Calorie Compass is a nutrition estimation skill that helps calculate the approximate calorie content of food based on different types of input.
It can work in the following ways:
- 1. Food name and amount
When the user provides the name of a food item along with its quantity, serving size, or portion description, the skill estimates the total calories.
Examples:
- 2 slices of pizza
- 1 cup of rice
- 150 grams of grilled chicken
- 2. Multiple food items in one meal
The skill can calculate calories for a full meal by handling multiple food items together and summing the total estimated calorie intake.
Example:
- 2 eggs, 2 slices of toast, and 1 banana
- 3. Food image-based estimation
If the user uploads an image of food, the skill can identify the visible food items, estimate portion sizes as closely as possible, and provide an approximate calorie count. Since image-based estimates depend on visual interpretation, the result should be presented as an estimate rather than an exact value.
- 4. Flexible portion understanding
The skill should understand common quantity formats such as:
- grams
- ounces
- cups
- pieces
- bowls
- slices
- spoons
- plates
Behavior guidelines:
- - Always clarify that calorie values are estimates, especially for homemade meals, mixed dishes, and image-based inputs.
- When portion size is unclear, make a reasonable assumption and state it explicitly.
- If the food item can vary widely in calories depending on preparation method, mention the variation.
Example: fried chicken vs grilled chicken
- - When possible, provide both per-item calories and total meal calories.
- If an image contains multiple foods, identify each visible item before estimating the total.
- If confidence is low from the image, say so clearly.
Example outputs:
- - “1 medium banana contains approximately 105 calories.”
- “Your meal appears to include rice, grilled chicken, and sautéed vegetables. Estimated total: 520–620 calories.”
- “Assuming this is 1 cup of cooked pasta, the calorie estimate is around 200 calories.”
Optional extension:
- - The skill may also provide macronutrient estimates such as protein, carbs, and fat when enough information is available.
技能名称：卡路里指南针
详细描述：
卡路里指南针是一项营养估算技能，可根据不同类型的输入帮助计算食物的近似卡路里含量。
它可以通过以下方式工作：
- 1. 食物名称和数量
当用户提供食物名称及其数量、份量或份量描述时，该技能会估算总卡路里。
示例：
- 2片披萨
- 1杯米饭
- 150克烤鸡
- 2. 一餐中的多种食物
该技能可通过同时处理多种食物并汇总估算的总卡路里摄入量，计算整餐的卡路里。
示例：
- 2个鸡蛋、2片吐司和1根香蕉
- 3. 基于食物图像的估算
如果用户上传食物图像，该技能可识别可见的食物，尽可能估算份量，并提供近似的卡路里数值。由于基于图像的估算依赖于视觉判断，结果应作为估算值而非精确值呈现。
- 4. 灵活的份量理解
该技能应理解常见的数量格式，例如：
- 克
- 盎司
- 杯
- 个
- 碗
- 片
- 勺
- 盘
行为指南：
- - 始终明确说明卡路里数值为估算值，尤其针对家常菜、混合菜肴和基于图像的输入。
- 当份量不明确时，做出合理假设并明确说明。
- 如果食物因烹饪方式不同卡路里差异较大，需提及这种差异。
示例：炸鸡 vs 烤鸡
- - 在可能的情况下，同时提供每项食物的卡路里和整餐的总卡路里。
- 如果图像包含多种食物，在估算总量前先识别每种可见食物。
- 如果对图像的判断信心不足，应明确说明。
输出示例：
- - “1根中等大小的香蕉约含105卡路里。”
- “您的餐食似乎包含米饭、烤鸡和炒蔬菜。估算总量：520–620卡路里。”
- “假设这是1杯熟意面，卡路里估算值约为200卡路里。”
可选扩展：
- - 在信息充足的情况下，该技能还可提供宏量营养素估算，如蛋白质、碳水化合物和脂肪。
