Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when auditing page metadata or generating SEO-optimized titles. Applies to every HTML page that should appear in search results.
.claude/skills/thedaviddias-meta-title/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 7% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 10% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 1% | 0% |
The <title> tag is the most prominent element in search result listings and browser tabs—it directly influences click-through rates and is a confirmed Google ranking signal.
Check the <head> section for a <title> tag. Verify it is unique (not duplicated on other pages), between 10 and 60 characters, and contains the page's primary keyword.
Add or update the <title> tag in <head>. Write a descriptive title of 50–60 characters that includes the primary keyword near the start and is unique across the site. Do not stuff keywords.
The <title> tag appears as the clickable headline in search results and browser tabs. It is a primary on-page SEO factor—Google uses it to understand what the page is about and displays it to users deciding whether to click.
Check the <head> for a <title> element. Verify: (1) exactly one <title> tag exists, (2) text content is between 10 and 60 characters, (3) the title is not identical to other pages' titles, (4) the primary keyword appears in the first half of the title, (5) the title is not empty or contains only a brand name.
For full implementation details, code examples, and framework-specific guidance, see references/rule.md.
Rule page: https://frontendchecklist.io/en/rules/seo/meta-title
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 9,466 | 8,786 | -7% | 1 | 1 | 0% | 1,720 | 1,836 | +7% | 0 | 0 | — |
case-02 | pass→pass | 9,420 | 7,122 | -24% | 1 | 1 | 0% | 1,412 | 1,548 | +10% | 0 | 0 | — |
case-03 | pass→pass | 11,171 | 8,774 | -21% | 1 | 1 | 0% | 1,587 | 1,605 | +1% | 0 | 0 | — |
case-04 | pass→pass | 4,245 | 3,841 | -10% | 1 | 1 | 0% | 618 | 957 | +55% | 0 | 0 | — |
case-05 | fail→pass | 8,554 | 5,498 | -36% | 1 | 1 | 0% | 1,280 | 1,279 | -0% | 0 | 0 | — |
case-06 | pass→pass | 4,824 | 3,372 | -30% | 1 | 1 | 0% | 635 | 913 | +44% | 0 | 0 | — |
case-07 | pass→pass | 7,991 | 5,033 | -37% | 1 | 1 | 0% | 1,111 | 1,203 | +8% | 0 | 0 | — |
case-08 | pass→pass | 5,608 | 5,157 | -8% | 1 | 1 | 0% | 816 | 1,140 | +40% | 0 | 0 | — |
case-09 | pass→pass | 9,437 | 9,080 | -4% | 1 | 1 | 0% | 1,342 | 1,663 | +24% | 0 | 0 | — |
case-10 | fail→fail | 5,562 | 6,702 | +20% | 1 | 1 | 0% | 782 | 1,466 | +87% | 0 | 0 | — |
case-11 | pass→pass | 8,396 | 4,765 | -43% | 1 | 1 | 0% | 1,256 | 1,192 | -5% | 0 | 0 | — |
case-12 | pass→pass | 10,459 | 10,126 | -3% | 1 | 1 | 0% | 1,552 | 1,825 | +18% | 0 | 0 | — |
case-13 | pass→pass | 7,300 | 5,985 | -18% | 1 | 1 | 0% | 1,094 | 1,400 | +28% | 0 | 0 | — |
case-14 | pass→pass | 5,306 | 4,736 | -11% | 1 | 1 | 0% | 864 | 1,199 | +39% | 0 | 0 | — |
case-15 | fail→pass | 8,708 | 6,407 | -26% | 1 | 1 | 0% | 1,397 | 1,331 | -5% | 0 | 0 | — |
case-16 | pass→pass | 8,404 | 6,350 | -24% | 1 | 1 | 0% | 1,425 | 1,401 | -2% | 0 | 0 | — |
case-17 | pass→pass | 7,400 | 4,579 | -38% | 1 | 1 | 0% | 1,256 | 1,192 | -5% | 0 | 0 | — |
case-18 | pass→pass | 11,877 | 3,903 | -67% | 1 | 1 | 0% | 1,888 | 967 | -49% | 0 | 0 | — |
case-19 | pass→pass | 8,759 | 4,978 | -43% | 1 | 1 | 0% | 1,381 | 1,242 | -10% | 0 | 0 | — |
case-20 | pass→pass | 6,541 | 3,791 | -42% | 1 | 1 | 0% | 1,127 | 1,015 | -10% | 0 | 0 | — |
case-21 | pass→pass | 8,570 | 6,771 | -21% | 1 | 1 | 0% | 1,455 | 1,521 | +5% | 0 | 0 | — |
case-22 | pass→pass | 11,949 | 12,527 | +5% | 1 | 1 | 0% | 1,982 | 2,294 | +16% | 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.