Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when auditing article or blog pages for date markup, generating Article JSON-LD with datePublished/dateModified, or checking whether a CMS template surfaces dates correctly.
.claude/skills/thedaviddias-content-dates/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 14% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 6% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 9% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 43% | 0% |
Google uses publication and modification dates to assess content freshness, which influences rankings for time-sensitive queries. Visible dates also build user trust by signalling that content is current and maintained.
dateModified in JSON-LD for every article or blog post2024-03-15T10:00:00Z) in structured data; human-readable in the visible UIdateModified only when content meaningfully changes — not on trivial editsOn each article or blog page, check: (1) Is there a visible published date in the page body or byline? (2) Does the JSON-LD Article or BlogPosting block include datePublished and dateModified properties in ISO 8601 format? (3) Does the <head> include <meta property="article:published_time"> and <meta property="article:modified_time"> Open Graph tags?
<time datetime="2024-03-15">March 15, 2024</time>.datePublished and dateModified to the Article JSON-LD block:json { "@type": "Article", "datePublished": "2024-03-15T10:00:00Z", "dateModified": "2024-11-20T14:30:00Z" }
<head>:html <meta property="article:published_time" content="2024-03-15T10:00:00Z"> <meta property="article:modified_time" content="2024-11-20T14:30:00Z">
dateModified automatically on content saves.Google's freshness algorithm rewards recently published or updated content for time-sensitive queries. Structured date markup lets Google confidently surface the correct date in search snippets; without it, Google must guess from page text or HTTP headers, often producing wrong or missing dates.
Verify that Article or BlogPosting JSON-LD includes both datePublished and dateModified in ISO 8601 format. Check that <time datetime='...'> elements in the body use machine-readable dates. Confirm dateModified updates when content changes, not just on every deploy.
For full implementation details, code examples, and framework-specific guidance, see references/rule.md.
Rule page: https://frontendchecklist.io/en/rules/seo/content-dates
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 11,007 | 10,721 | -3% | 1 | 1 | 0% | 2,473 | 2,830 | +14% | 0 | 0 | — |
case-02 | pass→pass | 12,065 | 10,049 | -17% | 1 | 1 | 0% | 2,045 | 2,338 | +14% | 0 | 0 | — |
case-03 | pass→pass | 9,152 | 5,493 | -40% | 1 | 1 | 0% | 1,760 | 1,861 | +6% | 0 | 0 | — |
case-04 | pass→pass | 7,016 | 3,557 | -49% | 1 | 1 | 0% | 1,304 | 1,425 | +9% | 0 | 0 | — |
case-05 | pass→pass | 4,744 | 3,633 | -23% | 1 | 1 | 0% | 937 | 1,336 | +43% | 0 | 0 | — |
case-06 | pass→pass | 5,400 | 3,231 | -40% | 1 | 1 | 0% | 1,227 | 1,240 | +1% | 0 | 0 | — |
case-07 | pass→pass | 11,404 | 6,682 | -41% | 1 | 1 | 0% | 1,789 | 1,648 | -8% | 0 | 0 | — |
case-08 | pass→pass | 13,246 | 8,694 | -34% | 1 | 1 | 0% | 2,282 | 2,215 | -3% | 0 | 0 | — |
case-09 | pass→pass | 4,957 | 2,923 | -41% | 1 | 1 | 0% | 1,158 | 1,217 | +5% | 0 | 0 | — |
case-10 | pass→pass | 8,322 | 4,457 | -46% | 1 | 1 | 0% | 1,492 | 1,498 | +0% | 0 | 0 | — |
case-11 | pass→pass | 4,690 | 2,825 | -40% | 1 | 1 | 0% | 1,020 | 1,218 | +19% | 0 | 0 | — |
case-12 | pass→pass | 14,391 | 10,979 | -24% | 1 | 1 | 0% | 2,479 | 2,494 | +1% | 0 | 0 | — |
case-22 | pass→pass | 13,593 | 11,546 | -15% | 1 | 1 | 0% | 2,471 | 2,744 | +11% | 0 | 0 | — |
case-13 | pass→pass | 3,097 | 2,934 | -5% | 1 | 1 | 0% | 713 | 1,226 | +72% | 0 | 0 | — |
case-14 | pass→pass | 9,466 | 6,538 | -31% | 1 | 1 | 0% | 1,642 | 1,865 | +14% | 0 | 0 | — |
case-15 | pass→pass | 9,351 | 5,699 | -39% | 1 | 1 | 0% | 1,919 | 1,979 | +3% | 0 | 0 | — |
case-16 | pass→pass | 8,084 | 3,508 | -57% | 1 | 1 | 0% | 1,574 | 1,448 | -8% | 0 | 0 | — |
case-17 | pass→pass | 10,363 | 8,742 | -16% | 1 | 1 | 0% | 1,696 | 1,986 | +17% | 0 | 0 | — |
case-18 | pass→pass | 9,923 | 3,155 | -68% | 1 | 1 | 0% | 2,136 | 1,283 | -40% | 0 | 0 | — |
case-19 | pass→pass | 11,819 | 7,548 | -36% | 1 | 1 | 0% | 2,001 | 2,164 | +8% | 0 | 0 | — |
case-20 | pass→pass | 11,517 | 12,747 | +11% | 1 | 1 | 0% | 2,193 | 3,205 | +46% | 0 | 0 | — |
case-21 | pass→pass | 10,628 | 8,011 | -25% | 1 | 1 | 0% | 2,408 | 2,416 | +0% | 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 +5 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.