Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Implement screen routes and deep-link/App Link routing with Jetpack Compose Navigation on Android. Use when the primary task is Compose route configuration or external URL routing; defer typed-route APIs, XML/fragments, generic back-stack, and transition questions to their specific navigation skills.
.claude/skills/hoangnguyen0403-android-navigation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -17% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 43% | 0% |
androidx.navigation:navigation-compose.intent-filter in Manifest and deepLinks in NavHost.Screen.Product.route instead of "product/$id".autoVerify=true intent filters.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 12,636 | 10,257 | -19% | 1 | 1 | 0% | 2,908 | 2,410 | -17% | 0 | 0 | — |
case-07 | fail→fail | 15,146 | 10,230 | -32% | 1 | 1 | 0% | 2,832 | 2,086 | -26% | 0 | 0 | — |
case-02 | fail→pass | 17,563 | 13,402 | -24% | 1 | 1 | 0% | 3,128 | 3,155 | +1% | 0 | 0 | — |
case-03 | fail→pass | 15,291 | 11,937 | -22% | 1 | 1 | 0% | 2,851 | 2,804 | -2% | 0 | 0 | — |
case-04 | pass→pass | 10,174 | 8,642 | -15% | 1 | 1 | 0% | 2,027 | 1,801 | -11% | 0 | 0 | — |
case-05 | pass→pass | 6,695 | 4,768 | -29% | 1 | 1 | 0% | 1,336 | 1,128 | -16% | 0 | 0 | — |
case-06 | pass→pass | 13,852 | 9,796 | -29% | 1 | 1 | 0% | 2,776 | 2,311 | -17% | 0 | 0 | — |
case-08 | fail→pass | 14,053 | 10,161 | -28% | 1 | 1 | 0% | 2,383 | 2,249 | -6% | 0 | 0 | — |
case-09 | pass→pass | 10,200 | 8,068 | -21% | 1 | 1 | 0% | 2,045 | 1,793 | -12% | 0 | 0 | — |
case-10 | pass→pass | 13,336 | 12,403 | -7% | 1 | 1 | 0% | 2,793 | 2,152 | -23% | 0 | 0 | — |
case-11 | fail→fail | 10,075 | 5,592 | -44% | 1 | 1 | 0% | 2,246 | 1,385 | -38% | 0 | 0 | — |
case-16 | fail→pass | 12,541 | 16,127 | +29% | 1 | 1 | 0% | 2,628 | 3,747 | +43% | 0 | 0 | — |
case-12 | fail→fail | 16,878 | 10,881 | -36% | 1 | 1 | 0% | 2,801 | 2,385 | -15% | 0 | 0 | — |
case-13 | pass→pass | 6,582 | 5,322 | -19% | 1 | 1 | 0% | 1,347 | 1,186 | -12% | 0 | 0 | — |
case-14 | fail→pass | 12,904 | 10,578 | -18% | 1 | 1 | 0% | 2,637 | 2,423 | -8% | 0 | 0 | — |
case-15 | fail→pass | 14,200 | 13,903 | -2% | 1 | 1 | 0% | 2,927 | 3,228 | +10% | 0 | 0 | — |
case-17 | fail→pass | 10,457 | 9,613 | -8% | 1 | 1 | 0% | 2,157 | 2,132 | -1% | 0 | 0 | — |
case-18 | fail→pass | 14,037 | 12,687 | -10% | 1 | 1 | 0% | 3,085 | 2,980 | -3% | 0 | 0 | — |
case-19 | fail→pass | 9,789 | 8,228 | -16% | 1 | 1 | 0% | 1,974 | 1,751 | -11% | 0 | 0 | — |
case-20 | pass→pass | 15,445 | 15,798 | +2% | 1 | 1 | 0% | 3,152 | 3,840 | +22% | 0 | 0 | — |
case-21 | pass→pass | 10,333 | 8,387 | -19% | 1 | 1 | 0% | 2,275 | 1,917 | -16% | 0 | 0 | — |
case-22 | pass→pass | 13,893 | 15,607 | +12% | 1 | 1 | 0% | 2,986 | 3,666 | +23% | 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 +45 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.