Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Use when asked to "simplify code", "clean up code", "refactor for clarity", "improve readability", or review recently modified code for elegance. Focuses on project-specific best practices.
.claude/skills/sickn33-code-simplifier/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 67% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 113% | 0% |
| case-19 | ✓→✗ | ▼ Worse | -46% | 0% |
| case-02 | ✓→✓ | = Same ✓ | 18% | 0% |
<!-- Based on Anthropic's code-simplifier agent: https://github.com/anthropics/claude-plugins-official/blob/main/plugins/code-simplifier/agents/code-simplifier.md -->
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.
Never change what the code does - only how it does it. All original features, outputs, and behaviors must remain intact.
Follow the established coding standards from CLAUDE.md including:
function keyword over arrow functionsSimplify code structure by:
Avoid over-simplification that could:
Only refine code that has been recently modified or touched in the current session, unless explicitly instructed to review a broader scope.
typescriptconst status = isLoading ? 'loading' : hasError ? 'error' : isComplete ? 'complete' : 'idle';
typescriptfunction getStatus(isLoading: boolean, hasError: boolean, isComplete: boolean): string { if (isLoading) return 'loading'; if (hasError) return 'error'; if (isComplete) return 'complete'; return 'idle'; }
typescriptconst result = arr.filter(x => x > 0).map(x => x * 2).reduce((a, b) => a + b, 0);
typescriptconst positiveNumbers = arr.filter(x => x > 0); const doubled = positiveNumbers.map(x => x * 2); const sum = doubled.reduce((a, b) => a + b, 0);
typescriptfunction isNotEmpty(arr: unknown[]): boolean { return arr.length > 0; } if (isNotEmpty(items)) { // ... }
typescriptif (items.length > 0) { // ... }
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 9,153 | 4,350 | -52% | 1 | 1 | 0% | 1,871 | 1,836 | -2% | 0 | 0 | — |
case-02 | pass→pass | 7,130 | 2,757 | -61% | 1 | 1 | 0% | 1,301 | 1,534 | +18% | 0 | 0 | — |
case-03 | pass→pass | 6,518 | 2,948 | -55% | 1 | 1 | 0% | 1,316 | 1,499 | +14% | 0 | 0 | — |
case-04 | fail→pass | 7,893 | 6,758 | -14% | 1 | 1 | 0% | 1,475 | 2,463 | +67% | 0 | 0 | — |
case-05 | pass→pass | 5,300 | 2,492 | -53% | 1 | 1 | 0% | 1,082 | 1,411 | +30% | 0 | 0 | — |
case-06 | pass→pass | 4,831 | 3,336 | -31% | 1 | 1 | 0% | 1,057 | 1,669 | +58% | 0 | 0 | — |
case-07 | pass→pass | 3,551 | 3,176 | -11% | 1 | 1 | 0% | 757 | 1,584 | +109% | 0 | 0 | — |
case-08 | pass→pass | 4,551 | 3,385 | -26% | 1 | 1 | 0% | 858 | 1,661 | +94% | 0 | 0 | — |
case-09 | pass→pass | 4,130 | 5,741 | +39% | 1 | 1 | 0% | 852 | 2,108 | +147% | 0 | 0 | — |
case-10 | pass→pass | 1,680 | 1,673 | -0% | 1 | 1 | 0% | 302 | 1,307 | +333% | 0 | 0 | — |
case-11 | pass→pass | 4,042 | 4,107 | +2% | 1 | 1 | 0% | 859 | 1,758 | +105% | 0 | 0 | — |
case-12 | pass→pass | 6,949 | 5,392 | -22% | 1 | 1 | 0% | 1,580 | 2,201 | +39% | 0 | 0 | — |
case-13 | fail→pass | 4,659 | 4,674 | +0% | 1 | 1 | 0% | 887 | 1,888 | +113% | 0 | 0 | — |
case-14 | pass→pass | 4,254 | 2,770 | -35% | 1 | 1 | 0% | 710 | 1,513 | +113% | 0 | 0 | — |
case-15 | pass→pass | 12,982 | 9,413 | -27% | 1 | 1 | 0% | 1,677 | 2,848 | +70% | 0 | 0 | — |
case-16 | pass→pass | 5,510 | 4,440 | -19% | 1 | 1 | 0% | 1,169 | 1,863 | +59% | 0 | 0 | — |
case-17 | pass→pass | 4,472 | 4,845 | +8% | 1 | 1 | 0% | 946 | 2,040 | +116% | 0 | 0 | — |
case-18 | pass→pass | 6,470 | 3,961 | -39% | 1 | 1 | 0% | 1,288 | 1,679 | +30% | 0 | 0 | — |
case-19 | pass→fail | 14,229 | 4,340 | -69% | 1 | 1 | 0% | 3,070 | 1,671 | -46% | 0 | 0 | — |
case-20 | pass→pass | 18,080 | 14,694 | -19% | 1 | 1 | 0% | 3,477 | 3,754 | +8% | 0 | 0 | — |
case-21 | pass→pass | 9,318 | 12,546 | +35% | 1 | 1 | 0% | 1,673 | 1,999 | +19% | 0 | 0 | — |
case-22 | pass→pass | 5,629 | 5,914 | +5% | 1 | 1 | 0% | 1,312 | 2,176 | +66% | 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. 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.