efecto-web-design
Design web pages and app UIs with Efecto — create sessions, build layouts with JSX and Tailwind CSS, manage artboards, and push real-time design changes via MCP tools. Use when asked to "design a page", "build a landing page", "create a website", "design a dashboard", "make a UI", or any visual design task. Requires Efecto MCP server.
What this skill does
# Efecto — Design Web Pages with AI
Efecto is a real-time web design tool that AI agents control programmatically. You create a **session**, the user opens a URL in their browser, and you push design commands that render instantly. Every node maps to a real HTML element styled with Tailwind CSS — web-native, semantic, and pixel-accurate.
---
## Setup
This skill requires the **Efecto MCP server**. Check if it's available by looking for tools like `create_session`, `add_section`, or `get_document` in your tool list.
**If Efecto tools are NOT available, install the MCP server:**
### Claude Code
```bash
claude mcp add efecto -- npx -y @efectoapp/mcp
```
### Cursor
Add to `.cursor/mcp.json`:
```json
{
"mcpServers": {
"efecto": {
"command": "npx",
"args": ["-y", "@efectoapp/mcp"]
}
}
}
```
### Windsurf / VS Code / Other MCP Clients
```json
{
"mcpServers": {
"efecto": {
"command": "npx",
"args": ["-y", "@efectoapp/mcp"]
}
}
}
```
Once installed, you'll have access to 68 MCP tools, including image search and native animation authoring. The MCP server connects your agent to the Efecto design canvas at [efecto.app](https://efecto.app).
---
## How Sessions Work
```
Agent ──POST /execute──> Server ──SSE──> Browser (renders live)
Agent <──poll/response── Server <──POST── Browser (returns results)
```
1. You create a session via the MCP server or REST API
2. The user opens the returned Efecto URL in their browser
3. You push tool calls — each one executes in the browser and returns a result
4. The user sees every change live as you build the design
Sessions expire after 2 hours of inactivity. The browser must be connected before tool calls can execute. If you restart or lose the MCP process, call `attach_session` with the user's current Efecto URL instead of creating a duplicate session.
---
## Quick Start — Build a Page in 7 Steps
### Step 1: Create a Session
```
create_session
label: "Landing page design"
```
Returns `{ sessionId, documentId, designUrl }`. Tell the user to open the URL. The session ID is stored automatically — all subsequent tools use it.
If the user already has an Efecto URL with `?session=...`, resume it:
```
attach_session
designUrl: "https://efecto.app/design/<file-id>/untitled?session=<session-id>"
```
**Do not call `create_session` again to "reconnect".** Use `attach_session` for an existing URL. A second `create_session` call refuses to overwrite a paired session unless you pass `force: true`.
### Step 2: Wait for Browser Connection
```
wait_for_connection
```
Blocks until the browser opens the URL and pairs (default 120s). Returns immediately if already paired.
To inspect routing state at any time:
```
session_status # legacy single-session shape (sessionId, paired, browserConnected, knownSessions)
session_status { all: true } # list shape — all sessions in this MCP process with isActive / paired flags
```
### Step 3: Create an Artboard
```
create_artboard
name: "Homepage"
width: 1440
height: 900
backgroundColor: "#ffffff"
className: "flex flex-col"
```
Returns the artboard ID. **Always set className to "flex flex-col"** so children stack vertically.
### Step 4: Add Sections with JSX
```
add_section
parentId: "<artboard-id>"
jsx: '<nav className="flex items-center justify-between px-16 py-5 bg-white w-full">
<h2 className="text-xl font-bold text-gray-900">Acme</h2>
<div className="flex items-center gap-8">
<a className="text-sm text-gray-600" href="#">Features</a>
<a className="text-sm text-gray-600" href="#">Pricing</a>
<button className="px-4 py-2 text-sm font-medium text-white bg-gray-900 rounded-lg">Get Started</button>
</div>
</nav>'
```
This is the most efficient way to build complex layouts — one JSX string per section.
### Step 5: Read Current State
```
get_document
```
Returns JSX-like markup with `data-id` attributes on every node. Use these IDs for updates.
### Step 6: Fine-Tune with Updates
```
batch_update
updates: [
{ nodeId: "abc", className: "text-2xl font-extrabold text-gray-900" },
{ nodeId: "def", textContent: "Updated heading text" }
]
```
### Step 7: Iterate
Repeat Steps 4-6 to add more sections, adjust styling, and refine the design. The user sees every change in real time.
---
## The Design Tools
### Reading State
| Tool | Purpose |
|------|---------|
| `get_selection` | Returns currently selected nodes/artboards with JSX subtrees |
| `get_document` | Returns document as JSX. Scoped modes (preferred on large docs): `outline: true` (one-line summary per top-level child), `artboardId` (single artboard), `maxDepth` (cap descent; 0 = artboard header only, 1 = top-level children only). Response includes an approx-token count. |
| `list_artboards` | Lists all artboards with IDs, names, dimensions |
| `find_nodes` | Search nodes by name, text content, type, or className. Returns IDs without subtree — use this to locate before calling `get_node_tree`. |
| `get_node_tree` | Serializes one node/artboard subtree only — drill in after `outline` or `find_nodes`. |
### Creating Content
| Tool | Purpose |
|------|---------|
| `create_artboard` | Creates a new artboard (screen/frame) |
| `add_section` | Adds complex layouts from JSX markup (preferred) |
| `add_node` | Adds a single node to a parent |
### Modifying Content
| Tool | Purpose |
|------|---------|
| `update_node` | Updates any node property (className, textContent, tag, style, src, link, elementId, etc.) |
| `update_class` | Shortcut: replaces only className on a node |
| `update_artboard` | Updates artboard properties (name, size, background, className, `timelineDuration`) |
| `batch_update` | Updates multiple nodes in one call (bulk styling) |
| `replace_section` | Replaces a node and its children with new JSX |
### Animation
| Tool | Purpose |
|------|---------|
| `list_animation_presets` | Lists native Efecto animation presets with ids, categories, defaults, and supported controls |
| `apply_animation_plan` | Applies a validated multi-layer animation plan in one call |
| `clear_animations` | Clears native animations from nodes, the selection, an artboard, or the whole document |
### Organizing Structure
| Tool | Purpose |
|------|---------|
| `move_node` | Reparents or reorders a node |
| `duplicate_node` | Deep-clones a node with fresh IDs |
| `duplicate_artboard` | Deep-clones an artboard for variations |
| `group_nodes` | Wraps selected nodes in a frame container |
| `ungroup_node` | Unwraps a group, moving children to parent |
| `reorder_node` | Brings to front or sends to back (z-order) |
### Display & Selection
| Tool | Purpose |
|------|---------|
| `select_nodes` | Highlights nodes for the user to see |
| `set_visibility` | Shows/hides nodes (like Figma eye icon) |
| `delete_nodes` | Deletes nodes and their children |
| `delete_artboard` | Deletes an artboard and all contents |
### Alignment & Distribution
| Tool | Purpose |
|------|---------|
| `align_nodes` | Aligns multiple nodes (left/center/right/top/middle/bottom) |
| `distribute_nodes` | Distributes nodes evenly (horizontal/vertical) |
### History
| Tool | Purpose |
|------|---------|
| `undo` | Undoes the last action (Cmd+Z) |
| `redo` | Redoes the last undone action (Cmd+Shift+Z) |
### Viewport & Document
| Tool | Purpose |
|------|---------|
| `zoom_to_artboard` | Zooms viewport to show a specific artboard |
| `zoom_to_fit` | Zooms to fit all artboards in the viewport |
| `set_viewport` | Sets viewport zoom level and/or pan position |
| `rename_document` | Renames the document |
| `new_document` | Creates a new blank document (replaces current) |
### Canvas & Reading
| Tool | Purpose |
|------|---------|
| `move_artboard` | Repositions an artboard on the canvas for multi-screen flows |
| `deselect_all` | Clears the current node selection |
| `get_node_tree` | Returns JSX for one node/artboard subtree (faster than full documRelated in Ads & Marketing
ads
IncludedMulti-platform paid advertising audit and optimization skill. Analyzes Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple Ads. 250+ checks with scoring, parallel agents, industry templates, and AI creative generation.
banana
IncludedAI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.
rpg-migration-analyzer
IncludedAnalyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies data structures (D-specs), file operations (F-specs), program dependencies (CALLB/CALLP), and converts RPG constructs to Java equivalents. Generates migration reports, complexity estimates, and Java implementation strategies with POJO classes, JPA entities, and service methods. Use when modernizing AS/400 or IBM i legacy systems, analyzing RPG source files (.rpg, .rpgle, .RPGLE), converting RPG to Java, mapping data specifications to Java classes, planning legacy system migration, or when user mentions RPG analysis, Report Program Generator, RPG III/IV/ILE, AS/400 modernization, IBM i migration, packed decimal conversion, or mainframe application rewrite.
brand-library-architect
IncludedBuild a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT), and a self-contained press kit. This skill should be used when the user asks to "build a brand library / brand kit / press kit / brand assets" for a product, "set up a brand library workflow," "create a positioning manifesto plus visual identity," or any combination of brand documentation + visual asset pipeline. Apply phase-by-phase or run end-to-end. Templates are product-agnostic and use {{TOKEN}} placeholders the skill prompts the user to fill.
writing-tech-post
IncludedAuthors engineering blog posts end-to-end: launch deep-dives, incident postmortems, architecture migrations, performance case studies, tutorials, AI/agent system writeups, security disclosures, and research-to-product translations. Picks the correct archetype, plans the abstraction ladder, enforces an evidence cadence (diagrams, benchmarks, profiles, traces, code, ablations), tunes voice against publisher house styles (Datadog, Vercel, GitHub, AWS, Meta, Cloudflare, Jane Street), and runs a pre-publish gate for narrative momentum and disclosure ethics. Use when drafting a new engineering post, restructuring a draft that feels flat, deciding which evidence form belongs where, validating that depth and product context are balanced, or preparing a postmortem, migration, or performance narrative for external publication. Do not use for API reference documentation, README authoring, marketing copy, release notes, generic SEO content, ghost-written executive thought leadership, or non-engineering long-form essays.
blog-google
IncludedGoogle API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".