Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when reviewing rendered HTML, interactive components, or design-system patterns related to Write in plain language. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.
.claude/skills/thedaviddias-plain-language/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -4% | 0% |
| case-19 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-16 | ✓→✗ | ▼ Worse | 70% | 0% |
| case-15 | ✓→✓ | ＝ Same ✓ | 1% | 0% |
Plain language helps users with cognitive disabilities, learning differences, attention disorders, non-native speakers, and anyone reading quickly or under stress.
Review content for jargon, complex sentences, and unnecessary technical terms. Verify reading level is appropriate for the audience. Check that instructions are clear and actions are obvious.
Simplify complex sentences. Define technical terms when first used. Use short paragraphs and bullet points. Write in active voice. Target a reading level appropriate for your broadest audience.
Explain how plain language benefits users with cognitive disabilities, learning differences, attention disorders, non-native speakers, and anyone in a hurry or under stress.
Review the rendered markup and interactive states that affect Write in plain language. Flag exact elements, roles, labels, focus behavior, or keyboard interactions that violate the rule, and note how to verify the fix with browser accessibility tooling or assistive tech.
For full implementation details, code examples, and framework-specific guidance, see references/rule.md.
Rule page: https://frontendchecklist.io/en/rules/accessibility/plain-language
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-15 | pass→pass | 9,279 | 7,639 | -18% | 1 | 1 | 0% | 1,638 | 1,658 | +1% | 0 | 0 | — |
case-01 | fail→pass | 12,328 | 12,214 | -1% | 1 | 1 | 0% | 2,327 | 2,550 | +10% | 0 | 0 | — |
case-02 | pass→pass | 6,941 | 6,771 | -2% | 1 | 1 | 0% | 1,245 | 1,542 | +24% | 0 | 0 | — |
case-03 | fail→fail | 6,068 | 7,414 | +22% | 1 | 1 | 0% | 1,127 | 1,681 | +49% | 0 | 0 | — |
case-04 | pass→pass | 6,713 | 5,511 | -18% | 1 | 1 | 0% | 1,217 | 1,211 | -0% | 0 | 0 | — |
case-05 | pass→pass | 11,677 | 9,851 | -16% | 1 | 1 | 0% | 2,084 | 2,213 | +6% | 0 | 0 | — |
case-06 | fail→fail | 7,504 | 8,765 | +17% | 1 | 1 | 0% | 1,438 | 1,863 | +30% | 0 | 0 | — |
case-07 | pass→pass | 12,399 | 8,108 | -35% | 1 | 1 | 0% | 2,010 | 1,594 | -21% | 0 | 0 | — |
case-08 | pass→pass | 10,181 | 7,942 | -22% | 1 | 1 | 0% | 1,763 | 1,707 | -3% | 0 | 0 | — |
case-09 | pass→pass | 4,964 | 3,611 | -27% | 1 | 1 | 0% | 897 | 952 | +6% | 0 | 0 | — |
case-10 | fail→pass | 9,678 | 8,867 | -8% | 1 | 1 | 0% | 1,812 | 1,746 | -4% | 0 | 0 | — |
case-11 | pass→pass | 4,688 | 3,767 | -20% | 1 | 1 | 0% | 935 | 1,022 | +9% | 0 | 0 | — |
case-12 | pass→pass | 4,735 | 5,886 | +24% | 1 | 1 | 0% | 905 | 1,379 | +52% | 0 | 0 | — |
case-13 | pass→pass | 5,588 | 4,323 | -23% | 1 | 1 | 0% | 1,096 | 1,044 | -5% | 0 | 0 | — |
case-14 | pass→pass | 4,786 | 4,022 | -16% | 1 | 1 | 0% | 956 | 996 | +4% | 0 | 0 | — |
case-16 | pass→fail | 5,831 | 8,343 | +43% | 1 | 1 | 0% | 1,112 | 1,889 | +70% | 0 | 0 | — |
case-17 | pass→pass | 8,075 | 4,613 | -43% | 1 | 1 | 0% | 1,327 | 1,077 | -19% | 0 | 0 | — |
case-18 | pass→pass | 4,385 | 4,022 | -8% | 1 | 1 | 0% | 791 | 949 | +20% | 0 | 0 | — |
case-19 | fail→pass | 11,715 | 10,561 | -10% | 1 | 1 | 0% | 2,251 | 2,209 | -2% | 0 | 0 | — |
case-20 | pass→pass | 8,685 | 9,660 | +11% | 1 | 1 | 0% | 2,156 | 2,528 | +17% | 0 | 0 | — |
case-21 | pass→pass | 13,396 | 11,169 | -17% | 1 | 1 | 0% | 2,945 | 2,643 | -10% | 0 | 0 | — |
case-22 | pass→pass | 9,125 | 9,289 | +2% | 1 | 1 | 0% | 1,635 | 2,160 | +32% | 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. 1 case got worse with the skill loaded, and it is included in that figure.
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.