Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to add, optimize, or design customer testimonials, reviews, or case study sections. Also use when the user mentions "testimonials," "reviews," "customer quotes," "social proof," "case studies," "testimonial section," "customer reviews," "review schema," "testimonial design," or "social proof section." For case studies page, use customer-stories-page-generator.
.claude/skills/kostja94-testimonials-generator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -23% | 0% |
| case-19 | ✓→✗ | ▼ Worse | 12% | 0% |
| case-20 | ✓→✗ | ▼ Worse | 38% | 0% |
| case-21 | ✓→✗ | ▼ Worse | 91% | 0% |
Guides testimonial design and placement for conversion. 92% of consumers read reviews before buying; testimonials can increase conversion by up to 67%.
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 customer personas and industries.
Identify:
| Format | Effectiveness | Best For | |--------|---------------|----------| | Video | Highest; 77% say it influences buying | Key landing pages | | Text + photo | Versatile; easy to implement | Product, pricing | | Case study | Deep credibility; specific outcomes | B2B, high-value | | Star ratings | Quick trust signal | E-commerce |
Video: 95% message retention vs 10% for text.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 18,350 | 13,576 | -26% | 1 | 1 | 0% | 2,719 | 2,911 | +7% | 0 | 0 | — |
case-02 | pass→pass | 15,141 | 12,640 | -17% | 1 | 1 | 0% | 2,265 | 2,776 | +23% | 0 | 0 | — |
case-03 | pass→pass | 13,303 | 13,482 | +1% | 1 | 1 | 0% | 2,105 | 2,683 | +27% | 0 | 0 | — |
case-04 | pass→pass | 16,807 | 18,268 | +9% | 1 | 1 | 0% | 2,673 | 2,801 | +5% | 0 | 0 | — |
case-05 | pass→pass | 12,890 | 8,494 | -34% | 1 | 1 | 0% | 2,042 | 1,900 | -7% | 0 | 0 | — |
case-06 | pass→pass | 16,547 | 11,380 | -31% | 1 | 1 | 0% | 3,001 | 2,776 | -7% | 0 | 0 | — |
case-07 | pass→pass | 11,231 | 11,936 | +6% | 1 | 1 | 0% | 2,148 | 2,804 | +31% | 0 | 0 | — |
case-13 | pass→pass | 9,773 | 12,779 | +31% | 1 | 1 | 0% | 1,754 | 2,627 | +50% | 0 | 0 | — |
case-08 | pass→pass | 11,831 | 11,025 | -7% | 1 | 1 | 0% | 1,826 | 2,330 | +28% | 0 | 0 | — |
case-09 | pass→pass | 10,063 | 10,680 | +6% | 1 | 1 | 0% | 1,676 | 2,395 | +43% | 0 | 0 | — |
case-10 | pass→pass | 8,847 | 6,901 | -22% | 1 | 1 | 0% | 1,592 | 1,963 | +23% | 0 | 0 | — |
case-11 | pass→pass | 10,647 | 8,024 | -25% | 1 | 1 | 0% | 1,845 | 1,989 | +8% | 0 | 0 | — |
case-12 | pass→pass | 8,173 | 7,550 | -8% | 1 | 1 | 0% | 1,633 | 2,162 | +32% | 0 | 0 | — |
case-14 | pass→pass | 14,994 | 11,124 | -26% | 1 | 1 | 0% | 2,415 | 2,468 | +2% | 0 | 0 | — |
case-15 | fail→fail | 12,215 | 9,918 | -19% | 1 | 1 | 0% | 2,096 | 2,294 | +9% | 0 | 0 | — |
case-16 | pass→pass | 14,211 | 13,004 | -8% | 1 | 1 | 0% | 2,384 | 3,037 | +27% | 0 | 0 | — |
case-17 | fail→pass | 19,192 | 11,379 | -41% | 1 | 1 | 0% | 3,494 | 2,695 | -23% | 0 | 0 | — |
case-18 | pass→pass | 10,612 | 8,882 | -16% | 1 | 1 | 0% | 1,776 | 2,040 | +15% | 0 | 0 | — |
case-19 | pass→fail | 12,385 | 10,806 | -13% | 1 | 1 | 0% | 2,206 | 2,466 | +12% | 0 | 0 | — |
case-20 | pass→fail | 10,889 | 14,547 | +34% | 1 | 1 | 0% | 2,142 | 2,959 | +38% | 0 | 0 | — |
case-21 | pass→fail | 15,463 | 24,564 | +59% | 1 | 1 | 0% | 3,588 | 6,844 | +91% | 0 | 0 | — |
case-22 | pass→pass | 15,354 | 11,410 | -26% | 1 | 1 | 0% | 3,208 | 3,185 | -1% | 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 -20 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 cases got worse with the skill loaded, and they are 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.