Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Analyze bundle size analyzer operations. Auto-activating skill for Frontend Development. Triggers on: bundle size analyzer, bundle size analyzer Part of the Frontend Development skill category. Use when analyzing or auditing bundle size analyzer. Trigger with phrases like "bundle size analyzer", "bundle analyzer", "analyze bundle size r".
.claude/skills/dicklesworthstone-bundle-size-analyzer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✓→✗ | ▼ Worse | 63% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 27% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 17% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 13% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 56% | 0% |
This skill provides automated assistance for bundle size analyzer tasks within the Frontend Development domain.
This skill activates automatically when you:
Example: Basic Usage Request: "Help me with bundle size analyzer" Result: Provides step-by-step guidance and generates appropriate configurations
| Error | Cause | Solution | |-------|-------|----------| | Configuration invalid | Missing required fields | Check documentation for required parameters | | Tool not found | Dependency not installed | Install required tools per prerequisites | | Permission denied | Insufficient access | Verify credentials and permissions |
Part of the Frontend Development skill category. Tags: react, vue, css, accessibility, web
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→fail | 14,548 | 17,630 | +21% | 1 | 1 | 0% | 1,729 | 2,824 | +63% | 0 | 0 | — |
case-02 | pass→pass | 14,365 | 15,234 | +6% | 1 | 1 | 0% | 1,886 | 2,386 | +27% | 0 | 0 | — |
case-03 | pass→pass | 18,486 | 18,430 | -0% | 1 | 1 | 0% | 2,325 | 2,712 | +17% | 0 | 0 | — |
case-04 | pass→pass | 18,635 | 18,402 | -1% | 1 | 1 | 0% | 2,511 | 2,844 | +13% | 0 | 0 | — |
case-05 | pass→pass | 9,915 | 11,177 | +13% | 1 | 1 | 0% | 885 | 1,385 | +56% | 0 | 0 | — |
case-06 | pass→pass | 9,245 | 10,972 | +19% | 1 | 1 | 0% | 704 | 1,420 | +102% | 0 | 0 | — |
case-07 | pass→pass | 14,806 | 14,965 | +1% | 1 | 1 | 0% | 1,905 | 2,297 | +21% | 0 | 0 | — |
case-08 | pass→pass | 16,765 | 18,417 | +10% | 1 | 1 | 0% | 2,108 | 2,750 | +30% | 0 | 0 | — |
case-09 | pass→pass | 14,207 | 18,541 | +31% | 1 | 1 | 0% | 1,836 | 3,109 | +69% | 0 | 0 | — |
case-10 | pass→pass | 19,098 | 18,967 | -1% | 1 | 1 | 0% | 2,477 | 2,872 | +16% | 0 | 0 | — |
case-11 | pass→pass | 13,742 | 19,123 | +39% | 1 | 1 | 0% | 2,709 | 3,177 | +17% | 0 | 0 | — |
case-12 | pass→pass | 19,089 | 19,545 | +2% | 1 | 1 | 0% | 2,446 | 2,787 | +14% | 0 | 0 | — |
case-13 | pass→pass | 8,208 | 16,381 | +100% | 1 | 1 | 0% | 1,530 | 2,382 | +56% | 0 | 0 | — |
case-14 | pass→pass | 21,611 | 14,675 | -32% | 1 | 1 | 0% | 3,370 | 3,131 | -7% | 0 | 0 | — |
case-15 | fail→fail | 8,657 | 14,300 | +65% | 1 | 1 | 0% | 1,532 | 1,990 | +30% | 0 | 0 | — |
case-16 | pass→pass | 14,266 | 9,680 | -32% | 1 | 1 | 0% | 1,747 | 2,060 | +18% | 0 | 0 | — |
case-17 | pass→pass | 19,600 | 13,639 | -30% | 1 | 1 | 0% | 2,526 | 2,710 | +7% | 0 | 0 | — |
case-18 | pass→pass | 18,404 | 12,106 | -34% | 1 | 1 | 0% | 2,336 | 2,571 | +10% | 0 | 0 | — |
case-19 | pass→pass | 9,299 | 9,020 | -3% | 1 | 1 | 0% | 630 | 985 | +56% | 0 | 0 | — |
case-20 | pass→pass | 10,099 | 14,527 | +44% | 1 | 1 | 0% | 1,884 | 2,028 | +8% | 0 | 0 | — |
case-21 | pass→pass | 16,972 | 18,506 | +9% | 1 | 1 | 0% | 2,308 | 2,896 | +25% | 0 | 0 | — |
case-22 | pass→pass | 23,586 | 17,870 | -24% | 1 | 1 | 0% | 3,917 | 4,154 | +6% | 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 -100 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.
Other measured skills in the registry, with their headline benchmark lift.