whatsapp-flows
Authoring WhatsApp Business Flows with validation, component guidance, and server integration patterns. Use when building conversational experiences, collecting user data, implementing conditional logic, or integrating with backend endpoints.
What this skill does
# WhatsApp Flows Skill
Build conversational WhatsApp experiences with dynamic forms, conditional logic, and server integration.
## Quick Start
### What are WhatsApp Flows?
WhatsApp Flows are structured conversations that collect user input through a series of screens. Use them to:
- Collect information (forms, surveys)
- Implement conditional logic (eligibility checks, branching)
- Display dynamic data (products, prices, inventory)
- Validate user input server-side
- Complete multi-step processes
### 5 Key Concepts
1. **Screens** - Individual steps in your flow. Each has a unique ID and layout.
2. **Components** - Building blocks (TextInput, Dropdown, Footer, If, etc.)
3. **Form Data** - User input via `${form.field_name}` binding
4. **Server Data** - Dynamic data via `${data.field_name}` binding
5. **Actions** - What happens: navigate, data_exchange, complete, update_data, open_url
### Minimal Example
```json
{
"version": "7.1",
"screens": [
{
"id": "GREETING",
"title": "Greeting",
"layout": {
"type": "SingleColumnLayout",
"children": [
{
"type": "TextHeading",
"text": "Welcome!"
},
{
"type": "TextBody",
"text": "Please tell us your name to proceed.",
"markdown": true
},
{
"type": "TextInput",
"name": "name",
"label": "What's your name?",
"required": true
},
{
"type": "Footer",
"label": "Continue",
"on-click-action": {
"name": "navigate",
"next": {
"type": "screen",
"name": "CONFIRMATION"
}
}
}
]
}
},
{
"id": "CONFIRMATION",
"title": "Confirmation",
"terminal": true,
"success": true,
"layout": {
"type": "SingleColumnLayout",
"children": [
{
"type": "TextHeading",
"text": "Hello ${screen.GREETING.form.name}!"
},
{
"type": "Footer",
"label": "Done",
"on-click-action": {
"name": "complete",
"payload": {
"name": "${screen.GREETING.form.name}"
}
}
}
]
}
}
]
}
```
**Business 3.0 API Requirements:**
- Every screen MUST have a `title` property
- Action properties use `name` (not `action`) with nested structure
**When to add `data_api_version`:**
- Only include `"data_api_version": "3.0"` if your flow needs server integration (data validation, dynamic data, form submission to backend)
- If your flow is client-side only with no backend endpoints, omit this property
- See [server-integration.md](reference/server-integration.md) for details on setting up endpoints
---
## Business 3.0 API Requirements
WhatsApp Flows uses the Business 3.0 API which has specific requirements:
**Every screen MUST have:**
- `id` (required) - Unique screen identifier
- `title` (required) - Screen title for display and navigation
**Markdown formatting:**
- Only **TextBody** and **TextCaption** support markdown
- Set `"markdown": true` to enable formatting
- **TextHeading does NOT support markdown** (will cause validation error)
- Markdown is disabled by default if property omitted
**Optional server integration:**
- `data_api_version: "3.0"` - Only required if your flow calls backend endpoints
- `routing_model` - Only required with `data_api_version` for dynamic routing
**Minimal structure (no backend needed):**
```json
{
"version": "7.1",
"screens": [
{
"id": "SCREEN_ID",
"title": "Screen Title",
"layout": { ... }
}
]
}
```
**With server integration (backend endpoints):**
```json
{
"version": "7.1",
"data_api_version": "3.0",
"routing_model": { ... },
"screens": [
{
"id": "SCREEN_ID",
"title": "Screen Title",
"layout": { ... }
}
]
}
```
See **[constraints.md](reference/constraints.md)** for complete validation rules and **[server-integration.md](reference/server-integration.md)** for endpoint setup.
---
## Essential Constraints
| Item | Limit | Impact |
|------|-------|--------|
| Components per screen | 50 | Split into multiple screens if exceeded |
| Nesting depth (If/Switch) | 3 levels | Simplify logic or use separate screens |
| Flow JSON size | 10MB | Compress or split large flows |
| Text heading length | 80 chars | Be concise with titles (NO markdown) |
| Text body length | 4096 chars | Supports markdown v5.1+ (set `markdown: true`) |
| Dropdown options | 200 (static) | Use dynamic data for more options |
| Image max size | 300KB | Optimize images before including |
| Image count per screen | 3 | Limit media usage per screen |
| Screen title | Required | Business 3.0 API requirement |
See **[constraints.md](reference/constraints.md)** for complete reference.
---
## Core Reference Files
Navigate to these for detailed guidance:
### Components
**[reference/components.md](reference/components.md)** - All 22 components with syntax and examples
- Text: TextHeading, TextSubheading, TextBody, TextCaption, RichText
- Input: TextInput (7 types), TextArea, DatePicker
- Selection: Dropdown, CheckboxGroup, RadioButtonsGroup, OptIn, ChipsSelector, NavigationList
- Media: Image, ImageCarousel
- Actions: Footer, EmbeddedLink
- Logic: If, Switch
### Actions
**[reference/actions.md](reference/actions.md)** - Control flow progression
- `navigate` - Move to next screen
- `data_exchange` - Send to server, receive next screen
- `complete` - End flow with response
- `update_data` - Update screen state (v6.0+)
- `open_url` - Open external link (v6.0+)
### Data Binding
**[reference/data-binding.md](reference/data-binding.md)** - How to reference data
- Form data: `${form.field_name}`
- Server data: `${data.field_name}`
- Global references: `${screen.SCREEN_ID.form.field}`
- Nested expressions: `${`...`}` (v6.0+)
### Conditional Logic
**[reference/conditional-logic.md](reference/conditional-logic.md)** - If and Switch components
- Boolean conditions with If
- Multi-way branching with Switch
- Nested conditionals (max 3 levels)
- Conditional navigation and inputs
### Server Integration
**[reference/server-integration.md](reference/server-integration.md)** - Backend integration
- Routing models for flow control
- Data endpoints (request/response format)
- Dynamic data from server
- Error handling and validation
### Constraints & Validation
**[reference/constraints.md](reference/constraints.md)** - Limits and rules
- Character limits per component
- Component counts per screen
- Validation checklist
- Common errors and fixes
### Security & Best Practices
**[reference/security.md](reference/security.md)** - Secure flows
- Sensitive data handling
- HTTPS requirements
- Input validation patterns
- GDPR compliance
### Versions & Features
**[reference/versions.md](reference/versions.md)** - Feature matrix v4.0-7.1
- Component availability by version
- Breaking changes between versions
- Migration guide
- Version recommendations
### Navigation
**[reference/TABLE_OF_CONTENTS.md](reference/TABLE_OF_CONTENTS.md)** - Find what you need
- By topic, use case, component type
- Quick reference guides
---
## Examples
See **[examples.md](examples.md)** for 4 complete, working flows:
1. **Simple Multi-Screen Survey** - Basic form with navigation
2. **Conditional Age Verification** - If/Switch with routing decisions
3. **E-Commerce Product Selection** - Dynamic data from server
4. **Server Validation Flow** - Email validation with error handling
---
## Common Tasks
### I need to add formatted text (bold, lists, emphasis)
1. Use **TextBody** or **TextCaption** components (not TextHeading)
2. Add `"markdown": true` property to enable formatting
3. Use markdown syntax: `**bold**`, `*italic*`, `\n` for line breaks, `•Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.