Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when auditing a site's internal link graph for dead-end pages, suggesting related-content links to add to thin or standalone pages, or reviewing CMS templates that produce link-free content pages.
.claude/skills/thedaviddias-dead-end-pages/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 34% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -13% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 15% | 0% |
Googlebot follows links to discover and re-crawl pages. A page with no outgoing internal links stops the crawler from reaching the rest of your site from that point and leaves users with nowhere logical to go, increasing bounce rate.
For each page, count the number of <a href> links pointing to other pages on the same domain (exclude navigation/header/footer if they are templated identically across all pages). Flag any page with zero or fewer than two unique internal links in the main content body (<main> or <article> element).
Internal links are the edges of your site's graph. Crawlers navigate by following links; a page with no outgoing links is a node with no edges leading forward. This prevents Googlebot from discovering linked pages during a crawl initiated from that dead end, and it signals to users that there is nothing more to explore.
Parse the <main> or <article> element of each rendered page. Count <a href> tags pointing to same-domain URLs. Flag pages with fewer than 2 such links. Exclude navigation, header, and footer elements that are shared across all pages, as these do not count as contextual internal links.
For full implementation details, code examples, and framework-specific guidance, see references/rule.md.
Rule page: https://frontendchecklist.io/en/rules/seo/dead-end-pages
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-11 | fail→pass | 6,433 | 3,665 | -43% | 1 | 1 | 0% | 1,193 | 1,261 | +6% | 0 | 0 | — |
case-01 | fail→fail | 14,337 | 11,192 | -22% | 1 | 1 | 0% | 2,488 | 2,603 | +5% | 0 | 0 | — |
case-02 | fail→pass | 15,367 | 16,024 | +4% | 1 | 1 | 0% | 2,790 | 3,749 | +34% | 0 | 0 | — |
case-03 | pass→fail | 12,833 | 12,939 | +1% | 1 | 1 | 0% | 2,309 | 2,853 | +24% | 0 | 0 | — |
case-04 | pass→pass | 14,290 | 10,240 | -28% | 1 | 1 | 0% | 2,211 | 2,535 | +15% | 0 | 0 | — |
case-05 | pass→fail | 12,404 | 11,943 | -4% | 1 | 1 | 0% | 2,537 | 3,008 | +19% | 0 | 0 | — |
case-06 | pass→pass | 10,130 | 5,479 | -46% | 1 | 1 | 0% | 1,718 | 1,670 | -3% | 0 | 0 | — |
case-07 | fail→pass | 10,869 | 5,857 | -46% | 1 | 1 | 0% | 1,854 | 1,606 | -13% | 0 | 0 | — |
case-08 | fail→pass | 8,384 | 3,037 | -64% | 1 | 1 | 0% | 1,533 | 1,091 | -29% | 0 | 0 | — |
case-09 | pass→pass | 11,336 | 7,784 | -31% | 1 | 1 | 0% | 1,978 | 1,970 | -0% | 0 | 0 | — |
case-10 | fail→fail | 14,512 | 13,070 | -10% | 1 | 1 | 0% | 2,694 | 3,134 | +16% | 0 | 0 | — |
case-12 | pass→pass | 12,385 | 4,405 | -64% | 1 | 1 | 0% | 2,112 | 1,281 | -39% | 0 | 0 | — |
case-13 | pass→pass | 11,962 | 8,626 | -28% | 1 | 1 | 0% | 1,806 | 2,065 | +14% | 0 | 0 | — |
case-14 | pass→pass | 13,852 | 10,790 | -22% | 1 | 1 | 0% | 2,256 | 2,393 | +6% | 0 | 0 | — |
case-15 | fail→pass | 8,277 | 5,880 | -29% | 1 | 1 | 0% | 1,496 | 1,717 | +15% | 0 | 0 | — |
case-20 | fail→pass | 28,904 | 13,436 | -54% | 1 | 1 | 0% | 1,409 | 2,690 | +91% | 0 | 0 | — |
case-16 | pass→pass | 8,267 | 4,771 | -42% | 1 | 1 | 0% | 1,474 | 1,251 | -15% | 0 | 0 | — |
case-17 | pass→pass | 13,638 | 11,973 | -12% | 1 | 1 | 0% | 2,262 | 2,543 | +12% | 0 | 0 | — |
case-18 | pass→pass | 9,258 | 8,945 | -3% | 1 | 1 | 0% | 1,675 | 2,168 | +29% | 0 | 0 | — |
case-19 | fail→pass | 10,475 | 7,271 | -31% | 1 | 1 | 0% | 1,762 | 1,789 | +2% | 0 | 0 | — |
case-21 | pass→pass | 7,339 | 2,879 | -61% | 1 | 1 | 0% | 1,266 | 1,068 | -16% | 0 | 0 | — |
case-22 | fail→fail | 17,249 | 16,594 | -4% | 1 | 1 | 0% | 3,160 | 3,829 | +21% | 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, and 21 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +23 percentage points is the difference between those two pass rates over the 21 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.