技能详情（站内镜像，无评论）
作者：ASP @anugotta
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v1.0.2
统计：⭐ 0 · 32 · 0 current installs · 0 all-time installs
⭐ 0
安装量（当前） 0
🛡 VirusTotal ：良性 · OpenClaw ：良性
Package：anugotta/india-food-ordering
安全扫描（ClawHub）
- VirusTotal ：良性
- OpenClaw ：良性
OpenClaw 评估
Instruction-only skill that documents a safe, human-confirmed multi-vendor food-ordering workflow; it asks no credentials and installs nothing, and its requests are consistent with its stated purpose.
目的
The name/description match the instructions: all files describe multi-vendor ordering workflows, confirmation prompts, and fallback logic. The skill requests no env vars, binaries, or installs that would be unrelated to food ordering.
说明范围
SKILL.md stays largely within ordering workflow boundaries (search, build cart, confirm, place order). It assumes existence of external 'connectors' and asks the agent to execute order commands and to use user context (saved addresses, prior orders). That is expected for an ordering skill, but the wording is somewhat high-level/vague (e.g., 'Execute order command', 'reconstruct likely cart from user message/context'), which grants the agent di…
安装机制
Instruction-only; no install spec, no downloads, and no code execution artifacts. This is the lowest-risk install surface.
证书
The skill declares no required environment variables, credentials, or config paths. References to logging and saved addresses are optional/operational and are proportionate to an ordering assistant, but you should confirm connectors handle payment credentials separately and securely.
持久
always:false and no install behavior. The skill does not request persistent system presence or modify other skills/config; it relies on separate connectors for auth and order execution.
综合结论
This skill is a documentation/workflow guide (no code, no installs, no secrets requested) and appears internally consistent. Before enabling it for live ordering: (1) verify the actual Swiggy/Zomato connectors the agent will use—confirm they require and store credentials securely and that you trust those connectors; (2) test in 'dry run' mode so the agent builds carts and prompts but cannot place real orders until you confirm; (3) confirm the …
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「India Food Ordering - Swiggy, Zomato etc」。简介：Unified food ordering assistant for India that supports Swiggy and Zomato workf…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/anugotta/india-food-ordering/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: india-food-ordering
description: Unified food ordering assistant for India that supports Swiggy and Zomato workflows with strict pre-order confirmation, cart preview, address checks, and vendor fallback logic.
metadata: {"openclaw":{"emoji":"🍽️","homepage":"https://clawhub.ai/regalstreak/swiggy"}}
---
# India Food Ordering (Swiggy + Zomato)
## What this skill does
Provides one consistent ordering workflow across both vendors:
- Swiggy
- Zomato
Additional vendor targets (when connector/MCP support exists):
- EatSure
- magicpin
- ONDC-compatible food apps
- Blinkit Bistro / Zepto Cafe style quick-food verticals
This skill focuses on safe, human-confirmed ordering operations.
## Disclaimer
This skill provides workflow guidance and command orchestration only. It does not guarantee availability, pricing, ETA, or cancellation rights on either platform. Vendor capabilities and policies can change without notice.
Use at your own risk. The skill author/publisher/developer is not liable for direct or indirect loss, wrong orders, payment issues, delays, cancellations, or other damages from use or misuse of this guidance.
## Core safety rules (non-negotiable)
1. **Never place an order without explicit user confirmation**
2. **Always show full cart preview before confirmation**
3. **Always confirm delivery address before placing order**
4. **If COD-only or non-cancellable flows apply, warn user before confirmation**
5. **If uncertain about item, price, or address, ask before proceeding**
## Standard workflow
### Step 1: Collect intent
- cuisine / item
- budget
- location (delivery area)
- delivery speed preference
- preferred vendor (optional)
### Step 2: Vendor discovery
- Search both vendors when possible.
- If only one vendor is available, continue with it.
- If both are available, compare and present best options.
### Step 3: Compare options
Return side-by-side:
- vendor
- restaurant
- item totals
- delivery fee
- taxes/charges
- ETA
- rating (if available)
### Step 4: Build cart
- add selected items
- show running subtotal
- check item availability
### Step 5: Mandatory confirmation prompt
Use this exact style:
```text
Ready to place order:
- Vendor: <Swiggy/Zomato>
- Restaurant: <name>
- Items: <list with qty>
- Total payable: <amount>
- Delivery address: <full address label>
- ETA: <time window>
- Notes: <COD only / non-cancellable / special terms if any>
Confirm order? (yes/no)
```
### Step 6: Place order only after "yes"
- Execute order command
- Return order ID/reference immediately
- Share tracking handoff steps
## Vendor routing logic
- If user specifies vendor, honor it unless unavailable.
- If unspecified, choose:
1. lower final payable
2. faster ETA
3. higher reliability/rating
- If selected vendor fails, offer fallback on the other vendor and re-confirm.
## Error handling
- **No restaurants found**: broaden radius or cuisine terms.
- **Item unavailable**: propose equivalent items.
- **Cart mismatch**: re-fetch cart and re-confirm.
- **Auth/session issue**: ask user to re-authenticate vendor connector.
- **Payment/checkout failure**: do not auto-retry order placement; ask user.
## Output format
When helping user order, respond in this structure:
1. Top options (max 3)
2. Recommended vendor and reason
3. Cart summary
4. Confirmation question
## Setup
Read [setup.md](setup.md) on first use.
## Validation
Run [validation-checklist.md](validation-checklist.md) before production usage.
## References
- Operational notes: [vendor-playbook.md](vendor-playbook.md)
- Prompt examples: [examples.md](examples.md)
- Safety and QA checks: [validation-checklist.md](validation-checklist.md)
- Launch flow: [launch-playbook.md](launch-playbook.md)