Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Audit and optimize a marketplace listing (Amazon, Etsy, eBay, Walmart) to rank and convert. Use when asked to optimize an Amazon/Etsy listing, improve marketplace SEO, fix a product listing that isn't selling, or write keyword-rich titles and bullets. Produces a prioritised optimization — title, bullets, backend keywords, A+/description, images plan, and conversion fixes — mapped to how that marketplace ranks and shoppers decide.
.claude/skills/mohitagw15856-marketplace-listing-optimizer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-10 | ✗→✓ | ▲ Improved | 66% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 129% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 74% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 134% | 0% |
| case-04 | ✓→✗ | ▼ Worse | 55% | 0% |
On a marketplace, the listing is the salesperson — and the algorithm reads it before a human does. Ranking comes from relevance (the right keywords in the right fields) and performance (click-through and conversion). This skill audits a listing against both and returns prioritised fixes, so "it's buried and not converting" becomes a specific to-do list.
Given a product and maybe a current title, produce the full optimization anyway — infer the category, buyer, and likely keywords, and label inferences. Don't invent metrics, certifications, or claims. Never withhold the audit for missing detail; mark what to confirm.
Ask for these only if they aren't already provided (else infer and label):
1. Diagnosis — is the gap visibility (keywords/relevance) or conversion (title/images/price/reviews)? Lead with the bigger lever.
2. Keywords — primary, secondary, and long-tail terms, grouped, and where each belongs (title vs. bullets vs. backend/tags). Note any to confirm with real search-volume data.
3. Title — an optimized title following the marketplace's pattern and length limit (Amazon: brand + key features + size/qty; Etsy: front-load buyer phrases).
4. Bullets / key features — rewritten benefit-led bullets that also carry secondary keywords.
5. Description / A+ — the longer copy (Amazon A+ modules, Etsy description) — structure + key points.
6. Backend / tags — hidden keyword fields, tags, attributes to fill (no repeats of the title).
7. Images & media plan — the shot list that converts (main on white, infographic, lifestyle, scale, detail) — a checklist, not the images.
8. Conversion fixes — price/coupon, reviews strategy, A+ trust, and anything dragging the buy decision.
9. Prioritised actions — ordered by impact-to-effort.
Marketplace SEO & CRO practice — relevance-and-performance ranking, field-appropriate keyword placement, and conversion optimization (title, images, reviews, price).
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 24,980 | 21,208 | -15% | 1 | 1 | 0% | 4,260 | 4,536 | +6% | 0 | 0 | — |
case-02 | fail→fail | 22,963 | 23,913 | +4% | 1 | 1 | 0% | 4,089 | 5,093 | +25% | 0 | 0 | — |
case-03 | fail→fail | 26,937 | 26,590 | -1% | 1 | 1 | 0% | 4,311 | 5,085 | +18% | 0 | 0 | — |
case-04 | pass→fail | 14,692 | 17,623 | +20% | 1 | 1 | 0% | 2,373 | 3,677 | +55% | 0 | 0 | — |
case-05 | fail→fail | 10,612 | 17,864 | +68% | 1 | 1 | 0% | 1,964 | 3,837 | +95% | 0 | 0 | — |
case-06 | fail→fail | 15,110 | 19,986 | +32% | 1 | 1 | 0% | 2,353 | 4,242 | +80% | 0 | 0 | — |
case-07 | pass→pass | 18,305 | 18,094 | -1% | 1 | 1 | 0% | 3,044 | 3,839 | +26% | 0 | 0 | — |
case-08 | fail→fail | 9,918 | 17,363 | +75% | 1 | 1 | 0% | 1,608 | 3,625 | +125% | 0 | 0 | — |
case-09 | fail→fail | 15,913 | 19,907 | +25% | 1 | 1 | 0% | 2,192 | 4,313 | +97% | 0 | 0 | — |
case-10 | fail→pass | 16,575 | 22,651 | +37% | 1 | 1 | 0% | 2,539 | 4,222 | +66% | 0 | 0 | — |
case-11 | pass→pass | 21,369 | 21,720 | +2% | 1 | 1 | 0% | 2,929 | 3,231 | +10% | 0 | 0 | — |
case-12 | pass→pass | 21,319 | 22,420 | +5% | 1 | 1 | 0% | 4,245 | 5,741 | +35% | 0 | 0 | — |
case-13 | pass→pass | 16,529 | 20,421 | +24% | 1 | 1 | 0% | 3,043 | 3,426 | +13% | 0 | 0 | — |
case-14 | fail→fail | 16,160 | 19,644 | +22% | 1 | 1 | 0% | 2,573 | 4,389 | +71% | 0 | 0 | — |
case-15 | fail→fail | 11,789 | 18,476 | +57% | 1 | 1 | 0% | 2,175 | 4,121 | +89% | 0 | 0 | — |
case-16 | fail→pass | 9,889 | 20,124 | +103% | 1 | 1 | 0% | 1,730 | 3,966 | +129% | 0 | 0 | — |
case-17 | pass→pass | 13,377 | 20,544 | +54% | 1 | 1 | 0% | 2,233 | 4,403 | +97% | 0 | 0 | — |
case-18 | fail→pass | 16,896 | 21,083 | +25% | 1 | 1 | 0% | 2,804 | 4,880 | +74% | 0 | 0 | — |
case-19 | fail→fail | 10,636 | 20,168 | +90% | 1 | 1 | 0% | 1,855 | 4,163 | +124% | 0 | 0 | — |
case-20 | fail→pass | 8,179 | 15,096 | +85% | 1 | 1 | 0% | 1,498 | 3,507 | +134% | 0 | 0 | — |
case-21 | fail→fail | 12,689 | 19,433 | +53% | 1 | 1 | 0% | 2,150 | 3,841 | +79% | 0 | 0 | — |
case-22 | fail→fail | 18,722 | 21,482 | +15% | 1 | 1 | 0% | 3,337 | 4,605 | +38% | 0 | 0 | — |
case-23 | fail→fail | 9,703 | 17,417 | +80% | 1 | 1 | 0% | 1,874 | 3,816 | +104% | 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. 23 cases were attempted. The headline lift of +13 percentage points is the difference between those two pass rates over the 23 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.