Waimai
Help users make better takeout ordering decisions from public merchant and promotion signals.
What makes this skill useful:
- - It focuses on actual order economics, not just headline discounts.
- It helps users reason about 起送价, 配送费, 满减, and meal-size fit together.
- It is strongest when the user wants a fast recommendation for what to order and from where.
Commerce Matrix
This skill is the takeout-order economics node in the shopping matrix.
Prefer nearby skills when the task changes:
- -
meituan for Meituan-specific marketplace guidance when that repo is active - general shopping skills such as
jd-shopping, pdd-shopping, or taobao-shopping when the user is buying goods instead of ordering takeout
This is a low-sensitivity public skill. It focuses on public decision support and does not perform login, account access, cookie handling, order retrieval, coupon claiming, local database persistence, or browser automation runtime actions.
Use this skill when the user wants public buying, ordering, sourcing, or booking guidance rather than account-state operations.
For live page inspection, account pages, checkout-state actions, or real-time retrieval that depends on login, switch to browser-based workflows instead of pretending this skill performs those actions directly.
Read these references as needed:
- -
references/comparison-guide.md for supporting guidance - INLINECODE5 for supporting guidance
- INLINECODE6 for supporting guidance
Workflow
- 1. Identify the user's shopping, ordering, or booking need.
- Accept a product, merchant, ride, store, or booking scenario.
- If the request is too broad, ask one short clarifying question.
- 2. Focus on public decision-relevant factors.
- Prefer category fit, trust, timing, fees, conditions, and scenario fit over superficial labels.
- 3. Explain trade-offs.
- Say why the strongest option fits.
- Mention meaningful risks or caveats.
- 4. Give practical next-step advice.
- Tell the user what to verify before paying or placing an order.
Output
Use this structure unless the user asks for something shorter:
Best Option
State the strongest current choice.
Why
List the main reasons.
Caveats
List meaningful concerns or trade-offs.
Final Advice
Give a direct practical suggestion.
Quality bar
Do:
- - focus on public decision support
- explain trade-offs clearly
- stay honest about not doing account-state operations
Do not:
- - pretend to log in
- claim to retrieve orders, coupons, or account data
- store cookies or user data
- present heuristics as guaranteed outcomes
外卖
帮助用户根据公开的商家信息和促销信号，做出更好的外卖点餐决策。
该技能的实用性体现在：
- - 关注实际的订单经济性，而不仅仅是表面的折扣信息。
- 帮助用户综合考量起送价、配送费、满减优惠和餐品份量是否匹配。
- 当用户希望快速获得点什么、从哪点的推荐时，该技能表现最佳。
购物矩阵
该技能是购物矩阵中外卖订单经济性分析节点。
当任务发生变化时，优先使用邻近技能：
- - meituan：当美团仓库活跃时，提供美团特定市场指导
- 通用购物技能，如jd-shopping、pdd-shopping或taobao-shopping：当用户购买商品而非点外卖时使用
这是一个低敏感度的公开技能。它专注于公开决策支持，不执行登录、账户访问、Cookie处理、订单检索、优惠券领取、本地数据库持久化或浏览器自动化运行时操作。
当用户需要公开的购买、下单、采购或预订指导，而非账户状态操作时，使用此技能。
对于实时页面检查、账户页面、结账状态操作或依赖登录的实时检索，请切换到基于浏览器的工作流程，而不是假装此技能可以直接执行这些操作。
根据需要参考以下资料：
- - references/comparison-guide.md 获取辅助指导
- references/risk-signals.md 获取辅助指导
- references/output-patterns.md 获取辅助指导
工作流程
- 1. 识别用户的购物、下单或预订需求。
- 接受产品、商家、出行、门店或预订场景。
- 如果请求过于宽泛，提出一个简短的澄清性问题。
- 2. 聚焦于与公开决策相关的因素。
- 优先考虑品类匹配度、信任度、时效性、费用、条件以及场景适配性，而非表面标签。
- 3. 解释权衡取舍。
- 说明为什么最优选项最合适。
- 提及有意义的风险或注意事项。
- 4. 提供实用的后续步骤建议。
- 告诉用户在付款或下单前需要核实什么。
输出格式
除非用户要求更简短的内容，否则使用以下结构：
最佳选择
说明当前最优选择。
原因
列出主要原因。
注意事项
列出有意义的顾虑或权衡点。
最终建议
给出直接实用的建议。
质量标准
应做：
- - 专注于公开决策支持
- 清晰解释权衡取舍
- 诚实说明不执行账户状态操作
不应做：
- - 假装登录
- 声称能检索订单、优惠券或账户数据
- 存储Cookie或用户数据
- 将启发式方法呈现为有保证的结果
