Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate pwa manifest generator operations. Auto-activating skill for Frontend Development. Triggers on: pwa manifest generator, pwa manifest generator Part of the Frontend Development skill category. Use when working with pwa manifest generator functionality. Trigger with phrases like "pwa manifest generator", "pwa generator", "pwa".
.claude/skills/dicklesworthstone-pwa-manifest-generator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-13 | ✓→✗ | ▼ Worse | 49% | 0% |
| case-19 | ✓→✗ | ▼ Worse | 94% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 85% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 48% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 39% | 0% |
This skill provides automated assistance for pwa manifest generator tasks within the Frontend Development domain.
This skill activates automatically when you:
Example: Basic Usage Request: "Help me with pwa manifest generator" 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→pass | 16,120 | 21,715 | +35% | 1 | 1 | 0% | 2,172 | 4,011 | +85% | 0 | 0 | — |
case-02 | pass→pass | 8,326 | 10,588 | +27% | 1 | 1 | 0% | 1,617 | 2,400 | +48% | 0 | 0 | — |
case-03 | pass→pass | 9,031 | 16,378 | +81% | 1 | 1 | 0% | 1,715 | 2,389 | +39% | 0 | 0 | — |
case-04 | pass→pass | 14,223 | 9,162 | -36% | 1 | 1 | 0% | 1,807 | 2,260 | +25% | 0 | 0 | — |
case-05 | pass→pass | 14,110 | 8,720 | -38% | 1 | 1 | 0% | 1,798 | 2,122 | +18% | 0 | 0 | — |
case-06 | pass→pass | 12,491 | 14,760 | +18% | 1 | 1 | 0% | 1,588 | 2,464 | +55% | 0 | 0 | — |
case-07 | pass→pass | 6,026 | 11,659 | +93% | 1 | 1 | 0% | 1,196 | 1,673 | +40% | 0 | 0 | — |
case-08 | pass→pass | 12,533 | 14,249 | +14% | 1 | 1 | 0% | 1,449 | 2,242 | +55% | 0 | 0 | — |
case-09 | pass→pass | 11,788 | 13,298 | +13% | 1 | 1 | 0% | 2,364 | 3,149 | +33% | 0 | 0 | — |
case-10 | pass→pass | 8,372 | 16,138 | +93% | 1 | 1 | 0% | 1,751 | 2,636 | +51% | 0 | 0 | — |
case-11 | pass→pass | 8,678 | 10,032 | +16% | 1 | 1 | 0% | 706 | 1,296 | +84% | 0 | 0 | — |
case-12 | pass→pass | 12,476 | 18,979 | +52% | 1 | 1 | 0% | 1,549 | 3,279 | +112% | 0 | 0 | — |
case-13 | pass→fail | 14,968 | 16,902 | +13% | 1 | 1 | 0% | 1,741 | 2,597 | +49% | 0 | 0 | — |
case-14 | pass→pass | 13,354 | 18,676 | +40% | 1 | 1 | 0% | 1,829 | 3,250 | +78% | 0 | 0 | — |
case-15 | pass→pass | 15,628 | 13,941 | -11% | 1 | 1 | 0% | 2,249 | 2,196 | -2% | 0 | 0 | — |
case-16 | pass→pass | 14,091 | 14,081 | -0% | 1 | 1 | 0% | 2,015 | 3,498 | +74% | 0 | 0 | — |
case-17 | pass→pass | 13,202 | 19,149 | +45% | 1 | 1 | 0% | 2,799 | 3,234 | +16% | 0 | 0 | — |
case-18 | pass→pass | 11,150 | 11,592 | +4% | 1 | 1 | 0% | 2,337 | 2,596 | +11% | 0 | 0 | — |
case-19 | pass→fail | 13,056 | 17,995 | +38% | 1 | 1 | 0% | 1,663 | 3,233 | +94% | 0 | 0 | — |
case-20 | pass→pass | 15,858 | 15,959 | +1% | 1 | 1 | 0% | 2,261 | 2,619 | +16% | 0 | 0 | — |
case-21 | pass→pass | 3,938 | 4,825 | +23% | 1 | 1 | 0% | 743 | 1,254 | +69% | 0 | 0 | — |
case-22 | pass→pass | 14,422 | 19,699 | +37% | 1 | 1 | 0% | 1,893 | 3,515 | +86% | 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. 2 cases got worse with the skill loaded, and they are included in that figure.
Other measured skills in the registry, with their headline benchmark lift.