Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Run a comprehensive technical SEO audit covering crawlability, indexability, rendering, site architecture, structured data, page experience, security, and internationalization. Use this skill whenever the user asks about technical SEO, crawl issues, indexing problems, sitemaps, robots.txt, canonical tags, schema markup, page speed, Core Web Vitals, hreflang, redirects, or site-wide search performance. Triggers on technical SEO, site audit, crawlability, indexability, sitemap, robots.txt, canonic
.claude/skills/rampstackco-seo-technical/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 107% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 70% | 0% |
| case-22 | ✗→✓ | ▲ Improved | 59% | 0% |
Audit and fix the layer beneath the content: how search engines crawl, render, index, and trust a site. Stack-agnostic.
seo-onpage)seo-keyword)seo-competitor)performance-optimization)If the site is large (10K+ URLs), confirm whether the audit is a full crawl or a sample.
Technical SEO has six layers, stacked. A failure in a lower layer breaks everything above it.
Can search engines access the URLs?
noindex on indexable pagesdisallow patterns blocking CSS or JS (rendering breaks)Of crawlable URLs, which should be indexed?
noindex on staging, search results, filter pages, thank-you pages, internal adminDoes the rendered HTML match what crawlers see?
Is the site structured for both users and crawlers?
Does the site speak crawler language?
seo-aeo-geo)Does the site meet the page experience baseline?
references/audit-template.md.noindex. Always check indexability before content work.Default output is a markdown audit at seo-technical-audit.md. Structure:
For migrations, include a redirect map as a CSV alongside the report.
This skill's output depends on data, measurements, or tool results it cannot generate on its own. When a required input, tool, or data source is unavailable or unverifiable, the sanctioned output is the deliverable with the gap stated: what was needed, what was actually obtained or verified, and which parts of the output are affected. Fabricating, estimating, or interpolating a required number to complete the deliverable is never sanctioned. A stated gap is a complete answer.
references/audit-template.md - Fillable technical SEO audit template.references/migration-checklist.md - Pre and post-migration checklist (covers the highest-risk scenario).| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-19 | pass→pass | 18,149 | 15,633 | -14% | 1 | 1 | 0% | 2,777 | 3,779 | +36% | 0 | 0 | — |
case-01 | fail→pass | 34,717 | 34,156 | -2% | 1 | 1 | 0% | 6,235 | 7,758 | +24% | 0 | 0 | — |
case-08 | pass→pass | 12,159 | 9,276 | -24% | 1 | 1 | 0% | 2,075 | 3,023 | +46% | 0 | 0 | — |
case-02 | fail→pass | 27,003 | 26,787 | -1% | 1 | 1 | 0% | 5,162 | 6,469 | +25% | 0 | 0 | — |
case-03 | fail→fail | 32,536 | 22,614 | -30% | 1 | 1 | 0% | 6,109 | 5,703 | -7% | 0 | 0 | — |
case-04 | fail→pass | 10,010 | 11,982 | +20% | 1 | 1 | 0% | 1,834 | 3,796 | +107% | 0 | 0 | — |
case-05 | fail→fail | 19,428 | 19,375 | -0% | 1 | 1 | 0% | 3,364 | 4,790 | +42% | 0 | 0 | — |
case-06 | fail→pass | 14,824 | 15,646 | +6% | 1 | 1 | 0% | 2,479 | 4,220 | +70% | 0 | 0 | — |
case-07 | fail→fail | 18,186 | 14,616 | -20% | 1 | 1 | 0% | 3,363 | 4,491 | +34% | 0 | 0 | — |
case-09 | pass→pass | 9,697 | 9,597 | -1% | 1 | 1 | 0% | 1,820 | 3,347 | +84% | 0 | 0 | — |
case-10 | pass→pass | 10,721 | 7,459 | -30% | 1 | 1 | 0% | 1,870 | 2,928 | +57% | 0 | 0 | — |
case-11 | pass→pass | 11,564 | 8,567 | -26% | 1 | 1 | 0% | 2,030 | 3,131 | +54% | 0 | 0 | — |
case-12 | pass→pass | 14,164 | 10,449 | -26% | 1 | 1 | 0% | 2,716 | 3,537 | +30% | 0 | 0 | — |
case-13 | pass→pass | 14,790 | 11,983 | -19% | 1 | 1 | 0% | 2,613 | 3,651 | +40% | 0 | 0 | — |
case-18 | pass→pass | 17,937 | 11,773 | -34% | 1 | 1 | 0% | 2,763 | 3,242 | +17% | 0 | 0 | — |
case-14 | pass→pass | 10,666 | 8,498 | -20% | 1 | 1 | 0% | 1,802 | 2,877 | +60% | 0 | 0 | — |
case-15 | pass→pass | 8,889 | 7,386 | -17% | 1 | 1 | 0% | 1,524 | 2,771 | +82% | 0 | 0 | — |
case-16 | pass→pass | 15,137 | 12,094 | -20% | 1 | 1 | 0% | 2,311 | 3,445 | +49% | 0 | 0 | — |
case-17 | pass→pass | 12,366 | 10,266 | -17% | 1 | 1 | 0% | 1,885 | 3,162 | +68% | 0 | 0 | — |
case-20 | pass→pass | 11,430 | 5,392 | -53% | 1 | 1 | 0% | 1,741 | 2,387 | +37% | 0 | 0 | — |
case-21 | pass→pass | 15,734 | 13,528 | -14% | 1 | 1 | 0% | 2,474 | 3,572 | +44% | 0 | 0 | — |
case-22 | fail→pass | 7,271 | 1,695 | -77% | 1 | 1 | 0% | 1,082 | 1,718 | +59% | 0 | 0 | — |
case-23 | pass→pass | 18,196 | 19,393 | +7% | 1 | 1 | 0% | 2,783 | 4,520 | +62% | 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 +22 percentage points is the difference between those two pass rates over the 23 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.