Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Upgrade Expo SDK versions
.claude/skills/lingxling-upgrading-expo/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-19 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 17% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 58% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | 18% | 0% |
Upgrade Expo SDK versions safely, handling breaking changes, dependencies, and configuration updates.
Use this skill when you need to upgrade Expo SDK versions.
Use this skill when:
This skill guides you through upgrading Expo SDK versions:
bash# Update Expo CLI npm install -g expo-cli@latest # Upgrade Expo SDK npx expo install expo@latest # Update all Expo packages npx expo install --fix
bash# Check for outdated packages npx expo-doctor # Update packages to compatible versions npx expo install --fix # Verify compatibility npx expo-doctor
expo install instead of npm install for Expo packagesapp.json for new SDK requirementsexpo-doctor to verify setupFor more information, see the source repository.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 36,358 | 31,871 | -12% | 1 | 1 | 0% | 4,858 | 3,920 | -19% | 0 | 0 | — |
case-02 | fail→pass | 21,549 | 19,271 | -11% | 1 | 1 | 0% | 3,519 | 3,254 | -8% | 0 | 0 | — |
case-03 | fail→fail | 22,057 | 15,747 | -29% | 1 | 1 | 0% | 3,266 | 3,414 | +5% | 0 | 0 | — |
case-04 | pass→pass | 21,068 | 7,112 | -66% | 1 | 1 | 0% | 1,557 | 1,824 | +17% | 0 | 0 | — |
case-05 | pass→pass | 4,844 | 3,620 | -25% | 1 | 1 | 0% | 731 | 1,158 | +58% | 0 | 0 | — |
case-06 | pass→pass | 7,062 | 2,688 | -62% | 1 | 1 | 0% | 899 | 1,062 | +18% | 0 | 0 | — |
case-07 | pass→pass | 9,385 | 3,773 | -60% | 1 | 1 | 0% | 1,194 | 1,128 | -6% | 0 | 0 | — |
case-08 | pass→pass | 4,933 | 2,938 | -40% | 1 | 1 | 0% | 884 | 1,026 | +16% | 0 | 0 | — |
case-09 | pass→pass | 11,295 | 6,500 | -42% | 1 | 1 | 0% | 1,697 | 1,501 | -12% | 0 | 0 | — |
case-10 | pass→pass | 5,557 | 3,938 | -29% | 1 | 1 | 0% | 571 | 1,069 | +87% | 0 | 0 | — |
case-11 | pass→pass | 16,246 | 2,126 | -87% | 1 | 1 | 0% | 679 | 937 | +38% | 0 | 0 | — |
case-12 | pass→pass | 14,618 | 4,720 | -68% | 1 | 1 | 0% | 1,972 | 1,232 | -38% | 0 | 0 | — |
case-13 | pass→pass | 19,055 | 6,270 | -67% | 1 | 1 | 0% | 2,544 | 1,624 | -36% | 0 | 0 | — |
case-14 | pass→pass | 24,973 | 15,742 | -37% | 1 | 1 | 0% | 3,195 | 3,088 | -3% | 0 | 0 | — |
case-15 | pass→pass | 24,817 | 12,235 | -51% | 1 | 1 | 0% | 2,931 | 2,655 | -9% | 0 | 0 | — |
case-16 | pass→pass | 11,172 | 4,028 | -64% | 1 | 1 | 0% | 1,371 | 1,146 | -16% | 0 | 0 | — |
case-17 | pass→pass | 11,110 | 6,774 | -39% | 1 | 1 | 0% | 1,818 | 1,725 | -5% | 0 | 0 | — |
case-18 | fail→fail | 17,302 | 12,760 | -26% | 1 | 1 | 0% | 2,674 | 2,745 | +3% | 0 | 0 | — |
case-19 | fail→pass | 9,217 | 2,937 | -68% | 1 | 1 | 0% | 1,532 | 978 | -36% | 0 | 0 | — |
case-20 | pass→pass | 10,943 | 10,693 | -2% | 1 | 1 | 0% | 1,958 | 2,032 | +4% | 0 | 0 | — |
case-21 | pass→pass | 18,594 | 18,971 | +2% | 1 | 1 | 0% | 2,654 | 3,418 | +29% | 0 | 0 | — |
case-22 | pass→pass | 14,201 | 14,063 | -1% | 1 | 1 | 0% | 2,939 | 3,074 | +5% | 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 +9 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.