SkillShelf

Build a Category Badge Framework

Produces a small, opinionated product badge system for a single ecommerce category. Identifies the decision axes that matter most to shoppers, then picks the best 1-2 products per badge.

Here's how the conversation starts

I'm going to build your brand voice profile. This is a document that captures how your brand writes, so you (and other AI tools) can produce on-brand copy consistently. Here's how it works:

  • You share examples of your brand's writing
  • I analyze the patterns and produce your voice profile
  • You review it, we refine anything that's off

Any questions? If not, we can get started. What's your brand name and website URL?

Common questions

What input do I need to run this skill? +

Product data for a single category (CSV export, pasted product list, or PDP content). Review data and existing badges are optional but helpful.

How many badges does it produce? +

Typically 3-5 badges, each pointing to 1-2 products. Most products in the category will not get a badge. That's intentional.

Can I run this across multiple categories at once? +

No. The skill works one category at a time. Badge themes that work for insulated jackets are different from ones that work for moisturizers. Run it separately per category.

Example skill output +

Example Output: Build Category Badge Framework

This example demonstrates the skill's output using a fictional Insulated Jackets category from Great Outdoors Co., an outdoor gear brand. The input was a product export with 10 insulated jackets, product attributes, and 48 customer reviews across the category.


Badge Framework: Insulated Jackets

Category Badge Framework

No Shell Needed

  • Definition: Warm enough on its own in freezing conditions
  • Why it matters: Shoppers here are split between people looking for a midlayer under a shell and people looking for one jacket that handles winter by itself. Reviewers consistently frame jackets as one or the other.
  • Considerations: Manufacturer temperature rating, fill weight, construction features (insulated hood, draft collar, hand pockets), and reviewer descriptions of standalone winter use
  • Recommended product: Frostline Parka. Rated to 0°F with 200g synthetic fill, insulated hood, draft tube, and storm cuffs. 12 of 14 reviews describe wearing it as their only winter layer. The Basecamp Down Hoody also qualifies on construction, but the Frostline has stronger review evidence for standalone use.

Wet Ready

  • Definition: Insulation that won't quit on you in rain
  • Why it matters: "What happens when this gets wet?" is one of the most common questions in reviews across this category. Shoppers who hike in wet climates need a different jacket than those in dry cold.
  • Considerations: Insulation type (synthetic or hydrophobic-treated down vs. standard untreated down), reviewer mentions of wet-weather performance
  • Recommended product: Ridgeline Synthetic Hoody. 150g PrimaLoft Gold synthetic fill throughout. 6 of 9 reviews mention wearing it in rain or damp conditions. Picked over other synthetic options because it's a full hoody (not a vest) with the strongest review signal for wet-weather use.

Packs Small

  • Definition: Compresses into its own pocket as a just-in-case layer
  • Why it matters: Reviewers in this category talk about packability almost as much as warmth. The shopper who cares about this badge is deciding which layers make the cut for a trip.
  • Considerations: Documented pack-into-pocket or stuff-sack mechanism with a listed packed size. Generic "packable" marketing claims don't count.
  • Recommended product: Summit Down Pullover. Packs into its chest pocket at 8.4 oz. Picked over the Alpine Down Jacket (also packs small) because it's meaningfully lighter and better suited to the "toss it in your pack just in case" use case.

Crowd Pick

  • Definition: Backed by a high volume of top ratings from real buyers
  • Why it matters: Some shoppers know exactly what they need. Others want a safe, well-tested option. High review volume is a proxy for "this works for most people."
  • Considerations: Volume of five-star reviews, not average rating. A product with 8 reviews and a 5.0 average is not comparable to one with 200 reviews and a 4.7.
  • Recommended product: Alpine Down Jacket. 34 five-star reviews out of 47 total. The next closest product has 19. This is the clear standout on social proof.

Considered and Rejected

"Best for Layering." Sounds like a real decision, but it's the inverse of No Shell Needed. If a jacket doesn't carry that badge, the shopper can already infer it's a midlayer. Adding a separate badge for layering just restates the same axis from the other side.

"Coldest Rated." A shopper might filter by this, but the temperature ratings across this set aren't standardized (some are manufacturer-rated, some are inferred from fill weight). No Shell Needed covers the core use case without requiring precise temp comparisons that the data can't support.

"Travel Friendly." Overlaps too heavily with Packs Small. The shopper who cares about travel packability is the same shopper who cares about Packs Small. Two badges for the same decision.

Ready to go

Download, then upload to Claude or ChatGPT. That's it.

Download Skill
GitHub