Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Amazon review authenticity analyzer. Detect fake reviews, suspicious patterns, and rating manipulation. Includes time clustering detection, content similarity analysis, rating distribution checks, and verified purchase validation. Progressive analysis with L1-L4 depth levels. No API key required.
.claude/skills/nexscope-ai-amazon-review-checker/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 75% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -24% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -53% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -30% | 0% |
Review authenticity analyzer — detect fake reviews, suspicious patterns, and rating manipulation.
bashnpx skills add nexscope-ai/eCommerce-Skills --skill amazon-review-checker -g
| Level | Required Data | Unlocked Analysis | |-------|---------------|-------------------| | L1 Basic | Review content | Similarity, length, keywords | | L2 Advanced | + Review date | Time clustering detection | | L3 Deep | + Star rating | Rating distribution analysis | | L4 Complete | + VP status | Verified purchase validation |
| Dimension | Weight | Method | |-----------|--------|--------| | Time Clustering | 25% | Sliding window + burst detection | | Content Similarity | 20% | N-gram + Jaccard similarity | | Rating Distribution | 20% | Chi-square test vs natural distribution | | VP Ratio | 15% | Compare to category benchmark | | Review Length | 5% | Entropy analysis | | Suspicious Keywords | 5% | Keyword pattern matching |
| Score | Level | Description | |-------|-------|-------------| | 70-100 | ✅ Low Risk | Reviews appear authentic | | 50-69 | ⚠️ Medium Risk | Some concerns found | | 30-49 | 🔴 High Risk | Multiple red flags | | 0-29 | 💀 Critical | Likely mass fake reviews |
Paste reviews directly in conversation:
Check these reviews:
5 stars - Great product! Works perfectly.
5 stars - Amazing! Best purchase ever.
1 star - Not as described.bashpython3 scripts/analyzer.py '[ {"content": "Great product!", "rating": 5, "date": "2024-01-15", "verified_purchase": true}, {"content": "Amazing!", "rating": 5, "date": "2024-01-15", "verified_purchase": false} ]'
bashpython3 scripts/analyzer.py --demo
📊 Review Authenticity Report
ASIN: B08XXXXX
Reviews: 10
Analysis Level: L4
━━━━━━━━━━━━━━━━━━━━━━━━
Authenticity Score: 66/100 ⚠️
Medium Risk - Some concerns found.
━━━━━━━━━━━━━━━━━━━━━━━━
Detection Dimensions
🔴 Time Clustering: 70/100
Max 6 reviews within 48h
✅ Content Similarity: 24/100
Found 0 highly similar review groups
━━━━━━━━━━━━━━━━━━━━━━━━
High-Risk Reviews (Top 3)
1. Risk 75% - "Perfect!"
Reason: Too short, non-VP, templated 5-star
🔍 Want more accurate analysis? Add:
• Reviewer info → Unlock "Account Profile Analysis"User Input (any format)
↓
Smart field detection
↓
Analyze with available data
↓
Results + depth suggestions
↓
User continues or endsPart of Nexscope AI — AI tools for e-commerce sellers.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 13,493 | 11,645 | -14% | 1 | 1 | 0% | 2,537 | 3,058 | +21% | 0 | 0 | — |
case-02 | fail→pass | 12,182 | 9,045 | -26% | 1 | 1 | 0% | 2,144 | 2,636 | +23% | 0 | 0 | — |
case-03 | fail→fail | 8,798 | 8,369 | -5% | 1 | 1 | 0% | 1,443 | 2,291 | +59% | 0 | 0 | — |
case-04 | pass→pass | 8,901 | 9,220 | +4% | 1 | 1 | 0% | 1,425 | 2,420 | +70% | 0 | 0 | — |
case-05 | pass→pass | 10,163 | 5,959 | -41% | 1 | 1 | 0% | 1,702 | 1,730 | +2% | 0 | 0 | — |
case-06 | fail→pass | 7,147 | 8,056 | +13% | 1 | 1 | 0% | 1,334 | 2,329 | +75% | 0 | 0 | — |
case-07 | pass→pass | 12,288 | 5,459 | -56% | 1 | 1 | 0% | 2,134 | 1,867 | -13% | 0 | 0 | — |
case-08 | fail→fail | 9,560 | 3,099 | -68% | 1 | 1 | 0% | 1,451 | 1,389 | -4% | 0 | 0 | — |
case-09 | fail→pass | 12,932 | 3,822 | -70% | 1 | 1 | 0% | 2,025 | 1,531 | -24% | 0 | 0 | — |
case-10 | pass→pass | 10,075 | 2,649 | -74% | 1 | 1 | 0% | 1,552 | 1,299 | -16% | 0 | 0 | — |
case-11 | pass→pass | 6,175 | 2,221 | -64% | 1 | 1 | 0% | 962 | 1,218 | +27% | 0 | 0 | — |
case-16 | fail→pass | 20,371 | 4,715 | -77% | 1 | 1 | 0% | 3,537 | 1,665 | -53% | 0 | 0 | — |
case-12 | pass→pass | 5,816 | 2,255 | -61% | 1 | 1 | 0% | 993 | 1,225 | +23% | 0 | 0 | — |
case-13 | pass→pass | 5,002 | 2,049 | -59% | 1 | 1 | 0% | 755 | 1,182 | +57% | 0 | 0 | — |
case-14 | pass→pass | 7,386 | 3,139 | -58% | 1 | 1 | 0% | 1,144 | 1,404 | +23% | 0 | 0 | — |
case-15 | fail→pass | 12,876 | 2,717 | -79% | 1 | 1 | 0% | 1,915 | 1,337 | -30% | 0 | 0 | — |
case-17 | fail→pass | 12,272 | 2,205 | -82% | 1 | 1 | 0% | 1,965 | 1,170 | -40% | 0 | 0 | — |
case-18 | fail→pass | 13,629 | 6,452 | -53% | 1 | 1 | 0% | 2,137 | 1,899 | -11% | 0 | 0 | — |
case-19 | fail→pass | 14,097 | 1,890 | -87% | 1 | 1 | 0% | 2,073 | 1,172 | -43% | 0 | 0 | — |
case-20 | fail→pass | 10,021 | 3,511 | -65% | 1 | 1 | 0% | 1,792 | 1,333 | -26% | 0 | 0 | — |
case-21 | fail→pass | 11,179 | 2,653 | -76% | 1 | 1 | 0% | 1,790 | 1,235 | -31% | 0 | 0 | — |
case-22 | pass→pass | 5,825 | 3,456 | -41% | 1 | 1 | 0% | 823 | 1,351 | +64% | 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 +45 percentage points is the difference between those two pass rates over the 22 comparable cases.
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.