Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for optimization development with DRY and SOLID principles integration.
.claude/skills/amariahak-cursor-rules-for-optimization-development-with-dry-and-solid-principles-integrat/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-15 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 104% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -31% | 0% |
Cursor rules for optimization development with DRY and SOLID principles integration.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/optimize-dry-solid-principles-cursorrules-prompt-f.mdc.
Communication and Problem-Solving:
Code Quality and Best Practices:
Paradigms and Principles:
Semantic Naming and Abstractions:
Platform Thinking:
Response Format:
Handling Uncertainty and Limitations:
When outputting code blocks, include a # or // file name comment prior to the block, with a few lines before and after the modification. This helps the user identify where to make changes.
Stick to the current architecture choices located in pyproject.toml unless the user suggests a new method or module.
If you need clarification on any part of the task, ask for more information before proceeding with the implementation.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 15,989 | 11,539 | -28% | 1 | 1 | 0% | 3,155 | 2,484 | -21% | 0 | 0 | — |
case-02 | fail→fail | 3,915 | 5,700 | +46% | 1 | 1 | 0% | 661 | 1,138 | +72% | 0 | 0 | — |
case-15 | fail→pass | 7,843 | 5,342 | -32% | 1 | 1 | 0% | 1,450 | 1,134 | -22% | 0 | 0 | — |
case-03 | fail→pass | 9,637 | 7,783 | -19% | 1 | 1 | 0% | 1,926 | 1,887 | -2% | 0 | 0 | — |
case-04 | fail→pass | 6,079 | 10,490 | +73% | 1 | 1 | 0% | 1,191 | 2,430 | +104% | 0 | 0 | — |
case-05 | pass→pass | 8,948 | 6,573 | -27% | 1 | 1 | 0% | 1,410 | 1,391 | -1% | 0 | 0 | — |
case-06 | fail→fail | 14,018 | 15,834 | +13% | 1 | 1 | 0% | 3,092 | 3,764 | +22% | 0 | 0 | — |
case-07 | fail→fail | 17,280 | 7,071 | -59% | 1 | 1 | 0% | 2,958 | 1,407 | -52% | 0 | 0 | — |
case-08 | fail→fail | 17,706 | 19,255 | +9% | 1 | 1 | 0% | 3,366 | 3,117 | -7% | 0 | 0 | — |
case-09 | fail→pass | 12,273 | 10,188 | -17% | 1 | 1 | 0% | 2,252 | 2,198 | -2% | 0 | 0 | — |
case-10 | pass→pass | 10,176 | 10,828 | +6% | 1 | 1 | 0% | 2,157 | 2,425 | +12% | 0 | 0 | — |
case-11 | fail→pass | 10,232 | 6,456 | -37% | 1 | 1 | 0% | 1,849 | 1,272 | -31% | 0 | 0 | — |
case-12 | pass→pass | 10,975 | 10,730 | -2% | 1 | 1 | 0% | 2,294 | 1,751 | -24% | 0 | 0 | — |
case-13 | pass→pass | 24,410 | 11,006 | -55% | 1 | 1 | 0% | 2,404 | 2,195 | -9% | 0 | 0 | — |
case-14 | fail→pass | 10,817 | 6,741 | -38% | 1 | 1 | 0% | 2,270 | 1,583 | -30% | 0 | 0 | — |
case-16 | fail→pass | 10,267 | 10,520 | +2% | 1 | 1 | 0% | 1,727 | 2,153 | +25% | 0 | 0 | — |
case-17 | fail→pass | 9,792 | 10,118 | +3% | 1 | 1 | 0% | 1,895 | 1,650 | -13% | 0 | 0 | — |
case-18 | fail→fail | 9,993 | 8,594 | -14% | 1 | 1 | 0% | 1,890 | 1,845 | -2% | 0 | 0 | — |
case-19 | pass→fail | 6,030 | 3,323 | -45% | 1 | 1 | 0% | 1,236 | 784 | -37% | 0 | 0 | — |
case-20 | pass→pass | 10,211 | 8,580 | -16% | 1 | 1 | 0% | 1,631 | 1,469 | -10% | 0 | 0 | — |
case-21 | pass→pass | 2,257 | 3,613 | +60% | 1 | 1 | 0% | 460 | 682 | +48% | 0 | 0 | — |
case-22 | pass→pass | 9,827 | 7,949 | -19% | 1 | 1 | 0% | 1,545 | 1,488 | -4% | 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 +32 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.