Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when auditing YMYL content pages for trust signals, generating disclaimer copy for medical or financial content, or reviewing affiliate disclosure requirements under FTC or ASA guidelines.
.claude/skills/thedaviddias-disclaimers/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 7% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 18% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 17% | 0% |
Google's Search Quality Rater Guidelines classify health, finance, and legal topics as 'Your Money or Your Life' (YMYL) pages that are held to the highest trust standards. Pages lacking appropriate disclaimers score low on Trustworthiness within the E-E-A-T framework, suppressing their rankings.
Identify pages covering medical, legal, financial, safety, or affiliate content. For each, check: (1) Is there a visible disclaimer stating the content does not constitute professional advice? (2) For affiliate content, is there an FTC-compliant disclosure before the first affiliate link? (3) Is the disclaimer placed prominently — not hidden in footers or after lengthy content?
Google evaluates YMYL pages under its E-E-A-T (Experience, Expertise, Authoritativeness, Trustworthiness) framework. Missing disclaimers on sensitive topics reduce the Trustworthiness score, which quality raters assign and which influences how Google ranks those pages. Disclaimers also reduce legal risk and meet regulatory requirements (FTC in the US, ASA in the UK for affiliates).
Scan page content for YMYL topic keywords (medical symptoms, drug names, investment advice, legal rights, etc.). If found, check for a disclaimer element near the top of <main> or <article>. Verify affiliate pages include FTC-compliant disclosure text before the first <a> with a referral parameter or affiliate domain.
For full implementation details, code examples, and framework-specific guidance, see references/rule.md.
Rule page: https://frontendchecklist.io/en/rules/seo/disclaimers
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 9,248 | 5,920 | -36% | 1 | 1 | 0% | 1,558 | 1,671 | +7% | 0 | 0 | — |
case-02 | pass→pass | 8,944 | 8,430 | -6% | 1 | 1 | 0% | 1,906 | 2,253 | +18% | 0 | 0 | — |
case-03 | pass→pass | 7,386 | 4,681 | -37% | 1 | 1 | 0% | 1,310 | 1,529 | +17% | 0 | 0 | — |
case-04 | pass→pass | 7,062 | 6,238 | -12% | 1 | 1 | 0% | 1,221 | 1,895 | +55% | 0 | 0 | — |
case-05 | pass→pass | 5,333 | 4,188 | -21% | 1 | 1 | 0% | 895 | 1,384 | +55% | 0 | 0 | — |
case-06 | pass→pass | 8,727 | 7,782 | -11% | 1 | 1 | 0% | 1,687 | 2,069 | +23% | 0 | 0 | — |
case-07 | pass→pass | 13,259 | 11,969 | -10% | 1 | 1 | 0% | 2,668 | 2,968 | +11% | 0 | 0 | — |
case-08 | pass→pass | 8,020 | 5,014 | -37% | 1 | 1 | 0% | 1,390 | 1,503 | +8% | 0 | 0 | — |
case-09 | pass→pass | 11,349 | 8,758 | -23% | 1 | 1 | 0% | 1,971 | 2,259 | +15% | 0 | 0 | — |
case-10 | pass→pass | 9,119 | 10,558 | +16% | 1 | 1 | 0% | 1,602 | 2,461 | +54% | 0 | 0 | — |
case-11 | fail→pass | 9,797 | 6,057 | -38% | 1 | 1 | 0% | 2,163 | 1,719 | -21% | 0 | 0 | — |
case-12 | pass→pass | 5,026 | 2,036 | -59% | 1 | 1 | 0% | 922 | 974 | +6% | 0 | 0 | — |
case-13 | pass→pass | 5,807 | 3,342 | -42% | 1 | 1 | 0% | 1,000 | 911 | -9% | 0 | 0 | — |
case-14 | pass→pass | 6,143 | 3,087 | -50% | 1 | 1 | 0% | 1,067 | 1,207 | +13% | 0 | 0 | — |
case-15 | pass→pass | 3,584 | 2,742 | -23% | 1 | 1 | 0% | 590 | 1,083 | +84% | 0 | 0 | — |
case-16 | fail→pass | 11,303 | 8,173 | -28% | 1 | 1 | 0% | 1,922 | 2,132 | +11% | 0 | 0 | — |
case-17 | pass→pass | 8,242 | 3,143 | -62% | 1 | 1 | 0% | 1,439 | 1,121 | -22% | 0 | 0 | — |
case-18 | pass→pass | 13,229 | 6,678 | -50% | 1 | 1 | 0% | 2,143 | 1,675 | -22% | 0 | 0 | — |
case-19 | pass→pass | 4,304 | 2,077 | -52% | 1 | 1 | 0% | 742 | 984 | +33% | 0 | 0 | — |
case-20 | pass→pass | 7,189 | 5,744 | -20% | 1 | 1 | 0% | 1,286 | 1,489 | +16% | 0 | 0 | — |
case-21 | pass→pass | 9,855 | 6,957 | -29% | 1 | 1 | 0% | 1,507 | 1,863 | +24% | 0 | 0 | — |
case-22 | pass→pass | 8,578 | 6,804 | -21% | 1 | 1 | 0% | 1,461 | 1,780 | +22% | 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.