direct spec statement.
- 60 to 90 words each. Arabic version written natively, not translated.
- Include: meta title (under 60 chars), meta description (under 155),
  and Product schema fields (name, description, material, color, size).

Match the tone of these approved examples: {paste 3-4 human-written examples}

<catalogue>{CSV}</catalogue>

Get it built

Reading is free. Building is what changes the numbers.

AskWisely is published by 67 Digital, an AI and automation team in Dubai. We take the skills on this site and turn them into systems that run inside your business, connected to the tools your team already uses.

AI agents that actually ship

We build the agent, wire it to your tools, and hand you the keys.

Automation on your stack

n8n, Make, or custom. Connected to the CRM and inbox you already use.

Team training in Arabic & English

Half-day sessions that leave your team using AI on Monday.

Talk to 67 Digital →