← 返回 Skills 市场
rajib76

Calorie Compass

作者 rajib · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
118
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install calorie-compass
功能描述
Estimate calorie content from food names, portion sizes, or food images.
使用说明 (SKILL.md)

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.
安全使用建议
This skill is internally coherent and doesn't request secrets or installs, but check two operational points before installing: (1) Ask the skill author or platform how image inputs are processed and stored — confirm whether images stay local or are sent to external services and whether they are logged/retained. (2) If you need higher accuracy or integration with nutrition databases, expect that additional API keys or external services may be required; those would be legitimate but should be disclosed. Also remember calorie estimates are inherently approximate and not a substitute for professional dietary advice.
能力评估
Purpose & Capability
Name and description align with the SKILL.md: estimating calories from textual descriptions, multi-item meals, and images is exactly what the instructions cover. No unrelated credentials, binaries, or config are requested.
Instruction Scope
SKILL.md stays on-topic (parsing food names/portions, summing meal calories, and describing assumptions). It mentions image-based estimation but does not specify how images are processed (locally vs. sent to external services); this is a functional gap rather than a security incoherence.
Install Mechanism
No install spec and no code files — instruction-only skills have the lowest installation risk. Nothing is downloaded or written to disk by the skill itself.
Credentials
The skill requires no environment variables, credentials, or config paths — this is proportionate to its stated functionality.
Persistence & Privilege
Default invocation settings (not always-enabled, agent-invocable) are used. The skill does not request persistent or elevated privileges.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install calorie-compass
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /calorie-compass 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Calorie Compass 1.0.0 – Initial release - Estimates calorie content from food names, portion sizes, or uploaded food images. - Supports calculations for individual items and full meals with multiple components. - Understands common quantity formats (grams, cups, slices, bowls, etc.). - Provides flexible, reasoned calorie estimates, clarifying assumptions and possible variations. - Delivers total and per-item calories, and may provide basic macronutrient data when details allow.
元数据
Slug calorie-compass
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Calorie Compass 是什么?

Estimate calorie content from food names, portion sizes, or food images. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 118 次。

如何安装 Calorie Compass?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install calorie-compass」即可一键安装,无需额外配置。

Calorie Compass 是免费的吗?

是的,Calorie Compass 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Calorie Compass 支持哪些平台?

Calorie Compass 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Calorie Compass?

由 rajib(@rajib76)开发并维护,当前版本 v1.0.0。

💬 留言讨论