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 contact page and forms. Also use when the user mentions "contact page," "contact form," "get in touch," "support form," "contact us," "reach us," "contact information," "support contact," or "inquiry form." For sitewide page planning, use website-structure.
.claude/skills/kostja94-contact-page-generator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -23% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -38% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -52% | 0% |
| case-14 | ✓→✗ | ▼ Worse | 18% | 0% |
| case-16 | ✓→✗ | ▼ Worse | -6% | 0% |
Guides contact page design and form optimization for conversions.
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 brand voice.
Identify:
| Principle | Guideline | |-----------|-----------| | Short | 3-5 fields for basic contact; long forms increase abandonment | | Single column | Vertical layout; works better on mobile | | Logical grouping | Name+email together; address fields together | | Required fields | Mark clearly (asterisk); avoid surprises | | Progressive disclosure | Show relevant fields based on selections |
| Element | Guideline | |---------|-----------| | Visibility | "Contact" or "Support" in main nav, not just footer | | Mobile | Appropriate input types (tel for phone), large tap targets | | Proofreading | No typos--credibility at conversion moment | | Alternatives | Email, phone, chat if form isn't right |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 22,703 | 15,184 | -33% | 1 | 1 | 0% | 4,150 | 3,194 | -23% | 0 | 0 | — |
case-02 | pass→pass | 19,603 | 12,002 | -39% | 1 | 1 | 0% | 3,765 | 2,841 | -25% | 0 | 0 | — |
case-03 | pass→pass | 12,446 | 10,814 | -13% | 1 | 1 | 0% | 2,144 | 2,122 | -1% | 0 | 0 | — |
case-22 | pass→pass | 14,241 | 6,819 | -52% | 1 | 1 | 0% | 2,477 | 1,823 | -26% | 0 | 0 | — |
case-04 | pass→pass | 14,677 | 13,215 | -10% | 1 | 1 | 0% | 2,689 | 2,898 | +8% | 0 | 0 | — |
case-05 | fail→pass | 15,645 | 10,035 | -36% | 1 | 1 | 0% | 3,845 | 2,393 | -38% | 0 | 0 | — |
case-06 | pass→pass | 9,312 | 7,395 | -21% | 1 | 1 | 0% | 1,795 | 2,064 | +15% | 0 | 0 | — |
case-07 | pass→pass | 7,283 | 6,215 | -15% | 1 | 1 | 0% | 1,363 | 1,745 | +28% | 0 | 0 | — |
case-08 | pass→pass | 9,514 | 9,800 | +3% | 1 | 1 | 0% | 1,679 | 2,139 | +27% | 0 | 0 | — |
case-09 | pass→pass | 7,625 | 8,307 | +9% | 1 | 1 | 0% | 1,495 | 2,041 | +37% | 0 | 0 | — |
case-10 | fail→fail | 6,909 | 8,955 | +30% | 1 | 1 | 0% | 1,304 | 2,174 | +67% | 0 | 0 | — |
case-11 | pass→pass | 14,762 | 10,861 | -26% | 1 | 1 | 0% | 2,635 | 2,500 | -5% | 0 | 0 | — |
case-12 | pass→pass | 14,340 | 10,275 | -28% | 1 | 1 | 0% | 2,601 | 2,486 | -4% | 0 | 0 | — |
case-13 | pass→pass | 9,322 | 8,080 | -13% | 1 | 1 | 0% | 1,712 | 2,011 | +17% | 0 | 0 | — |
case-14 | pass→fail | 8,790 | 7,734 | -12% | 1 | 1 | 0% | 1,661 | 1,964 | +18% | 0 | 0 | — |
case-15 | fail→pass | 25,603 | 13,052 | -49% | 1 | 1 | 0% | 6,156 | 2,927 | -52% | 0 | 0 | — |
case-16 | pass→fail | 12,774 | 9,101 | -29% | 1 | 1 | 0% | 2,251 | 2,109 | -6% | 0 | 0 | — |
case-17 | pass→pass | 10,863 | 7,554 | -30% | 1 | 1 | 0% | 1,865 | 1,761 | -6% | 0 | 0 | — |
case-18 | pass→pass | 15,250 | 8,729 | -43% | 1 | 1 | 0% | 3,016 | 2,374 | -21% | 0 | 0 | — |
case-19 | pass→pass | 13,712 | 13,624 | -1% | 1 | 1 | 0% | 2,721 | 3,492 | +28% | 0 | 0 | — |
case-20 | pass→pass | 10,130 | 9,594 | -5% | 1 | 1 | 0% | 1,845 | 2,380 | +29% | 0 | 0 | — |
case-21 | pass→pass | 9,795 | 12,677 | +29% | 1 | 1 | 0% | 2,080 | 3,019 | +45% | 0 | 0 | — |
case-23 | pass→pass | 9,348 | 6,761 | -28% | 1 | 1 | 0% | 1,524 | 1,687 | +11% | 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 +4 percentage points is the difference between those two pass rates over the 23 comparable cases. 2 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.