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 features page content. Also use when the user mentions "features page," "product features," "capabilities," "what it does," "feature list," "feature comparison," "product capabilities," or "features section." For sitewide page planning, use website-structure.
.claude/skills/kostja94-features-page-generator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-20 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-03 | ✓→✗ | ▼ Worse | 16% | 0% |
Guides features page content, structure, and conversion optimization.
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, differentiation, and proof points.
Identify:
| Section | Purpose | |---------|---------| | Headline | Benefit-led; "Everything you need to..." | | Feature grid/list | Each feature: name, benefit, optional screenshot | | Use case links | "For marketers," "For developers" | | Social proof | Testimonials, logos | | CTA | Try free, see demo, contact |
| Page | Purpose | Monetization | |------|---------|--------------| | Features | Paid product capabilities; conversion | Primary revenue | | Tools | Free utilities; lead gen; excerpt from product | Not primary; drives signups |
See tools-page-generator for free tools pages.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 18,263 | 12,141 | -34% | 1 | 1 | 0% | 3,304 | 3,202 | -3% | 0 | 0 | — |
case-02 | fail→fail | 17,169 | 11,660 | -32% | 1 | 1 | 0% | 3,471 | 3,176 | -8% | 0 | 0 | — |
case-03 | pass→fail | 14,362 | 11,441 | -20% | 1 | 1 | 0% | 2,466 | 2,855 | +16% | 0 | 0 | — |
case-04 | fail→fail | 19,396 | 14,881 | -23% | 1 | 1 | 0% | 3,190 | 3,667 | +15% | 0 | 0 | — |
case-05 | pass→pass | 12,388 | 9,802 | -21% | 1 | 1 | 0% | 2,603 | 2,959 | +14% | 0 | 0 | — |
case-06 | fail→fail | 12,005 | 11,139 | -7% | 1 | 1 | 0% | 2,002 | 2,857 | +43% | 0 | 0 | — |
case-07 | fail→pass | 10,973 | 8,420 | -23% | 1 | 1 | 0% | 1,814 | 2,327 | +28% | 0 | 0 | — |
case-08 | pass→pass | 9,380 | 9,094 | -3% | 1 | 1 | 0% | 1,674 | 2,397 | +43% | 0 | 0 | — |
case-09 | pass→pass | 10,359 | 10,019 | -3% | 1 | 1 | 0% | 1,717 | 2,378 | +38% | 0 | 0 | — |
case-10 | pass→pass | 7,776 | 8,400 | +8% | 1 | 1 | 0% | 1,554 | 2,494 | +60% | 0 | 0 | — |
case-11 | pass→pass | 8,477 | 5,361 | -37% | 1 | 1 | 0% | 1,665 | 2,021 | +21% | 0 | 0 | — |
case-12 | pass→fail | 5,212 | 4,707 | -10% | 1 | 1 | 0% | 927 | 1,661 | +79% | 0 | 0 | — |
case-13 | pass→pass | 17,170 | 14,680 | -15% | 1 | 1 | 0% | 3,406 | 3,648 | +7% | 0 | 0 | — |
case-14 | pass→pass | 12,288 | 12,130 | -1% | 1 | 1 | 0% | 2,255 | 3,160 | +40% | 0 | 0 | — |
case-15 | pass→pass | 10,872 | 7,669 | -29% | 1 | 1 | 0% | 1,881 | 2,344 | +25% | 0 | 0 | — |
case-16 | fail→pass | 8,023 | 3,073 | -62% | 1 | 1 | 0% | 1,477 | 1,489 | +1% | 0 | 0 | — |
case-17 | pass→fail | 10,234 | 6,973 | -32% | 1 | 1 | 0% | 2,058 | 2,101 | +2% | 0 | 0 | — |
case-18 | pass→pass | 14,592 | 10,115 | -31% | 1 | 1 | 0% | 2,460 | 2,737 | +11% | 0 | 0 | — |
case-19 | pass→pass | 10,876 | 7,897 | -27% | 1 | 1 | 0% | 2,074 | 2,333 | +12% | 0 | 0 | — |
case-20 | fail→pass | 13,570 | 8,704 | -36% | 1 | 1 | 0% | 2,420 | 2,393 | -1% | 0 | 0 | — |
case-21 | pass→pass | 13,966 | 7,303 | -48% | 1 | 1 | 0% | 2,437 | 2,246 | -8% | 0 | 0 | — |
case-22 | pass→pass | 12,361 | 10,197 | -18% | 1 | 1 | 0% | 2,169 | 2,871 | +32% | 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 +5 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.