Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when applies primarily when creating new content pages. Low priority for existing indexed pages where redirect risk outweighs gain. Use when building a slug naming convention.
.claude/skills/thedaviddias-stop-words/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 20% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -24% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 4% | 0% |
Shorter, keyword-focused URL slugs are easier for users to read and share; removing stop words is a minor hygiene improvement, especially for new content.
Analyze URL slugs on content pages and flag stop words in the path (e.g., /blog/the-best-ways-to-improve-your-seo could be /blog/best-ways-improve-seo). Focus on new pages; do not flag established pages with backlinks unless redirects are already planned.
For new pages, configure the CMS or slug generator to strip common stop words automatically. For existing pages, only remove stop words if a URL overhaul with proper 301 redirects is already planned.
Explain what stop words are in the context of URLs, why modern search engines handle them fine in page content but slugs benefit from brevity, and when it is not worth changing existing URLs.
Review metadata generation, rendered HTML, structured data, and response headers related to URL Stop Words. 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/stop-words
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 12,347 | 11,868 | -4% | 1 | 1 | 0% | 2,125 | 2,591 | +22% | 0 | 0 | — |
case-02 | pass→pass | 10,973 | 4,816 | -56% | 1 | 1 | 0% | 1,827 | 1,254 | -31% | 0 | 0 | — |
case-03 | pass→pass | 11,896 | 8,914 | -25% | 1 | 1 | 0% | 2,101 | 2,109 | +0% | 0 | 0 | — |
case-04 | pass→pass | 12,865 | 11,225 | -13% | 1 | 1 | 0% | 2,162 | 2,156 | -0% | 0 | 0 | — |
case-05 | fail→pass | 10,464 | 10,108 | -3% | 1 | 1 | 0% | 1,734 | 2,080 | +20% | 0 | 0 | — |
case-06 | fail→pass | 15,274 | 8,450 | -45% | 1 | 1 | 0% | 2,625 | 1,875 | -29% | 0 | 0 | — |
case-07 | pass→pass | 8,533 | 5,414 | -37% | 1 | 1 | 0% | 1,413 | 1,394 | -1% | 0 | 0 | — |
case-08 | pass→pass | 12,058 | 5,794 | -52% | 1 | 1 | 0% | 1,937 | 1,385 | -28% | 0 | 0 | — |
case-09 | pass→pass | 9,478 | 5,157 | -46% | 1 | 1 | 0% | 1,656 | 1,297 | -22% | 0 | 0 | — |
case-10 | pass→pass | 10,335 | 5,044 | -51% | 1 | 1 | 0% | 1,812 | 1,332 | -26% | 0 | 0 | — |
case-11 | pass→pass | 6,238 | 5,144 | -18% | 1 | 1 | 0% | 1,169 | 1,343 | +15% | 0 | 0 | — |
case-12 | pass→pass | 12,450 | 7,970 | -36% | 1 | 1 | 0% | 2,131 | 1,792 | -16% | 0 | 0 | — |
case-13 | pass→pass | 10,159 | 9,225 | -9% | 1 | 1 | 0% | 1,701 | 1,962 | +15% | 0 | 0 | — |
case-14 | fail→pass | 11,196 | 5,973 | -47% | 1 | 1 | 0% | 1,896 | 1,448 | -24% | 0 | 0 | — |
case-15 | fail→pass | 14,233 | 12,976 | -9% | 1 | 1 | 0% | 2,746 | 2,859 | +4% | 0 | 0 | — |
case-16 | pass→pass | 9,306 | 7,995 | -14% | 1 | 1 | 0% | 1,726 | 1,835 | +6% | 0 | 0 | — |
case-17 | pass→pass | 11,639 | 7,182 | -38% | 1 | 1 | 0% | 1,920 | 1,624 | -15% | 0 | 0 | — |
case-18 | pass→pass | 10,879 | 6,068 | -44% | 1 | 1 | 0% | 1,890 | 1,442 | -24% | 0 | 0 | — |
case-19 | pass→pass | 7,666 | 3,706 | -52% | 1 | 1 | 0% | 1,314 | 1,026 | -22% | 0 | 0 | — |
case-20 | pass→pass | 11,686 | 8,192 | -30% | 1 | 1 | 0% | 2,197 | 2,003 | -9% | 0 | 0 | — |
case-21 | pass→pass | 13,365 | 12,099 | -9% | 1 | 1 | 0% | 2,306 | 2,470 | +7% | 0 | 0 | — |
case-22 | pass→pass | 8,139 | 8,175 | +0% | 1 | 1 | 0% | 1,469 | 1,863 | +27% | 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 +23 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.