efecto-graphic-design
Design graphic assets with Efecto — presentations, pitch decks, event posters, email headers, blog images, open graph cards, business cards, resumes, menus, infographics, invitations, newsletters, and documents. Use when asked to "design a poster", "create a pitch deck", "make a presentation", "design a business card", or any graphic design task. Requires Efecto MCP server.
What this skill does
# Efecto — Graphic Design Guide
Design graphic assets — presentations, pitch decks, event posters, email headers, blog images, OG cards, business cards, resumes, menus, infographics, invitations, newsletters, and documents — using the Efecto design tool.
---
## 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 It Works
1. Your agent creates an Efecto session via MCP (`create_session`)
2. You open the returned design URL in your browser
3. The agent pushes design commands — you see every change live
4. Iterate with natural language until the design is perfect
---
## Using Efecto Tools — Quick Reference
### Session Workflow
Every design starts with a session:
```
create_session label: "Pitch Deck"
```
Returns `{ sessionId, documentId, designUrl }`. Tell the user to open the URL, then call `wait_for_connection` (blocks until paired). If the user already has an Efecto URL with `?session=...`, call `attach_session` with that URL instead of creating a duplicate session. Never call `create_session` twice to "reconnect" — a paired session refuses overwrite without `force: true`. Use `session_status` to inspect routing (`{ all: true }` for the full session list).
### Building Designs
The primary workflow is: **create artboard → add sections with JSX → refine with updates**.
```
# 1. Create an artboard
create_artboard name: "Slide 1" width: 1920 height: 1080 backgroundColor: "#1a1a1a" className: "flex flex-col"
# 2. Add content with JSX (most efficient way to build)
add_section parentId: "<artboard-id>" jsx: '<section className="flex flex-col items-center justify-center gap-6 p-24 w-full h-full">
<h1 className="text-7xl font-extrabold text-white text-center">Your Title Here</h1>
<p className="text-2xl text-gray-400">Subtitle text</p>
</section>'
# 3. Read current state to get node IDs
get_document
# 4. Fine-tune with batch updates
batch_update updates: [
{ nodeId: "abc", className: "text-8xl font-black text-white" },
{ nodeId: "def", textContent: "New text" }
]
```
### All 68 Tools
| Category | Tools |
|----------|-------|
| **Session** | `create_session`, `attach_session`, `wait_for_connection`, `session_status`, `close_session` |
| **Reading** | `get_document`, `get_selection`, `get_node_tree`, `list_artboards`, `find_nodes` |
| **Creating** | `create_artboard`, `add_section`, `add_node` |
| **Modifying** | `update_node`, `update_class`, `update_artboard` (accepts `speakerNotes` for slides and `timelineDuration` for animation), `batch_update`, `replace_section` |
| **Animation** | `list_animation_presets`, `apply_animation_plan`, `clear_animations` |
| **Organizing** | `move_node`, `duplicate_node`, `duplicate_artboard`, `group_nodes`, `ungroup_node`, `reorder_node` |
| **Selection** | `select_nodes`, `deselect_all`, `set_visibility`, `delete_nodes`, `delete_artboard` |
| **Alignment** | `align_nodes`, `distribute_nodes` |
| **Fill & Export** | `set_fill`, `export_image` |
| **Viewport** | `zoom_to_artboard`, `zoom_to_fit`, `set_viewport`, `move_artboard` |
| **Document** | `rename_document`, `new_document` |
| **History** | `undo`, `redo` |
| **Theme** | `get_theme`, `set_theme`, `set_theme_mode`, `reset_theme` |
| **Quality** | `audit_design`, `repair_design` |
**Scoped reads (large docs).** `get_document` returns the whole tree by default — on multi-artboard docs that can blow past tool-result token caps. Prefer scoped modes: `outline: true` (one-line summary per top-level child), `artboardId: "..."` (single artboard), `maxDepth: N` (cap descent; 0 = artboard header only, 1 = top-level children). Response includes an approx-token count so you can decide whether to widen. Drill into a subtree with `get_node_tree` after.
**Routing inspection.** `session_status` returns the legacy single-session shape by default (sessionId, paired, browserConnected, knownSessions). Pass `{ all: true }` for the list shape — every session in this MCP process with isActive/paired flags. If this MCP process restarted, `attach_session` with the current browser URL makes that session active again.
### JSX Format for `add_section`
Write standard HTML tags with Tailwind `className`. The tag determines the node type:
```
<div>/<section>/<nav> → frame <img> → image
<h1>-<h6>/<p>/<span> → text <button> → button
<a> → link <svg> → icon
<input> → input <video> → video
```
Icons: `<svg icon="arrow-right" className="w-5 h-5 text-gray-600" />`
### Critical Gotchas
- **Artboard `className` must include `flex flex-col`** — without it, children overlap at (0,0)
- **Artboard `backgroundColor` is a property, NOT a className** — use `backgroundColor: "#1a1a1a"`, not `className: "bg-gray-900"`
- **Never use arbitrary hex in className** — `bg-[#f9f9f9]` silently fails. Use named colors (`bg-gray-50`) or inline `style`
- **Use `grow` instead of `flex-1`** — `flex-1` doesn't work in Efecto
- **Buttons ignore children** — use a flex container with `<span>` + `<svg>` instead
- **Always add `w-full`** on direct children of artboards
---
## Images — Use Real Photos, Not Placeholders
Use `search_images` to find free, high-quality stock photos from Lummi. **No session required** — call it anytime.
```
search_images
query: "conference stage audience"
orientation: "horizontal"
luminance: "dark"
limit: 4
```
Then apply images to your designs:
- **Image node**: `add_node` with `type: "image"`, `src: "<url>"`, `alt: "..."`, `className: "w-full h-[400px] object-cover rounded-2xl"`
- **Background fill**: `set_fill` with `fill: { type: "image", url: "<url>", size: "cover" }`
- **In JSX**: `<img src="<url>" alt="..." className="w-full h-[400px] object-cover rounded-2xl" />`
**Tips for graphic design**: Match `orientation` to your artboard (vertical for posters/stories, horizontal for banners/presentations, square for social cards). Use `luminance: "dark"` for dark-themed designs. Search before designing — build layouts around real images, not empty gray boxes.
---
## Shader Nodes & Visual Effects
Add visual effects to graphic designs with shader nodes. Use `add_node` with `type: "shader"`.
### Generative Backgrounds
Create eye-catching backgrounds without images:
```
add_node
parentId: "<artboard-id>"
type: "shader"
shaderType: "meshGradient"
className: "w-full h-full"
```
**Shader types**: `meshGradient` (organic blending), `dotGrid` (tech/data), `voronoi` (organic cells), `liquidMetal` (premium), `chrome` (reflective), `pulsar` (energy), `blackHole` (dramatic), `glass` (frosted), `spiral` (playful), `particles` (atmospheric), `fireworks` (celebration).
### Apply Effects to Images
Process photos with ASCII, dither, halftone, glitch, or art effects:
```
search_images query: "portrait" orientation: "vertical" limit: 1
add_node
parentId: "<artboard-id>"
type: "shader"
inputType: "image"
mediaInput: { mediaUrl: "<url>", mediaType: "image", objectFit: "cover" }
effectId: "halftone-mono"
effectEnabled: true
className: "w-full h-full"
```
**Effect categories**: ASCII (`ascii-standard`, `ascii-dense`, `ascii-minimal`, `ascii-blocks`), Dither (`dither-floyd-steiRelated 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.