Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →生成3D纸艺弹出书风格插画，具备立体层次感、明亮温暖色调，适用于科技、教育、品牌展示等场景
.claude/skills/anbeime-pop-up-book-illustration/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 41% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 41% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 78% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 47% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 49% | 0% |
根据核心设计要素，构建包含以下元素的提示词：
基础结构：
3D纸艺弹出书风格插画，立体层次感，打开的书本场景，书页边缘清晰可见色彩添加：
明亮温暖色调，薄荷绿、天蓝色、珊瑚橙、奶油黄配色质感描述：
纸质纹理质感，折痕细节，手工制作感，纸张表面触感立体效果：
多层弹出结构，前后景深，立体阴影，真实立体感科技元素（如需要）：
柔和霓虹光效点缀，数字科技元素，科技图标，数据流线条，温暖科技光照风格特征：
圆润可爱但专业精致，细节丰富，精美装饰功能说明：展示AI技术与纸质工艺的结合
提示词构建：
3D纸艺弹出书风格插画，打开的书本中央弹出AI大脑图案，周围是神经网络线条，纸质纹理质感，立体层次明显，薄荷绿和天蓝色为主色调，柔和霓虹光效点缀，温暖科技光照，书页边缘可见，圆润可爱但专业精致功能说明：展示知识探索场景
提示词构建：
3D纸艺弹出书风格插画，打开的书本弹出多层知识树，树上有书本、灯泡、齿轮等元素，珊瑚橙和奶油黄为主色调，纸质折痕细节丰富，立体阴影增强层次感，书页边缘清晰，从简单到复杂的视觉递进，温暖明亮氛围功能说明：展示产品或品牌故事
提示词构建：
3D纸艺弹出书风格插画，打开的书本中央弹出品牌产品，周围环绕品牌关键词和装饰元素，薄荷绿和天蓝色配合珊瑚橙点缀，纸质纹理与数字科技元素结合，柔和霓虹光效，立体多层结构，书页边缘真实可见，专业精致且温暖可爱| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 13,757 | 10,880 | -21% | 1 | 1 | 0% | 2,239 | 3,161 | +41% | 0 | 0 | — |
case-02 | fail→pass | 12,747 | 10,642 | -17% | 1 | 1 | 0% | 2,191 | 3,091 | +41% | 0 | 0 | — |
case-03 | fail→pass | 9,299 | 10,937 | +18% | 1 | 1 | 0% | 1,650 | 2,935 | +78% | 0 | 0 | — |
case-04 | pass→pass | 22,849 | 23,676 | +4% | 1 | 1 | 0% | 3,170 | 4,372 | +38% | 0 | 0 | — |
case-05 | pass→pass | 12,162 | 9,843 | -19% | 1 | 1 | 0% | 2,337 | 3,106 | +33% | 0 | 0 | — |
case-06 | pass→pass | 14,410 | 19,665 | +36% | 1 | 1 | 0% | 3,146 | 5,486 | +74% | 0 | 0 | — |
case-07 | fail→fail | 10,551 | 9,567 | -9% | 1 | 1 | 0% | 1,787 | 2,809 | +57% | 0 | 0 | — |
case-08 | fail→fail | 13,226 | 10,529 | -20% | 1 | 1 | 0% | 2,285 | 3,071 | +34% | 0 | 0 | — |
case-09 | fail→pass | 12,505 | 10,456 | -16% | 1 | 1 | 0% | 1,858 | 2,724 | +47% | 0 | 0 | — |
case-10 | fail→fail | 8,511 | 10,378 | +22% | 1 | 1 | 0% | 1,568 | 2,932 | +87% | 0 | 0 | — |
case-11 | fail→pass | 13,106 | 9,151 | -30% | 1 | 1 | 0% | 1,864 | 2,784 | +49% | 0 | 0 | — |
case-12 | fail→pass | 13,910 | 11,406 | -18% | 1 | 1 | 0% | 2,171 | 3,299 | +52% | 0 | 0 | — |
case-13 | fail→fail | 10,998 | 13,307 | +21% | 1 | 1 | 0% | 1,859 | 3,052 | +64% | 0 | 0 | — |
case-14 | fail→fail | 12,327 | 13,450 | +9% | 1 | 1 | 0% | 2,093 | 3,512 | +68% | 0 | 0 | — |
case-15 | fail→pass | 14,134 | 6,083 | -57% | 1 | 1 | 0% | 1,438 | 2,387 | +66% | 0 | 0 | — |
case-16 | pass→pass | 13,473 | 7,579 | -44% | 1 | 1 | 0% | 1,965 | 2,479 | +26% | 0 | 0 | — |
case-17 | fail→pass | 13,354 | 8,461 | -37% | 1 | 1 | 0% | 2,332 | 2,683 | +15% | 0 | 0 | — |
case-18 | fail→fail | 11,977 | 41,366 | +245% | 1 | 1 | 0% | 2,097 | 2,764 | +32% | 0 | 0 | — |
case-19 | fail→pass | 14,285 | 17,313 | +21% | 1 | 1 | 0% | 1,981 | 3,179 | +60% | 0 | 0 | — |
case-20 | fail→fail | 12,680 | 10,756 | -15% | 1 | 1 | 0% | 1,870 | 3,018 | +61% | 0 | 0 | — |
case-21 | pass→pass | 14,713 | 13,527 | -8% | 1 | 1 | 0% | 2,360 | 3,037 | +29% | 0 | 0 | — |
case-22 | fail→fail | 11,895 | 10,729 | -10% | 1 | 1 | 0% | 2,106 | 2,857 | +36% | 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 +41 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.