Train Your Team to Read Reviews the Same Way
Build a shared method so every team member extracts the same insights from customer feedback
Each team member reads the same reviews but walks away with different priorities and conflicting recommendations. Without a standard process, insights stay fragmented and action items contradict each other across departments.
That is the gap this drop closes. It is a marketing 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
Marketing managers rolling out review analysis across customer service, product and sales teams
How it works
The skill file does five things, in this order.
1. Write your house categories. List the 6-8 business areas your company can actually fix: delivery speed, product quality, staff behaviour, pricing clarity, app usability, packaging.
2. Build the sorting prompt. Create one prompt that takes any review text and assigns it to your categories with a confidence score, so different team members get identical outputs.
3. Test with five people on the same batch. Have five team members run the prompt on 20 identical reviews, compare outputs, and refine category definitions until results match.
4. Document the two-step workflow. Write a one-page guide showing the prompt to use and the spreadsheet template to record findings, so anyone can repeat the process without asking questions.
5. Schedule monthly calibration sessions. Meet monthly to review outlier cases where the AI or a team member categorised differently, and update the prompt together to close gaps.
What comes back
A repeatable review analysis process that produces consistent category assignments and priority lists regardless of who runs it
The mistake to avoid
Version your prompt with a date code and store it in a shared document. When team members report different results, check they are using the same version before troubleshooting further.
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 are a customer feedback analyst for {company_name} in {industry}.
Read the review below and classify the main issue into exactly ONE of these categories:
{category_1}: {definition_1}
{category_2}: {definition_2}
{category_3}: {definition_3}
{category_4}: {definition_4}
{category_5}: {definition_5}
{category_6}: {definition_6}
If the review mentions multiple issues, choose the one the customer emphasises most or mentions first.
Provide your answer in this format:
Category: {chosen category}
Confidence: {High/Medium/Low}
Reasoning: {one sentence explaining why}
Review text:
{review_text}