Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to create, optimize, or audit a product listing or category page. Also use when the user mentions "product page," "product listing," "shop," "e-commerce products," "product catalog," "product grid," "product cards," or "product overview." For category SEO, use category-page-generator.
.claude/skills/kostja94-products-page-generator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | -20% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-08 | ✓→✗ | ▼ Worse | -25% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 0% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 43% | 0% |
Guides product listing and category page content for e-commerce. For individual product detail pages, structure varies by platform.
When invoking: On first use, if helpful, open with 1-2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.
Check for project context first: If .claude/project-context.md or .cursor/project-context.md exists, read it for product catalog and positioning.
Identify:
| Element | Purpose | |---------|---------| | Category title | Clear H1; target keyword | | Description | SEO copy; benefits of category | | Filters | Price, size, brand, etc. | | Product cards | Image, name, price, CTA | | Pagination | Crawlable; rel prev/next |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 12,770 | 9,772 | -23% | 1 | 1 | 0% | 2,353 | 2,354 | +0% | 0 | 0 | — |
case-02 | pass→pass | 10,805 | 11,819 | +9% | 1 | 1 | 0% | 1,809 | 2,580 | +43% | 0 | 0 | — |
case-03 | fail→pass | 12,391 | 7,166 | -42% | 1 | 1 | 0% | 2,248 | 1,800 | -20% | 0 | 0 | — |
case-04 | pass→pass | 15,074 | 9,362 | -38% | 1 | 1 | 0% | 2,308 | 2,012 | -13% | 0 | 0 | — |
case-21 | pass→pass | 21,607 | 12,565 | -42% | 1 | 1 | 0% | 4,226 | 2,978 | -30% | 0 | 0 | — |
case-05 | fail→pass | 14,120 | 12,791 | -9% | 1 | 1 | 0% | 2,378 | 2,491 | +5% | 0 | 0 | — |
case-06 | pass→pass | 8,926 | 7,443 | -17% | 1 | 1 | 0% | 1,436 | 1,754 | +22% | 0 | 0 | — |
case-07 | pass→pass | 9,401 | 6,628 | -29% | 1 | 1 | 0% | 1,555 | 1,580 | +2% | 0 | 0 | — |
case-08 | pass→fail | 15,041 | 8,607 | -43% | 1 | 1 | 0% | 2,714 | 2,043 | -25% | 0 | 0 | — |
case-09 | pass→pass | 10,501 | 8,214 | -22% | 1 | 1 | 0% | 1,865 | 1,920 | +3% | 0 | 0 | — |
case-10 | pass→pass | 6,470 | 6,427 | -1% | 1 | 1 | 0% | 1,101 | 1,555 | +41% | 0 | 0 | — |
case-11 | pass→pass | 13,001 | 10,783 | -17% | 1 | 1 | 0% | 2,208 | 2,387 | +8% | 0 | 0 | — |
case-12 | pass→pass | 10,924 | 10,856 | -1% | 1 | 1 | 0% | 1,899 | 2,507 | +32% | 0 | 0 | — |
case-13 | pass→pass | 6,512 | 4,427 | -32% | 1 | 1 | 0% | 1,284 | 1,433 | +12% | 0 | 0 | — |
case-14 | pass→pass | 6,435 | 5,194 | -19% | 1 | 1 | 0% | 1,253 | 1,538 | +23% | 0 | 0 | — |
case-15 | fail→fail | 14,165 | 9,908 | -30% | 1 | 1 | 0% | 2,572 | 2,408 | -6% | 0 | 0 | — |
case-16 | pass→pass | 15,203 | 10,328 | -32% | 1 | 1 | 0% | 2,613 | 2,245 | -14% | 0 | 0 | — |
case-17 | pass→pass | 13,863 | 6,456 | -53% | 1 | 1 | 0% | 2,598 | 1,714 | -34% | 0 | 0 | — |
case-18 | pass→pass | 9,487 | 7,604 | -20% | 1 | 1 | 0% | 1,744 | 1,852 | +6% | 0 | 0 | — |
case-19 | pass→pass | 15,358 | 10,031 | -35% | 1 | 1 | 0% | 2,588 | 2,342 | -10% | 0 | 0 | — |
case-20 | pass→pass | 32,363 | 21,537 | -33% | 1 | 1 | 0% | 6,182 | 4,946 | -20% | 0 | 0 | — |
case-22 | pass→pass | 18,495 | 9,621 | -48% | 1 | 1 | 0% | 4,724 | 2,416 | -49% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of 0 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.