食物数据库查询技能 workflow skill. Use this skill when the user needs Food Database Query and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
This public intake copy packages plugins/antigravity-awesome-skills/skills/food-database-query from https://github.com/sickn33/antigravity-awesome-skills into the native Omni Skills editorial shape without hiding its origin.
Use it when the operator needs the upstream workflow, support files, and repository context to stay intact while the public validator and private enhancer continue their normal downstream flow.
This intake keeps the copied upstream files intact and uses EXTERNAL_SOURCE.json plus ORIGIN.md as the provenance anchor for review.
Imported source sections that did not map cleanly to the public headings are still preserved below or in the support files. Notable imported sections: 技能概述, 数据源, 功能模块, 数据结构, RDA参考值, 集成功能.
Use this section as the trigger filter. It should make the activation boundary explicit before the operator loads files, runs commands, or opens a pull request.
| Situation | Start here | Why it matters |
|---|---|---|
| First-time use | EXTERNAL_SOURCE.json | Confirms repository, branch, commit, and imported path before touching the copied workflow |
| Provenance review | ORIGIN.md | Gives reviewers a plain-language audit trail for the imported source |
| Workflow execution | SKILL.md | Starts with the smallest copied file that materially changes execution |
| Supporting context | SKILL.md | Adds the next most relevant copied source file without loading the entire package |
| Handoff decision | ## Related Skills | Helps the operator switch to a stronger native skill when the task drifts |
This workflow is intentionally editorial and operational at the same time. It keeps the imported source useful to the operator while still satisfying the public intake standards that feed the downstream enhancer flow.
本技能提供全面的营养食物数据库查询功能,支持食物营养信息查询、比较、推荐和自动营养计算。
核心功能:
Use @food-database-query-v2 to handle <task>. Start from the copied upstream workflow, load only the files that change the outcome, and keep provenance visible in the answer.
Explanation: This is the safest starting point when the operator needs the imported workflow, but not the entire repository.
Review @food-database-query-v2 against EXTERNAL_SOURCE.json and ORIGIN.md, then explain which copied upstream files you would load first and why.
Explanation: Use this before review or troubleshooting when you need a precise, auditable explanation of origin and file selection.
Use @food-database-query-v2 for <task>. Load only the copied references, examples, or scripts that change the outcome, and name the files explicitly before proceeding.
Explanation: This keeps the skill aligned with progressive disclosure instead of loading the whole copied package by default.
Review @food-database-query-v2 using the copied upstream files plus provenance, then summarize any gaps before merge.
Explanation: This is useful when the PR is waiting for human review and you want a repeatable audit packet.
Treat the generated public skill as a reviewable packaging layer around the upstream repository. The goal is to keep provenance explicit and load only the copied source material that materially improves execution.
Symptoms: The result ignores the upstream workflow in plugins/antigravity-awesome-skills/skills/food-database-query, fails to mention provenance, or does not use any copied source files at all.
Solution: Re-open EXTERNAL_SOURCE.json, ORIGIN.md, and the most relevant copied upstream files. Load only the files that materially change the answer, then restate the provenance before continuing.
Symptoms: Reviewers can see the generated SKILL.md, but they cannot quickly tell which references, examples, or scripts matter for the current task.
Solution: Point at the exact copied references, examples, scripts, or assets that justify the path you took. If the gap is still real, record it in the PR instead of hiding it.
Symptoms: The imported skill starts in the right place, but the work turns into debugging, architecture, design, security, or release orchestration that a native skill handles better. Solution: Use the related skills section to hand off deliberately. Keep the imported provenance visible so the next skill inherits the right context instead of starting blind.
@2d-games-v2 - Use when the work is better handled by that native specialization after this imported skill establishes context.@3d-games-v2 - Use when the work is better handled by that native specialization after this imported skill establishes context.@firecrawl-scraper-v2 - Use when the work is better handled by that native specialization after this imported skill establishes context.@firmware-analyst-v2 - Use when the work is better handled by that native specialization after this imported skill establishes context.Use this support matrix and the linked files below as the operator packet for this imported skill. They should reflect real copied source material, not generic scaffolding.
| Resource family | What it gives the reviewer | Example path |
|---|---|---|
references | copied reference notes, guides, or background material from upstream | references/n/a |
examples | worked examples or reusable prompts copied from upstream | examples/n/a |
scripts | upstream helper scripts that change execution or validation | scripts/n/a |
agents | routing or delegation notes that are genuinely part of the imported package | agents/n/a |
assets | supporting assets or schemas copied from the source package | assets/n/a |
data/food-database.jsondata/food-categories.json用途: 根据食物名称查询营养信息
支持输入:
查询流程:
返回信息:
示例:
# 用户输入: "燕麦"
# 返回:
{
"name": "燕麦",
"name_en": "Oats",
"category": "谷物类",
"nutrition_per_100g": {
"calories": 389,
"protein_g": 16.9,
"carbs_g": 66.3,
"fat_g": 6.9,
"fiber_g": 10.6,
# ... 更多营养素
},
"health_tags": ["高纤维", "低GI"],
"glycemic_index": {"value": 55, "level": "低"}
}
用途: 根据营养特征搜索食物
搜索条件:
搜索逻辑:
# 示例: 搜索"高蛋白 低卡路里"
def search_foods(criteria):
results = []
for food in database:
protein = food.nutrition_per_100g.protein_g
calories = food.nutrition_per_100g.calories
# 定义阈值
high_protein = protein >= 15 # 每100g≥15g蛋白质
low_calorie = calories <= 150 # 每100g≤150卡
if high_protein and low_calorie:
results.append(food)
return sorted(results, key=lambda x: x.protein_g, reverse=True)
返回格式:
用途: 按食物分类浏览所有食物
分类层级:
蛋白质来源
├── 肉类
├── 禽类
├── 鱼虾贝类
├── 蛋类
├── 豆类
├── 坚果种子
└── 乳制品
浏览模式:
功能: 比较两种食物的营养差异
比较维度:
计算逻辑:
def compare_foods(food1, food2):
comparison = {}
# 宏量营养素差异
for nutrient in ["calories", "protein_g", "fiber_g"]:
val1 = food1.nutrition_per_100g[nutrient]
val2 = food2.nutrition_per_100g[nutrient]
diff = val1 - val2
percent = (diff / val2) * 100
comparison[nutrient] = {
"food1": val1,
"food2": val2,
"difference": diff,
"percent_change": percent,
"better": "food1" if diff > 0 else "food2"
}
return comparison
输出格式:
支持模式:
示例: /nutrition compare 三文鱼 鸡胸肉 营养素
推荐逻辑:
def recommend_by_nutrient(nutrient, min_value=None, max_value=None):
recommendations = []
for food in database:
value = food.nutrition_per_100g[nutrient]
# 筛选符合条件
if min_value and value < min_value:
continue
if max_value and value > max_value:
continue
recommendations.append({
"food": food,
"value": value,
"rda_percent": (value / RDA[nutrient]) * 100
})
# 按含量排序
return sorted(recommendations, key=lambda x: x["value"], reverse=True)
推荐类别:
支持组合条件:
排序策略:
高血压 (DASH饮食):
糖尿病:
高血脂:
骨质疏松:
贫血:
输入解析:
def parse_food_input(text):
# 示例: "燕麦粥 1杯 + 鸡蛋 1个 + 牛奶 250ml"
foods = []
portions = []
# 识别食物名称
for item in text.split("+"):
food_name = extract_food_name(item) # "燕麦粥"
portion = extract_portion(item) # "1杯"
# 标准化食物名称
standard_name = normalize_food_name(food_name) # "燕麦"
# 查询数据库
food_data = query_database(standard_name)
foods.append(food_data)
portions.append(parse_portion(portion))
return foods, portions
常见份量:
份量数据库:
{
"common_portions": [
{
"amount": 1,
"unit": "个",
"weight_g": 50,
"description": "1个大号鸡蛋"
},
{
"amount": 1,
"unit": "杯",
"weight_g": 240,
"description": "1杯牛奶"
}
]
}
计算公式:
def calculate_nutrition(food, portion_grams):
nutrition = {}
for nutrient, value_per_100g in food.nutrition_per_100g.items():
# 按100g比例计算
nutrition[nutrient] = (value_per_100g * portion_grams) / 100
return nutrition
考虑因素:
示例:
支持同义词:
匹配算法:
def find_food(name):
# 1. 精确匹配主名称
if name in database:
return database[name]
# 2. 匹配别名
for food in database:
if name in food.aliases:
return food
# 3. 模糊匹配
matches = fuzzy_search(name)
if matches:
return matches[0]
return None
编辑距离算法:
def fuzzy_search(name, max_distance=2):
matches = []
for food in database:
# 计算编辑距离
distance = levenshtein_distance(name, food.name)
if distance <= max_distance:
matches.append((food, distance))
# 按距离排序
return sorted(matches, key=lambda x: x[1])
{
"id": "FD_001",
"name": "燕麦",
"name_en": "Oats",
"aliases": ["燕麦片", "oats", "rolled oats"],
"category": "grains",
"subcategory": "whole_grains",
"standard_portion": {
"amount": 100,
"unit": "g",
"description": "100克"
},
"nutrition_per_100g": {
"calories": 389,
"protein_g": 16.9,
"carbs_g": 66.3,
"fat_g": 6.9,
"fiber_g": 10.6,
"sugar_g": 0.99,
"saturated_fat_g": 1.4,
"monounsaturated_fat_g": 2.5,
"polyunsaturated_fat_g": 2.9,
"trans_fat_g": 0,
"water_g": 8.9,
"vitamin_a_mcg": 0,
"vitamin_c_mg": 0,
"vitamin_d_mcg": 0,
"vitamin_e_mg": 1.1,
"vitamin_k_mcg": 1.9,
"thiamine_mg": 0.763,
"riboflavin_mg": 0.139,
"niacin_mg": 6.921,
"vitamin_b6_mg": 0.165,
"folate_mcg": 56,
"vitamin_b12_mcg": 0,
"pantothenic_acid_mg": 1.349,
"biotin_mcg": 0,
"calcium_mg": 54,
"iron_mg": 4.72,
"magnesium_mg": 177,
"phosphorus_mg": 523,
"potassium_mg": 429,
"sodium_mg": 2,
"zinc_mg": 3.97,
"copper_mg": 0.526,
"manganese_mg": 4.916,
"selenium_mcg": 2.8,
"iodine_mcg": 0
},
"special_nutrients": {
"omega_3_g": 0.685,
"omega_6_g": 1.428,
"choline_mg": 43.4,
"beta_carotene_mcg": 0,
"lutein_mcg": 0,
"zeaxanthin_mcg": 0
},
"glycemic_index": {
"value": 55,
"level": "低",
"glycemic_load": 11
},
"common_portions": [
{
"amount": 30,
"unit": "g",
"description": "1/4杯",
"approximate_volume": "1/4 cup"
},
{
"amount": 40,
"unit": "g",
"description": "1/3杯",
"approximate_volume": "1/3 cup"
},
{
"amount": 200,
"unit": "ml",
"description": "煮熟1杯",
"notes": "煮熟后体积增加"
}
],
"cooking_effects": {
"boiling": {
"weight_change_percent": 200,
"nutrient_changes": {
"vitamin_c_retention": 0,
"b_vitamins_retention": 60
}
}
},
"health_tags": ["高纤维", "低GI", "无麸质选项", "心脏健康"],
"suitable_for": ["素食者", "高血压", "糖尿病", "高血脂"],
"notes": "富含β-葡聚糖,有助于降低胆固醇"
}
RDA = {
# 宏量营养素
"calories": 2500, # 中等活动水平
"protein_g": 56,
"carbs_g": 130, # 最低值
"fiber_g": 38,
# 维生素
"vitamin_a_mcg": 900,
"vitamin_c_mg": 90,
"vitamin_d_mcg": 15,
"vitamin_e_mg": 15,
"vitamin_k_mcg": 120,
"thiamine_mg": 1.2,
"riboflavin_mg": 1.3,
"niacin_mg": 16,
"vitamin_b6_mg": 1.3,
"folate_mcg": 400,
"vitamin_b12_mcg": 2.4,
"pantothenic_acid_mg": 5,
"biotin_mcg": 30,
# 矿物质
"calcium_mg": 1000,
"iron_mg": 8,
"magnesium_mg": 400,
"phosphorus_mg": 700,
"potassium_mg": 3400,
"sodium_mg": 1500, # 上限
"zinc_mg": 11,
"copper_mg": 0.9,
"manganese_mg": 2.3,
"selenium_mcg": 55
}
RDA_FEMALE = {
"calories": 2000, # 中等活动水平
"protein_g": 46,
"fiber_g": 25,
"iron_mg": 18, # 育龄期
# ... 其他略有差异
}
用户输入:
/nutrition record breakfast 燕麦粥 1杯 + 鸡蛋 1个 + 牛奶 250ml
系统处理:
返回结果:
✅ 早餐已记录
**食物**: 燕麦粥(1杯) + 鸡蛋(1个) + 牛奶(250ml)
**营养汇总**:
- 卡路里: 417 卡
- 蛋白质: 25.1g
- 碳水化合物: 48.5g
- 脂肪: 15.2g
- 膳食纤维: 8.2g
**微量营养素亮点**:
- 维生素D: 3.1 μg (21% RDA)
- 钙: 332 mg (33% RDA)
- 维生素B12: 1.3 μg (54% RDA)
用户输入:
/nutrition food 三文鱼
返回结果:
# 三文鱼 营养信息
#### Imported: 基本信息
- **名称**: 三文鱼 (Salmon)
- **分类**: 蛋白质来源 > 鱼虾贝类
- **标准份量**: 100克
#### Imported: 宏量营养素 (每100克)
- **卡路里**: 208 卡
- **蛋白质**: 20g ✅
- **碳水化合物**: 0g
- **脂肪**: 13g
- **Omega-3**: 2.5g ✅✅✅
#### Imported: 营养亮点
- ✅✅✅ 富含Omega-3脂肪酸 (EPA+DHA)
- ✅✅ 高质量蛋白质
- ✅ 富含维生素D (11μg)
- ✅ 富含维生素B12 (3.2μg)
#### Imported: 健康标签
- ✅ 高蛋白
- ✅ 富含Omega-3
- ✅ 心脏健康
- ✅ 大脑健康
#### Imported: 推荐份量
- 100-150g/餐 (每周2-3次)
用户输入:
/nutrition compare 鸡胸肉 三文鱼
返回结果:
# 食物比较: 鸡胸肉 vs 三文鱼
#### Imported: 营养对比 (每100克)
| 营养素 | 鸡胸肉 | 三文鱼 | 差异 |
|--------|--------|--------|------|
| 卡路里 | 165 | 208 | +26% |
| 蛋白质 (g) | 31 | 20 | -35% ✅ |
| 脂肪 (g) | 3.6 | 13 | +261% |
| Omega-3 (g) | 0.1 | 2.5 | +2400% ✅✅✅ |
#### Imported: 推荐建议
**选择鸡胸肉更适合**:
- ✅ 减脂期间 (低卡高蛋白)
- ✅ 控制脂肪摄入
- ✅ 蛋白质需求高
**选择三文鱼更适合**:
- ✅ 心脏健康 (高Omega-3)
- ✅ 大脑健康 (DHA)
- ✅ 抗炎需求
data/food-database.jsondata/food-categories.json.claude/commands/nutrition.md.claude/skills/food-database-query/SKILL.md技能版本: v1.0 最后更新: 2026-01-06 维护者: WellAlly Tech