Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when applies to all HTML pages. Use when auditing a site crawl report or investigating why multiple pages compete for the same keyword in search results.
.claude/skills/thedaviddias-title-unique/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-07 | ✓→✓ | ＝ Same ✓ | -7% | 0% |
| case-14 | ✓→✓ | ＝ Same ✓ | 5% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 29% | 0% |
Duplicate titles prevent Google from determining which page is the authoritative result for a given query, splitting ranking signals and reducing total organic visibility.
<title> tag with content unique across the entire site[Page Topic] | [Brand] patternCrawl all pages and extract <title> tag content. Group pages by identical title text and flag duplicates. Also flag pages with no title, empty titles, or titles matching the CMS default (e.g., 'Home', 'Page', 'Untitled').
Give each page a descriptive, unique title incorporating the page's primary keyword: [Specific Topic] – [Site Name]. For blog posts: use the post title. For products: use product name + key differentiator. For category pages: use the category name + context.
Explain how duplicate titles affect crawl budget, indexing prioritization, and keyword ranking; and why Google rewrites titles it considers misleading or non-descriptive.
Review metadata generation, rendered HTML, structured data, and response headers related to Keep page titles unique. 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/title-unique
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-07 | pass→pass | 10,411 | 7,921 | -24% | 1 | 1 | 0% | 1,783 | 1,662 | -7% | 0 | 0 | — |
case-14 | pass→pass | 15,949 | 13,752 | -14% | 1 | 1 | 0% | 2,439 | 2,566 | +5% | 0 | 0 | — |
case-01 | fail→pass | 15,659 | 15,214 | -3% | 1 | 1 | 0% | 2,860 | 2,991 | +5% | 0 | 0 | — |
case-02 | pass→pass | 10,070 | 9,537 | -5% | 1 | 1 | 0% | 1,682 | 2,177 | +29% | 0 | 0 | — |
case-03 | pass→pass | 12,811 | 10,637 | -17% | 1 | 1 | 0% | 2,035 | 2,120 | +4% | 0 | 0 | — |
case-04 | pass→pass | 9,194 | 8,890 | -3% | 1 | 1 | 0% | 1,564 | 1,942 | +24% | 0 | 0 | — |
case-05 | pass→pass | 9,990 | 10,341 | +4% | 1 | 1 | 0% | 1,842 | 2,227 | +21% | 0 | 0 | — |
case-06 | pass→pass | 10,766 | 9,658 | -10% | 1 | 1 | 0% | 1,766 | 2,104 | +19% | 0 | 0 | — |
case-08 | pass→pass | 11,925 | 11,992 | +1% | 1 | 1 | 0% | 2,044 | 2,438 | +19% | 0 | 0 | — |
case-09 | pass→pass | 11,004 | 12,539 | +14% | 1 | 1 | 0% | 1,804 | 2,573 | +43% | 0 | 0 | — |
case-10 | pass→pass | 16,246 | 9,230 | -43% | 1 | 1 | 0% | 2,729 | 1,980 | -27% | 0 | 0 | — |
case-11 | pass→pass | 12,141 | 10,736 | -12% | 1 | 1 | 0% | 2,218 | 2,111 | -5% | 0 | 0 | — |
case-12 | fail→fail | 12,921 | 11,237 | -13% | 1 | 1 | 0% | 2,689 | 2,626 | -2% | 0 | 0 | — |
case-13 | pass→pass | 16,820 | 14,565 | -13% | 1 | 1 | 0% | 2,856 | 3,261 | +14% | 0 | 0 | — |
case-15 | pass→pass | 10,129 | 8,158 | -19% | 1 | 1 | 0% | 1,801 | 1,771 | -2% | 0 | 0 | — |
case-16 | fail→pass | 17,006 | 14,615 | -14% | 1 | 1 | 0% | 2,825 | 2,686 | -5% | 0 | 0 | — |
case-17 | pass→pass | 9,531 | 6,023 | -37% | 1 | 1 | 0% | 1,631 | 1,321 | -19% | 0 | 0 | — |
case-18 | pass→pass | 11,266 | 9,457 | -16% | 1 | 1 | 0% | 1,906 | 1,900 | -0% | 0 | 0 | — |
case-19 | pass→pass | 12,235 | 12,047 | -2% | 1 | 1 | 0% | 1,900 | 2,273 | +20% | 0 | 0 | — |
case-20 | pass→pass | 11,289 | 8,018 | -29% | 1 | 1 | 0% | 1,980 | 1,785 | -10% | 0 | 0 | — |
case-21 | pass→pass | 14,363 | 8,997 | -37% | 1 | 1 | 0% | 2,265 | 1,951 | -14% | 0 | 0 | — |
case-22 | pass→pass | 8,592 | 6,926 | -19% | 1 | 1 | 0% | 1,426 | 1,491 | +5% | 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 +9 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.