Mine Reviews for the Five Fixes
Turn a year of reviews into a ranked, costed fix list.
Reading reviews one by one produces feelings, not decisions. Read together, the same complaint appears in forty different phrasings.
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
Restaurants, clinics, retail, and D2C brands with review volume.
How it works
The skill file does five things, in this order.
1. Export everything. Google, Talabat, Instagram comments, support emails, all of it.
2. Cluster by underlying cause. 'Slow' and 'forgot my order' are often the same staffing problem.
3. Weight by rating impact. Which complaint actually costs you stars, not just mentions.
4. Separate fixable from structural. Parking complaints are real but you cannot build a car park.
5. Cost each fix roughly. So the cheap high-impact ones become obvious.
What comes back
A ranked cause list with star impact, rough cost, and five prioritised fixes.
The mistake to avoid
Ask it to quote three real customer sentences per cause. Abstract findings get argued with in meetings; a customer's own words end the argument.
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
Analyse all reviews and feedback in this export.
1. ROOT CAUSE CLUSTERS, group by underlying cause, not by wording. "Slow
service" and "they forgot my order" may be one staffing cause. State your
clustering logic.
2. For each cluster: mention count, share of 1-2 star reviews, average rating of
reviews mentioning it, trend over time, and three short verbatim quotes
(under 15 words each).
3. STAR IMPACT, estimate how much each cluster costs the overall rating.
4. FIXABLE VS STRUCTURAL, split clusters into what operations can change and
what is fixed by location, format, or price point.
5. TOP FIVE FIXES, ranked by star impact divided by rough implementation cost.
Each with the first concrete action to take this week.
<reviews>{export}</reviews>