Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when auditing metadata, crawlability, structured data, or indexability related to Create a comprehensive Contact page. Verify the rendered HTML and HTTP response rather than relying only on source files.
.claude/skills/thedaviddias-contact-page/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -14% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 59% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | 20% | 0% |
A clear and accessible contact page is a major trust signal for E-E-A-T and provides essential support for users, improving overall site credibility.
Verify that the website has a dedicated Contact page with multiple, working contact methods.
Create a /contact page and add a contact form, email address, and other relevant contact information.
Explain why having a verifiable contact page is a critical factor for business legitimacy and search rankings.
Review metadata generation, rendered HTML, structured data, and response headers related to Create a comprehensive Contact page. Flag exact routes or templates where search-facing output violates the rule, and describe how to verify the final page output.
For full implementation details, code examples, and framework-specific guidance, see references/rule.md.
Rule page: https://frontendchecklist.io/en/rules/seo/contact-page
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | pass→pass | 11,301 | 8,850 | -22% | 1 | 1 | 0% | 2,203 | 2,642 | +20% | 0 | 0 | — |
case-07 | pass→pass | 20,086 | 14,844 | -26% | 1 | 1 | 0% | 3,936 | 3,868 | -2% | 0 | 0 | — |
case-01 | fail→pass | 20,746 | 17,027 | -18% | 1 | 1 | 0% | 4,974 | 4,259 | -14% | 0 | 0 | — |
case-02 | pass→pass | 10,553 | 12,437 | +18% | 1 | 1 | 0% | 2,258 | 3,257 | +44% | 0 | 0 | — |
case-03 | fail→fail | 11,301 | 15,726 | +39% | 1 | 1 | 0% | 1,960 | 3,495 | +78% | 0 | 0 | — |
case-04 | pass→pass | 11,283 | 12,698 | +13% | 1 | 1 | 0% | 1,885 | 2,810 | +49% | 0 | 0 | — |
case-05 | pass→pass | 11,216 | 10,605 | -5% | 1 | 1 | 0% | 1,888 | 2,616 | +39% | 0 | 0 | — |
case-08 | pass→pass | 10,426 | 8,548 | -18% | 1 | 1 | 0% | 1,779 | 1,954 | +10% | 0 | 0 | — |
case-09 | pass→pass | 17,265 | 12,581 | -27% | 1 | 1 | 0% | 3,145 | 2,992 | -5% | 0 | 0 | — |
case-10 | pass→pass | 9,258 | 6,770 | -27% | 1 | 1 | 0% | 1,610 | 1,542 | -4% | 0 | 0 | — |
case-11 | fail→pass | 14,757 | 16,561 | +12% | 1 | 1 | 0% | 3,000 | 3,833 | +28% | 0 | 0 | — |
case-12 | fail→pass | 10,717 | 13,154 | +23% | 1 | 1 | 0% | 1,848 | 2,943 | +59% | 0 | 0 | — |
case-13 | pass→pass | 12,617 | 13,039 | +3% | 1 | 1 | 0% | 2,124 | 2,883 | +36% | 0 | 0 | — |
case-14 | pass→pass | 7,974 | 7,440 | -7% | 1 | 1 | 0% | 1,540 | 1,784 | +16% | 0 | 0 | — |
case-15 | pass→pass | 13,757 | 9,127 | -34% | 1 | 1 | 0% | 2,811 | 1,988 | -29% | 0 | 0 | — |
case-16 | pass→pass | 12,205 | 12,334 | +1% | 1 | 1 | 0% | 2,131 | 2,499 | +17% | 0 | 0 | — |
case-17 | pass→pass | 7,288 | 8,038 | +10% | 1 | 1 | 0% | 1,689 | 2,164 | +28% | 0 | 0 | — |
case-18 | fail→pass | 11,194 | 9,545 | -15% | 1 | 1 | 0% | 1,992 | 2,124 | +7% | 0 | 0 | — |
case-19 | pass→pass | 9,900 | 12,343 | +25% | 1 | 1 | 0% | 1,768 | 2,900 | +64% | 0 | 0 | — |
case-20 | pass→pass | 11,382 | 15,235 | +34% | 1 | 1 | 0% | 3,033 | 3,895 | +28% | 0 | 0 | — |
case-21 | pass→pass | 13,183 | 14,298 | +8% | 1 | 1 | 0% | 3,134 | 3,408 | +9% | 0 | 0 | — |
case-22 | pass→pass | 21,345 | 20,696 | -3% | 1 | 1 | 0% | 4,844 | 5,155 | +6% | 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 +18 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.