Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Simplify and refine recently modified code for clarity and consistency. Use after writing code to improve readability without changing functionality.
.claude/skills/aiskillstore-simplify/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-16 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-21 | ✗→✓ | ▲ Improved | 427% | 0% |
| case-01 | ✓→✓ | = Same ✓ | -26% | 0% |
| case-02 | ✓→✓ | = Same ✓ | 58% | 0% |
| case-03 | ✓→✓ | = Same ✓ | 16% | 0% |
You are an expert code simplification specialist focused on enhancing code clarity, consistency, and maintainability while preserving exact functionality. Your expertise lies in applying project-specific best practices to simplify and improve code without altering its behavior. You prioritize readable, explicit code over overly compact solutions. This is a balance that you have mastered as a result your years as an expert software engineer.
You will analyze recently modified code and apply refinements that:
function keyword over arrow functionsYour refinement process:
You operate autonomously and proactively, refining code immediately after it's written or modified without requiring explicit requests. Your goal is to ensure all code meets the highest standards of elegance and maintainability while preserving its complete functionality.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 16,787 | 10,641 | -37% | 1 | 1 | 0% | 2,020 | 1,498 | -26% | 0 | 0 | — |
case-02 | pass→pass | 11,522 | 13,728 | +19% | 1 | 1 | 0% | 1,226 | 1,935 | +58% | 0 | 0 | — |
case-03 | pass→pass | 13,441 | 5,933 | -56% | 1 | 1 | 0% | 1,404 | 1,635 | +16% | 0 | 0 | — |
case-04 | pass→pass | 5,350 | 5,282 | -1% | 1 | 1 | 0% | 915 | 1,472 | +61% | 0 | 0 | — |
case-05 | pass→pass | 12,822 | 12,363 | -4% | 1 | 1 | 0% | 1,503 | 1,829 | +22% | 0 | 0 | — |
case-06 | pass→pass | 14,794 | 9,997 | -32% | 1 | 1 | 0% | 1,561 | 2,122 | +36% | 0 | 0 | — |
case-07 | pass→pass | 5,146 | 10,459 | +103% | 1 | 1 | 0% | 826 | 1,446 | +75% | 0 | 0 | — |
case-08 | pass→pass | 11,234 | 12,733 | +13% | 1 | 1 | 0% | 1,121 | 1,841 | +64% | 0 | 0 | — |
case-09 | pass→pass | 11,905 | 10,705 | -10% | 1 | 1 | 0% | 2,144 | 2,365 | +10% | 0 | 0 | — |
case-10 | pass→pass | 10,574 | 7,168 | -32% | 1 | 1 | 0% | 897 | 1,878 | +109% | 0 | 0 | — |
case-11 | pass→pass | 2,056 | 2,551 | +24% | 1 | 1 | 0% | 297 | 925 | +211% | 0 | 0 | — |
case-12 | pass→pass | 9,568 | 12,516 | +31% | 1 | 1 | 0% | 1,712 | 1,996 | +17% | 0 | 0 | — |
case-13 | pass→pass | 4,022 | 11,180 | +178% | 1 | 1 | 0% | 691 | 1,701 | +146% | 0 | 0 | — |
case-14 | pass→pass | 3,580 | 7,761 | +117% | 1 | 1 | 0% | 645 | 941 | +46% | 0 | 0 | — |
case-15 | pass→pass | 21,265 | 11,337 | -47% | 1 | 1 | 0% | 2,862 | 2,728 | -5% | 0 | 0 | — |
case-16 | fail→pass | 5,527 | 9,356 | +69% | 1 | 1 | 0% | 926 | 1,322 | +43% | 0 | 0 | — |
case-17 | pass→pass | 15,384 | 6,533 | -58% | 1 | 1 | 0% | 1,941 | 1,639 | -16% | 0 | 0 | — |
case-18 | fail→fail | 10,297 | 4,273 | -59% | 1 | 1 | 0% | 728 | 1,194 | +64% | 0 | 0 | — |
case-19 | fail→fail | 21,299 | 19,471 | -9% | 1 | 1 | 0% | 4,086 | 2,315 | -43% | 0 | 0 | — |
case-20 | pass→pass | 14,383 | 11,967 | -17% | 1 | 1 | 0% | 1,571 | 1,952 | +24% | 0 | 0 | — |
case-21 | fail→pass | 7,955 | 18,011 | +126% | 1 | 1 | 0% | 264 | 1,390 | +427% | 0 | 0 | — |
case-22 | pass→pass | 12,260 | 6,001 | -51% | 1 | 1 | 0% | 1,264 | 1,636 | +29% | 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.