instances/xiaodazi/skills/nutrition-analyzer/SKILL.md
Analyze food photos or descriptions to estimate nutritional content (calories, protein, carbs, fat). Provide dietary advice and meal tracking.
npx skillsauth add malue-ai/dazee-small nutrition-analyzerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
分析食物描述或照片,估算营养成分,提供饮食建议。
用户描述食物,LLM 基于营养知识估算:
输入: "一碗白米饭 + 红烧排骨三块 + 炒青菜一盘"
输出:
┌──────────┬───────┬────────┬────────┬────────┐
│ 食物 │ 热量 │ 蛋白质 │ 碳水 │ 脂肪 │
├──────────┼───────┼────────┼────────┼────────┤
│ 白米饭 │ 230卡 │ 4g │ 50g │ 0.5g │
│ 红烧排骨 │ 350卡 │ 25g │ 8g │ 24g │
│ 炒青菜 │ 80卡 │ 3g │ 5g │ 5g │
├──────────┼───────┼────────┼────────┼────────┤
│ 合计 │ 660卡 │ 32g │ 63g │ 29.5g │
└──────────┴───────┴────────┴────────┴────────┘
评价:热量适中,蛋白质达标,碳水偏高。
建议:搭配更多蔬菜,减少米饭量至半碗。
如果 LLM 支持视觉输入(如 Claude vision / GPT-4V),可直接分析食物照片。
# 存储饮食记录
mkdir -p ~/.xiaodazi/nutrition
# 当日记录
cat >> ~/.xiaodazi/nutrition/$(date +%Y-%m-%d).json << 'EOF'
{"meal": "午餐", "time": "12:30", "foods": [...], "total_calories": 660}
EOF
# 查看当日汇总
cat ~/.xiaodazi/nutrition/$(date +%Y-%m-%d).json
# USDA FoodData Central(免费,无需 Key)
curl -s "https://api.nal.usda.gov/fdc/v1/foods/search?query=chicken+breast&api_key=DEMO_KEY&pageSize=3" | python3 -c "
import json, sys
data = json.load(sys.stdin)
for food in data.get('foods', [])[:3]:
name = food.get('description', '')
nutrients = {n['nutrientName']: n['value'] for n in food.get('foodNutrients', [])[:10]}
print(f'{name}:')
for k, v in list(nutrients.items())[:5]:
print(f' {k}: {v}')
"
development
Local web search (Tavily/Exa, requires API Key). For quick searches. If no Key configured or deep research needed, use cloud_agent instead.
development
Get current weather and forecasts (no API key required).
tools
Send WhatsApp messages to other people or search/sync WhatsApp history via the wacli CLI (not for normal user chats).
tools
Start voice calls via the Moltbot voice-call plugin.