Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Develop React Native, Flutter, or native mobile apps with modern architecture patterns. Masters cross-platform development, native integrations, offline sync, and app store optimization. Use PROACTIVELY for mobile features, cross-platform code, or app optimization.
.claude/skills/dokhacgiakhoa-mobile-developer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-13 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-22 | ✗→✓ | ▲ Improved | 33% | 0% |
| case-10 | ✓→✗ | ▼ Worse | -9% | 0% |
| case-11 | ✓→✗ | ▼ Worse | 3% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | -28% | 0% |
resources/implementation-playbook.md.You are a mobile development expert specializing in cross-platform and native mobile application development.
Expert mobile developer specializing in React Native, Flutter, and native iOS/Android development. Masters modern mobile architecture patterns, performance optimization, and platform-specific integrations while maintaining code reusability across platforms.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-14 | fail→fail | 19,675 | 22,851 | +16% | 1 | 1 | 0% | 2,921 | 3,784 | +30% | 0 | 0 | — |
case-01 | fail→fail | 29,994 | 27,796 | -7% | 1 | 1 | 0% | 5,152 | 4,644 | -10% | 0 | 0 | — |
case-02 | fail→fail | 47,556 | 33,990 | -29% | 1 | 1 | 0% | 8,232 | 6,541 | -21% | 0 | 0 | — |
case-03 | pass→pass | 36,450 | 19,299 | -47% | 1 | 1 | 0% | 5,438 | 3,893 | -28% | 0 | 0 | — |
case-15 | pass→pass | 24,428 | 26,946 | +10% | 1 | 1 | 0% | 3,880 | 5,033 | +30% | 0 | 0 | — |
case-04 | pass→pass | 20,748 | 16,551 | -20% | 1 | 1 | 0% | 3,036 | 2,844 | -6% | 0 | 0 | — |
case-05 | pass→pass | 15,784 | 15,548 | -1% | 1 | 1 | 0% | 3,318 | 3,758 | +13% | 0 | 0 | — |
case-06 | pass→pass | 20,312 | 22,379 | +10% | 1 | 1 | 0% | 3,033 | 3,935 | +30% | 0 | 0 | — |
case-07 | pass→pass | 16,377 | 17,429 | +6% | 1 | 1 | 0% | 2,796 | 3,572 | +28% | 0 | 0 | — |
case-08 | pass→pass | 19,743 | 20,644 | +5% | 1 | 1 | 0% | 3,031 | 3,664 | +21% | 0 | 0 | — |
case-16 | pass→pass | 14,841 | 17,906 | +21% | 1 | 1 | 0% | 2,559 | 3,088 | +21% | 0 | 0 | — |
case-09 | pass→pass | 18,161 | 18,066 | -1% | 1 | 1 | 0% | 3,678 | 3,348 | -9% | 0 | 0 | — |
case-10 | pass→fail | 20,036 | 15,206 | -24% | 1 | 1 | 0% | 3,138 | 2,843 | -9% | 0 | 0 | — |
case-11 | pass→fail | 19,356 | 15,429 | -20% | 1 | 1 | 0% | 2,641 | 2,721 | +3% | 0 | 0 | — |
case-12 | pass→pass | 19,679 | 19,763 | +0% | 1 | 1 | 0% | 3,295 | 3,317 | +1% | 0 | 0 | — |
case-13 | fail→pass | 18,463 | 18,643 | +1% | 1 | 1 | 0% | 3,111 | 3,035 | -2% | 0 | 0 | — |
case-17 | pass→pass | 26,672 | 22,137 | -17% | 1 | 1 | 0% | 4,913 | 4,626 | -6% | 0 | 0 | — |
case-18 | pass→pass | 19,763 | 19,440 | -2% | 1 | 1 | 0% | 3,294 | 3,624 | +10% | 0 | 0 | — |
case-19 | pass→pass | 23,262 | 20,392 | -12% | 1 | 1 | 0% | 3,470 | 3,287 | -5% | 0 | 0 | — |
case-20 | pass→pass | 16,902 | 14,783 | -13% | 1 | 1 | 0% | 2,867 | 2,906 | +1% | 0 | 0 | — |
case-21 | pass→pass | 46,137 | 28,921 | -37% | 1 | 1 | 0% | 8,227 | 6,470 | -21% | 0 | 0 | — |
case-22 | fail→pass | 23,975 | 28,727 | +20% | 1 | 1 | 0% | 3,343 | 4,444 | +33% | 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 0 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.
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.