Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for Java General Purpose.
.claude/skills/amariahak-cursor-rules-for-java-general-purpose/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 48% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 71% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 45% | 0% |
| case-22 | ✓→✓ | = Same ✓ | 44% | 0% |
Cursor rules for Java General Purpose.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/java-general-purpose-cursorrules-prompt-file.mdc.
file_location: root_directory file_name: .cursorrules
ai_persona: role: Senior Java Developer principles:
tech_stack: framework: none build_tool: Maven java_version: 24 dependencies:
language: English code_comments: English
effective_java_notes: chapter_2: title: "Creating and Destroying Objects" items:
chapter_3: title: "Methods Common to All Objects" items:
chapter_4: title: "Classes and Interfaces" items:
chapter_5: title: "Generics" items:
chapter_6: title: "Enums and Annotations" items:
chapter_7: title: "Lambdas and Streams" items:
chapter_8: title: "Methods" items:
chapter_9: title: "General Programming" items:
chapter_10: title: "Exceptions" items:
chapter_11: title: "Concurrency" items:
chapter_12: title: "Serialization" items:
concurrency_guidelines:
functional_programming_guidelines:
data_oriented_programming_pillars:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-22 | pass→pass | 14,540 | 11,360 | -22% | 1 | 1 | 0% | 2,503 | 3,594 | +44% | 0 | 0 | — |
case-01 | fail→pass | 17,518 | 10,358 | -41% | 1 | 1 | 0% | 2,973 | 3,225 | +8% | 0 | 0 | — |
case-02 | fail→pass | 15,962 | 23,096 | +45% | 1 | 1 | 0% | 2,858 | 4,217 | +48% | 0 | 0 | — |
case-03 | pass→pass | 13,478 | 9,164 | -32% | 1 | 1 | 0% | 2,400 | 3,292 | +37% | 0 | 0 | — |
case-04 | pass→pass | 13,727 | 9,785 | -29% | 1 | 1 | 0% | 2,244 | 3,434 | +53% | 0 | 0 | — |
case-05 | pass→pass | 11,049 | 8,885 | -20% | 1 | 1 | 0% | 1,898 | 3,227 | +70% | 0 | 0 | — |
case-06 | pass→pass | 10,041 | 8,158 | -19% | 1 | 1 | 0% | 1,962 | 3,225 | +64% | 0 | 0 | — |
case-07 | pass→pass | 14,375 | 11,324 | -21% | 1 | 1 | 0% | 2,500 | 3,788 | +52% | 0 | 0 | — |
case-08 | pass→pass | 14,328 | 8,037 | -44% | 1 | 1 | 0% | 2,097 | 3,374 | +61% | 0 | 0 | — |
case-09 | fail→pass | 8,209 | 3,788 | -54% | 1 | 1 | 0% | 1,381 | 2,364 | +71% | 0 | 0 | — |
case-10 | pass→pass | 11,567 | 9,678 | -16% | 1 | 1 | 0% | 2,068 | 3,271 | +58% | 0 | 0 | — |
case-11 | pass→pass | 10,465 | 8,483 | -19% | 1 | 1 | 0% | 2,103 | 3,404 | +62% | 0 | 0 | — |
case-12 | pass→pass | 12,976 | 9,769 | -25% | 1 | 1 | 0% | 2,464 | 3,448 | +40% | 0 | 0 | — |
case-13 | fail→pass | 12,805 | 8,387 | -35% | 1 | 1 | 0% | 2,234 | 3,236 | +45% | 0 | 0 | — |
case-14 | pass→pass | 4,623 | 6,805 | +47% | 1 | 1 | 0% | 839 | 2,834 | +238% | 0 | 0 | — |
case-15 | pass→pass | 10,980 | 8,893 | -19% | 1 | 1 | 0% | 1,906 | 3,286 | +72% | 0 | 0 | — |
case-16 | pass→pass | 12,246 | 11,537 | -6% | 1 | 1 | 0% | 2,172 | 3,629 | +67% | 0 | 0 | — |
case-17 | pass→pass | 9,720 | 6,535 | -33% | 1 | 1 | 0% | 1,763 | 2,911 | +65% | 0 | 0 | — |
case-18 | pass→pass | 4,040 | 7,353 | +82% | 1 | 1 | 0% | 739 | 2,455 | +232% | 0 | 0 | — |
case-19 | pass→pass | 9,940 | 9,451 | -5% | 1 | 1 | 0% | 1,883 | 3,401 | +81% | 0 | 0 | — |
case-20 | pass→pass | 15,073 | 11,990 | -20% | 1 | 1 | 0% | 2,812 | 3,918 | +39% | 0 | 0 | — |
case-21 | pass→pass | 10,369 | 8,361 | -19% | 1 | 1 | 0% | 1,870 | 2,994 | +60% | 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 +18 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.