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 Allow pasting into form inputs. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.
.claude/skills/thedaviddias-paste-inputs/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -4% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-22 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 0% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 0% | 0% |
Restricting pasting makes it difficult for users to use password managers or copy-paste long strings of data, which can lead to increased errors and a poor user experience.
onpaste="return false" from all input elementsCheck the codebase for any JavaScript or HTML attributes that prevent users from pasting into form fields.
Remove any code (e.g., onpaste="return false") that blocks the default paste behavior in inputs.
Explain how allowing pasting into forms improves security and accessibility for users with physical or cognitive disabilities.
Review the rendered markup and interactive states that affect Allow pasting into form inputs. 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/paste-inputs
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 11,437 | 10,652 | -7% | 1 | 1 | 0% | 2,180 | 2,092 | -4% | 0 | 0 | — |
case-02 | pass→pass | 11,621 | 9,355 | -19% | 1 | 1 | 0% | 2,135 | 2,129 | -0% | 0 | 0 | — |
case-03 | pass→pass | 11,208 | 9,594 | -14% | 1 | 1 | 0% | 1,944 | 1,937 | -0% | 0 | 0 | — |
case-04 | pass→pass | 14,981 | 12,608 | -16% | 1 | 1 | 0% | 2,434 | 2,415 | -1% | 0 | 0 | — |
case-05 | pass→pass | 14,642 | 9,406 | -36% | 1 | 1 | 0% | 2,536 | 2,047 | -19% | 0 | 0 | — |
case-06 | pass→pass | 11,574 | 10,314 | -11% | 1 | 1 | 0% | 1,945 | 2,038 | +5% | 0 | 0 | — |
case-07 | pass→pass | 10,304 | 12,183 | +18% | 1 | 1 | 0% | 1,855 | 2,556 | +38% | 0 | 0 | — |
case-08 | pass→pass | 8,511 | 6,874 | -19% | 1 | 1 | 0% | 1,533 | 1,445 | -6% | 0 | 0 | — |
case-09 | fail→pass | 10,907 | 7,685 | -30% | 1 | 1 | 0% | 1,951 | 1,633 | -16% | 0 | 0 | — |
case-10 | pass→pass | 8,912 | 7,428 | -17% | 1 | 1 | 0% | 1,638 | 1,592 | -3% | 0 | 0 | — |
case-11 | pass→pass | 14,809 | 10,947 | -26% | 1 | 1 | 0% | 2,460 | 2,188 | -11% | 0 | 0 | — |
case-12 | fail→fail | 16,423 | 12,579 | -23% | 1 | 1 | 0% | 2,831 | 2,465 | -13% | 0 | 0 | — |
case-13 | pass→pass | 10,599 | 8,040 | -24% | 1 | 1 | 0% | 2,000 | 1,805 | -10% | 0 | 0 | — |
case-14 | pass→pass | 10,192 | 6,017 | -41% | 1 | 1 | 0% | 1,819 | 1,276 | -30% | 0 | 0 | — |
case-15 | pass→pass | 10,242 | 10,409 | +2% | 1 | 1 | 0% | 1,976 | 2,133 | +8% | 0 | 0 | — |
case-21 | pass→pass | 10,812 | 8,045 | -26% | 1 | 1 | 0% | 2,361 | 1,852 | -22% | 0 | 0 | — |
case-16 | pass→pass | 11,549 | 6,788 | -41% | 1 | 1 | 0% | 1,887 | 1,427 | -24% | 0 | 0 | — |
case-17 | pass→pass | 11,357 | 8,557 | -25% | 1 | 1 | 0% | 2,119 | 1,917 | -10% | 0 | 0 | — |
case-18 | pass→pass | 17,162 | 10,015 | -42% | 1 | 1 | 0% | 2,862 | 1,927 | -33% | 0 | 0 | — |
case-19 | pass→pass | 10,066 | 7,867 | -22% | 1 | 1 | 0% | 2,069 | 1,649 | -20% | 0 | 0 | — |
case-20 | pass→pass | 10,342 | 8,844 | -14% | 1 | 1 | 0% | 2,055 | 1,880 | -9% | 0 | 0 | — |
case-22 | fail→pass | 16,256 | 11,994 | -26% | 1 | 1 | 0% | 2,903 | 2,446 | -16% | 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 +14 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.