Inject Brand Voice Into Bulk Product Copy
Make AI-written descriptions sound like your brand, not a generic catalogue
Your catalogue reads correctly but sounds like everyone else's. The details are accurate but the personality is missing, and customers scroll past without connecting to your brand.
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
Content managers who already generate product descriptions at scale but struggle with flat, interchangeable tone
How it works
The skill file does five things, in this order.
1. Find three descriptions you love. Pull examples you have written or approved that capture your brand voice perfectly.
2. Label what makes them yours. Note specific patterns like sentence rhythm, humor level, technical depth, or how you address the customer.
3. Write your voice rules as constraints. Turn observations into instructions the model can follow, like sentence length limits or banned phrases.
4. Test on five diverse products. Run the prompt on items from different categories to see if voice holds or breaks down.
5. Refine the examples you feed in. Swap weak reference descriptions for stronger ones until output consistency improves.
What comes back
A reusable prompt that produces descriptions customers recognize as unmistakably yours, even across hundreds of SKUs
The mistake to avoid
Voice breaks down faster than facts when you scale. Audit a random sample of 20 outputs weekly, not just the first batch, and update your constraints when you spot drift.
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
You write product descriptions for {brand_name}, a {industry} brand serving {target_audience} in {market}.
Our brand voice follows these rules:
- {voice_rule_1}
- {voice_rule_2}
- {voice_rule_3}
- {voice_rule_4}
We never: {banned_phrases_or_patterns}
Here are three approved descriptions that represent our voice perfectly:
1. {example_product_1_name}: {example_description_1}
2. {example_product_2_name}: {example_description_2}
3. {example_product_3_name}: {example_description_3}
Write a product description for:
Product name: {new_product_name}
Category: {category}
Key features: {feature_list}
Target use case: {use_case}
Price tier: {price_positioning}
Match the voice, rhythm and tone of the examples. Keep it to {word_count} words.