Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when reviewing scripts, client components, bundles, or runtime behavior related to Use ES modules (import/export). Inspect both source code and the browser execution path so fixes target the real bottleneck or bug.
.claude/skills/thedaviddias-es-modules/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-23 | ✗→✓ | ▲ Improved | 231% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 22% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 112% | 0% |
| case-07 | ✓→✓ | ＝ Same ✓ | 180% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | -3% | 0% |
ES modules are statically analyzable — bundlers can determine at build time what code is actually used and eliminate the rest (tree-shaking). CommonJS require() is dynamic and prevents this optimization. ES modules are also the browser-native standard, reducing the need for build-time transformation.
Identify any use of require(), module.exports, or exports in this JavaScript file that should be converted to ES module syntax.
Convert all require() and module.exports statements to ES module import/export syntax.
Explain the benefits of ES modules over CommonJS, including tree-shaking, static analysis, and browser support.
Review scripts, client components, and browser execution paths related to Use ES modules (import/export). Flag exact imports, event handlers, runtime side effects, or blocking operations that violate the rule, and state how the change should be verified in the browser.
For full implementation details, code examples, and framework-specific guidance, see references/rule.md.
Rule page: https://frontendchecklist.io/en/rules/javascript/es-modules
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 5,128 | 4,521 | -12% | 1 | 1 | 0% | 989 | 1,210 | +22% | 0 | 0 | — |
case-02 | pass→pass | 3,267 | 5,519 | +69% | 1 | 1 | 0% | 652 | 1,383 | +112% | 0 | 0 | — |
case-07 | pass→pass | 2,338 | 4,781 | +104% | 1 | 1 | 0% | 479 | 1,341 | +180% | 0 | 0 | — |
case-03 | pass→pass | 8,636 | 6,176 | -28% | 1 | 1 | 0% | 1,501 | 1,461 | -3% | 0 | 0 | — |
case-04 | pass→pass | 3,447 | 5,008 | +45% | 1 | 1 | 0% | 679 | 1,320 | +94% | 0 | 0 | — |
case-05 | pass→pass | 3,005 | 4,086 | +36% | 1 | 1 | 0% | 558 | 1,021 | +83% | 0 | 0 | — |
case-06 | pass→pass | 3,742 | 4,229 | +13% | 1 | 1 | 0% | 884 | 1,213 | +37% | 0 | 0 | — |
case-08 | pass→pass | 7,709 | 4,719 | -39% | 1 | 1 | 0% | 1,340 | 1,131 | -16% | 0 | 0 | — |
case-09 | pass→pass | 13,989 | 10,345 | -26% | 1 | 1 | 0% | 2,586 | 2,169 | -16% | 0 | 0 | — |
case-10 | pass→pass | 8,188 | 5,962 | -27% | 1 | 1 | 0% | 1,631 | 1,546 | -5% | 0 | 0 | — |
case-11 | pass→pass | 1,713 | 3,251 | +90% | 1 | 1 | 0% | 340 | 955 | +181% | 0 | 0 | — |
case-12 | pass→pass | 8,451 | 4,734 | -44% | 1 | 1 | 0% | 1,684 | 1,234 | -27% | 0 | 0 | — |
case-13 | pass→pass | 4,685 | 4,710 | +1% | 1 | 1 | 0% | 813 | 1,163 | +43% | 0 | 0 | — |
case-14 | pass→pass | 1,672 | 4,113 | +146% | 1 | 1 | 0% | 247 | 1,164 | +371% | 0 | 0 | — |
case-15 | pass→pass | 9,012 | 5,348 | -41% | 1 | 1 | 0% | 1,466 | 1,289 | -12% | 0 | 0 | — |
case-16 | pass→pass | 1,250 | 3,183 | +155% | 1 | 1 | 0% | 272 | 836 | +207% | 0 | 0 | — |
case-17 | pass→pass | 4,220 | 7,193 | +70% | 1 | 1 | 0% | 883 | 1,637 | +85% | 0 | 0 | — |
case-18 | pass→pass | 5,122 | 5,556 | +8% | 1 | 1 | 0% | 1,054 | 1,413 | +34% | 0 | 0 | — |
case-19 | pass→pass | 2,657 | 4,168 | +57% | 1 | 1 | 0% | 491 | 1,106 | +125% | 0 | 0 | — |
case-20 | pass→pass | 6,016 | 6,266 | +4% | 1 | 1 | 0% | 1,230 | 1,511 | +23% | 0 | 0 | — |
case-21 | pass→pass | 3,692 | 3,632 | -2% | 1 | 1 | 0% | 648 | 932 | +44% | 0 | 0 | — |
case-22 | pass→pass | 4,375 | 2,624 | -40% | 1 | 1 | 0% | 853 | 793 | -7% | 0 | 0 | — |
case-23 | fail→pass | 2,650 | 6,053 | +128% | 1 | 1 | 0% | 462 | 1,527 | +231% | 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. 23 cases were attempted. The headline lift of +4 percentage points is the difference between those two pass rates over the 23 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.