Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Run a comprehensive on-page SEO audit or optimization pass covering title tags, meta descriptions, header structure, content quality, internal links, image optimization, URL hygiene, and on-page schema. Use this skill whenever the user asks to optimize a page, audit on-page SEO, fix titles or meta tags, review header structure, check internal linking, improve a single URL's search performance, or write SEO-friendly copy. Triggers on on-page SEO, page audit, title tag, meta description, H1, heade
.claude/skills/rampstackco-seo-onpage/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 39% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -13% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-17 | ✓→✓ | = Same ✓ | 34% | 0% |
Optimize a single page for search relevance, click-through, and crawler comprehension. Stack-agnostic. Works on any CMS, framework, or static site.
seo-technical)seo-keyword)seo-competitor)seo-content-audit)If the target query is unknown, run seo-keyword first or ask the user to name one.
A complete on-page audit covers eight dimensions. Score each as Pass, Needs work, or Fail. Note the specific fix.
<title>, <meta>, headers, and schema in the source.references/audit-template.md.When you spot one of these, push back before delivering.
seo-technical first. No on-page work helps a noindexed page.seo-content-audit to decide which page should rank.Default output is a markdown audit at seo-audit-[page-slug].md in the project root. Structure:
Keep audits under 1500 words. If a page needs more detail, link to deeper appendices.
references/audit-template.md - Fillable audit template, copy and use.references/onpage-checklist.md - Quick-reference checklist for the 8 dimensions.references/title-and-meta-patterns.md - Patterns for writing strong titles and meta descriptions.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-17 | pass→pass | 14,117 | 10,117 | -28% | 1 | 1 | 0% | 2,584 | 3,462 | +34% | 0 | 0 | — |
case-01 | fail→pass | 25,610 | 22,976 | -10% | 1 | 1 | 0% | 4,806 | 5,244 | +9% | 0 | 0 | — |
case-02 | fail→pass | 19,601 | 17,612 | -10% | 1 | 1 | 0% | 3,585 | 4,981 | +39% | 0 | 0 | — |
case-03 | fail→pass | 20,292 | 9,861 | -51% | 1 | 1 | 0% | 3,834 | 3,346 | -13% | 0 | 0 | — |
case-04 | pass→pass | 21,605 | 5,787 | -73% | 1 | 1 | 0% | 3,789 | 2,487 | -34% | 0 | 0 | — |
case-05 | pass→pass | 21,108 | 13,931 | -34% | 1 | 1 | 0% | 3,592 | 4,076 | +13% | 0 | 0 | — |
case-06 | pass→pass | 16,519 | 17,666 | +7% | 1 | 1 | 0% | 2,745 | 4,241 | +54% | 0 | 0 | — |
case-07 | pass→pass | 11,956 | 6,887 | -42% | 1 | 1 | 0% | 2,001 | 2,582 | +29% | 0 | 0 | — |
case-08 | pass→pass | 10,364 | 4,827 | -53% | 1 | 1 | 0% | 1,677 | 2,279 | +36% | 0 | 0 | — |
case-09 | pass→pass | 14,853 | 11,995 | -19% | 1 | 1 | 0% | 2,453 | 3,520 | +43% | 0 | 0 | — |
case-10 | pass→pass | 13,383 | 7,200 | -46% | 1 | 1 | 0% | 2,389 | 2,621 | +10% | 0 | 0 | — |
case-11 | pass→pass | 14,548 | 14,265 | -2% | 1 | 1 | 0% | 2,643 | 4,188 | +58% | 0 | 0 | — |
case-12 | pass→pass | 8,791 | 8,575 | -2% | 1 | 1 | 0% | 1,634 | 3,107 | +90% | 0 | 0 | — |
case-13 | pass→pass | 11,429 | 9,229 | -19% | 1 | 1 | 0% | 2,222 | 3,228 | +45% | 0 | 0 | — |
case-14 | pass→pass | 9,545 | 5,491 | -42% | 1 | 1 | 0% | 1,824 | 2,522 | +38% | 0 | 0 | — |
case-15 | pass→pass | 13,003 | 9,523 | -27% | 1 | 1 | 0% | 2,201 | 3,075 | +40% | 0 | 0 | — |
case-16 | pass→pass | 9,338 | 6,152 | -34% | 1 | 1 | 0% | 1,787 | 2,586 | +45% | 0 | 0 | — |
case-18 | pass→pass | 12,666 | 7,277 | -43% | 1 | 1 | 0% | 2,276 | 2,800 | +23% | 0 | 0 | — |
case-19 | pass→pass | 10,717 | 9,830 | -8% | 1 | 1 | 0% | 2,189 | 3,480 | +59% | 0 | 0 | — |
case-20 | fail→pass | 21,030 | 11,791 | -44% | 1 | 1 | 0% | 3,724 | 3,774 | +1% | 0 | 0 | — |
case-21 | pass→pass | 9,322 | 7,199 | -23% | 1 | 1 | 0% | 1,589 | 2,741 | +72% | 0 | 0 | — |
case-22 | pass→pass | 15,237 | 11,858 | -22% | 1 | 1 | 0% | 2,417 | 3,555 | +47% | 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.