swiggy
Order food, groceries, and book restaurants in India via Swiggy's MCP servers. Food delivery, Instamart groceries, and Dineout restaurant bookings with safety-first confirmation workflow.
What this skill does
# Swiggy Skill
Order food, groceries, and book restaurants in India via Swiggy's MCP servers.
## Installation
The skill includes a `swiggy` CLI binary. After installing the skill:
```bash
cd skills/swiggy
npm link
```
This creates a global `swiggy` command. Verify with: `which swiggy`
## When to Use
- Food delivery: "Order biryani", "What's open late?", "Team lunch for 8"
- Groceries (Instamart): "Get eggs and milk", "Weekly groceries", "Recipe ingredients"
- Restaurant bookings (Dineout): "Book dinner Saturday 8pm", "Italian in Koramangala"
## Available Commands
### Food Delivery
```bash
# Search restaurants
swiggy food search "biryani" --location "Koramangala, Bengaluru"
# Get menu
swiggy food menu <restaurant-id>
# Cart management
swiggy food cart add <item-id> --quantity 2
swiggy food cart show
swiggy food cart clear
# Order (requires confirmation)
swiggy food order --address "home" --confirm
```
### Instamart (Groceries)
```bash
# Search products
swiggy im search "eggs" --location "HSR Layout, Bengaluru"
# Cart operations
swiggy im cart add <item-id> --quantity 3
swiggy im cart show
swiggy im cart clear
# Checkout (requires confirmation)
swiggy im order --address "home" --confirm
```
### Dineout (Restaurant Bookings)
```bash
# Search restaurants
swiggy dineout search "Italian Indiranagar"
# Get details
swiggy dineout details <restaurant-id>
# Check availability
swiggy dineout slots <restaurant-id> --date 2026-01-30
# Book table (free bookings only, requires confirmation)
swiggy dineout book <restaurant-id> --date 2026-01-30 --time 20:00 --guests 2 --confirm
```
## CRITICAL: Safety Rules
### ⚠️ NEVER Auto-Order
**ALWAYS get explicit confirmation before placing orders.**
1. **Show cart preview first:**
- All items with quantities and prices
- Total amount
- Delivery address
- Estimated delivery time (food/groceries)
2. **Ask for confirmation:**
```
Ready to order:
- 2x Chicken Biryani (₹500)
- 1x Raita (₹60)
Total: ₹560 + delivery
Deliver to: Home (HSR Layout)
ETA: 30-40 mins
Confirm order? (yes/no)
```
3. **Only after user says YES:**
- Run the order command with `--confirm` flag
- Log to `memory/swiggy-orders.json`
### COD Warning
Swiggy MCP currently supports **Cash on Delivery only**. Orders **cannot be cancelled** once placed. Always double-check before confirming.
### Address Handling
- User may say "home", "office", etc. - map to actual addresses from USER.md or ask
- Always confirm delivery location in preview
- For Dineout, location is used for search only (not delivery)
## Workflow Examples
### Food Order Flow
```bash
# 1. Search
swiggy food search "biryani near Koramangala"
# 2. Browse menu (use restaurant ID from search)
swiggy food menu rest_12345
# 3. Add to cart
swiggy food cart add item_67890 --quantity 1
# 4. Preview cart
swiggy food cart show
# 5. Show preview to user, ask confirmation
# 6. If confirmed, order
swiggy food order --address "HSR Layout, Sector 2, Bengaluru" --confirm
```
### Grocery Shopping Flow
```bash
# 1. Search items
swiggy im search "eggs" --location "Koramangala"
swiggy im search "milk" --location "Koramangala"
# 2. Add to cart
swiggy im cart add item_11111 --quantity 2
swiggy im cart add item_22222 --quantity 1
# 3. Preview
swiggy im cart show
# 4. Confirm with user
# 5. Checkout
swiggy im order --address "Koramangala, Bengaluru" --confirm
```
### Restaurant Booking Flow
```bash
# 1. Search
swiggy dineout search "Italian Indiranagar"
# 2. Check details
swiggy dineout details rest_99999
# 3. Check slots
swiggy dineout slots rest_99999 --date 2026-01-30
# 4. Show options to user, confirm choice
# 5. Book
swiggy dineout book rest_99999 --date 2026-01-30 --time 20:00 --guests 2 --confirm
```
## Error Handling
- **No results:** Suggest broader search or different location
- **Out of stock:** Show alternatives
- **No slots available:** Suggest different times/dates
- **Authentication required:** User needs to authenticate via OAuth (handled by MCP)
## Tips
- For team orders: build cart iteratively, ask for preferences
- For budget shopping: filter results by price, show running total
- For recipe-to-cart: search each ingredient, add progressively
- For late night: mention delivery time in search criteria
## Order Logging
After successful order, append to `memory/swiggy-orders.json`:
```json
{
"timestamp": "2026-01-28T21:16:00+05:30",
"type": "food",
"items": [...],
"total": "₹560",
"address": "HSR Layout",
"orderId": "..."
}
```
## Authentication
Swiggy MCP uses OAuth. First use will trigger auth flow. The `swiggy` CLI handles this via mcporter.
## Dependencies
- Requires `mcporter` skill (uses it under the hood)
- Node.js runtime for the CLI wrapper
## Known Limitations
- COD only (no online payment yet)
- Orders cannot be cancelled
- Dineout: free bookings only
- Don't open Swiggy app while using MCP (session conflicts)
---
**Remember: Confirmation BEFORE ordering. Every. Single. Time.** 🐾
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.