Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when reviewing a website for layout and functionality issues caused by adblocker filter rules targeting common ad-related class names and IDs.
.claude/skills/thedaviddias-element-hiding/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -13% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-21 | ✗→✓ | ▲ Improved | 31% | 0% |
If your cookie consent banner has class .cookie-banner or ID #consent-popup, adblockers may hide it — users never see the consent notice, which can cause GDPR compliance issues and broken UX for ~30-40% of desktop users.
.ad, .ads, .advertisement, .banner, #ad, #ads, #banner, .sponsorReview the HTML source for element IDs and class names that match common adblocker patterns: .ad, .ads, .advertisement, .banner, .sponsor, #ad, #banner, .cookie-notice, .consent. Test the page with uBlock Origin enabled in a browser to identify elements that are hidden.
Rename affected elements using specific, content-focused class names that do not match adblocker patterns. For cookie consent banners specifically, use class names like .privacy-controls or .cookie-preferences instead of .cookie-banner or .gdpr-notice.
Explain how adblocker filter lists work, which HTML class names and IDs are commonly blocked, and how to rename elements to avoid false-positive blocking while maintaining their function.
Review server config, headers, forms, and integration points related to Adblock Element Hiding. Flag exact responses, cookies, or browser behaviors that violate the rule, and verify them against the effective production-like response.
For full implementation details, code examples, and framework-specific guidance, see references/rule.md.
Rule page: https://frontendchecklist.io/en/rules/security/element-hiding
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 13,269 | 8,623 | -35% | 1 | 1 | 0% | 2,447 | 2,120 | -13% | 0 | 0 | — |
case-02 | pass→pass | 9,621 | 4,935 | -49% | 1 | 1 | 0% | 1,626 | 1,255 | -23% | 0 | 0 | — |
case-03 | pass→pass | 8,439 | 5,340 | -37% | 1 | 1 | 0% | 1,548 | 1,658 | +7% | 0 | 0 | — |
case-04 | pass→pass | 7,848 | 5,226 | -33% | 1 | 1 | 0% | 1,462 | 1,464 | +0% | 0 | 0 | — |
case-05 | pass→pass | 6,974 | 4,481 | -36% | 1 | 1 | 0% | 1,305 | 1,127 | -14% | 0 | 0 | — |
case-06 | fail→pass | 10,516 | 7,807 | -26% | 1 | 1 | 0% | 1,870 | 1,686 | -10% | 0 | 0 | — |
case-07 | pass→pass | 12,379 | 7,711 | -38% | 1 | 1 | 0% | 1,989 | 1,911 | -4% | 0 | 0 | — |
case-08 | pass→pass | 7,520 | 5,670 | -25% | 1 | 1 | 0% | 1,318 | 1,510 | +15% | 0 | 0 | — |
case-09 | pass→pass | 15,454 | 14,357 | -7% | 1 | 1 | 0% | 2,577 | 2,632 | +2% | 0 | 0 | — |
case-10 | fail→fail | 11,665 | 5,362 | -54% | 1 | 1 | 0% | 1,921 | 1,383 | -28% | 0 | 0 | — |
case-11 | pass→pass | 9,261 | 6,057 | -35% | 1 | 1 | 0% | 1,640 | 1,538 | -6% | 0 | 0 | — |
case-12 | fail→pass | 5,845 | 2,991 | -49% | 1 | 1 | 0% | 1,100 | 1,146 | +4% | 0 | 0 | — |
case-13 | fail→pass | 30,772 | 3,150 | -90% | 1 | 1 | 0% | 1,349 | 862 | -36% | 0 | 0 | — |
case-14 | pass→pass | 10,285 | 6,775 | -34% | 1 | 1 | 0% | 1,785 | 1,725 | -3% | 0 | 0 | — |
case-15 | pass→pass | 4,102 | 5,110 | +25% | 1 | 1 | 0% | 887 | 1,393 | +57% | 0 | 0 | — |
case-16 | fail→fail | 8,944 | 5,949 | -33% | 1 | 1 | 0% | 1,646 | 1,535 | -7% | 0 | 0 | — |
case-17 | pass→pass | 6,864 | 2,083 | -70% | 1 | 1 | 0% | 1,292 | 811 | -37% | 0 | 0 | — |
case-18 | pass→pass | 17,194 | 13,816 | -20% | 1 | 1 | 0% | 2,841 | 2,714 | -4% | 0 | 0 | — |
case-19 | pass→pass | 15,121 | 9,772 | -35% | 1 | 1 | 0% | 2,791 | 2,216 | -21% | 0 | 0 | — |
case-20 | pass→pass | 4,173 | 4,293 | +3% | 1 | 1 | 0% | 716 | 1,271 | +78% | 0 | 0 | — |
case-21 | fail→pass | 12,577 | 13,775 | +10% | 1 | 1 | 0% | 2,432 | 3,190 | +31% | 0 | 0 | — |
case-22 | pass→pass | 6,543 | 4,891 | -25% | 1 | 1 | 0% | 1,303 | 1,350 | +4% | 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.
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.