Stitch logo

Stitch

CommunityPopular
Dicklesworthstone
stitch

Generate UI designs and frontend code with Google Stitch via MCP. Use when asked to create screens, mockups, UI designs, or generate frontend code from text descriptions. Supports desktop, mobile, and tablet layouts.

Overview

PublisherDicklesworthstone
Repositorypi_agent_rust
Skill namestitch
Stars
1.7K
Forks
206
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Dicklesworthstone on GitHub. Read the source before you install it.

Installation

Install the Stitch AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Dicklesworthstone/pi_agent_rust.git /tmp/pi_agent_rust
mkdir -p .claude/skills
cp -r /tmp/pi_agent_rust/tests/ext_conformance/artifacts/agents-mikeastock/skills/stitch .claude/skills/stitch
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Stitch in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Stitch on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Stitch is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Google Stitch — AI UI/UX Design Generation

Generate production-ready UI designs and frontend code using Google Stitch via MCP.

Prerequisites

Verify stitch is configured:

bash
mcporter list stitch

If missing, configure it:

bash
# 1. Authenticate with Google Cloud
gcloud auth application-default login

# 2. Enable Stitch API
gcloud beta services mcp enable stitch.googleapis.com --project=YOUR_PROJECT_ID

# 3. Add to mcporter
mcporter config add stitch --stdio "npx -y stitch-mcp" --env GOOGLE_CLOUD_PROJECT=YOUR_PROJECT_ID

Tools

ToolPurpose
list_projectsList all projects
create_projectCreate a project
get_projectGet project details
list_screensList screens in a project
get_screenGet screen details
generate_screen_from_textGenerate a screen from a prompt
fetch_screen_codeDownload HTML/CSS code
fetch_screen_imageDownload preview image

Workflows

List Projects

bash
mcporter call stitch.list_projects
mcporter call stitch.list_projects filter="view=owned"
mcporter call stitch.list_projects filter="view=shared"

Create a Project

bash
mcporter call stitch.create_project title="My App Design"

Generate a Screen

bash
mcporter call stitch.generate_screen_from_text \
  projectId="PROJECT_ID" \
  prompt="A modern dashboard with sidebar navigation, user stats cards, and a data table" \
  deviceType="DESKTOP" \
  modelId="GEMINI_3_PRO"

Parameters:

  • projectId (required): Numeric project ID (e.g., 4651986810686364080)
  • prompt (required): UI description
  • deviceType: MOBILE (default), DESKTOP, TABLET, or AGNOSTIC
  • modelId: GEMINI_3_FLASH (default, 30–60s) or GEMINI_3_PRO (1–3min, higher quality)

Generation takes 1–3 minutes. Do not retry.

List Screens

bash
mcporter call stitch.list_screens projectId="PROJECT_ID"

Get Screen Details

bash
mcporter call stitch.get_screen projectId="PROJECT_ID" screenId="SCREEN_ID"

Download Code

bash
mcporter call stitch.fetch_screen_code projectId="PROJECT_ID" screenId="SCREEN_ID"

Returns self-contained HTML with Tailwind CSS.

Download Image

bash
mcporter call stitch.fetch_screen_image projectId="PROJECT_ID" screenId="SCREEN_ID"

Saves PNG to current directory; returns base64 data.

Prompt Engineering

Specify These Elements

  • Layout: sidebar, header, grid, cards
  • Components: buttons, forms, tables, modals
  • Content: user data, charts, lists
  • Style: minimal, corporate, playful, dark mode

Strong Prompts

A settings page with a left sidebar showing navigation categories 
and a main content area with toggle switches for notifications, 
privacy settings, and account preferences. Dark mode.
An e-commerce product listing page with a search bar, filter sidebar 
on the left, and a 3-column grid of product cards showing image, 
title, price, and add-to-cart button.

Weak Prompts

A nice website
Settings page

Device Types

TypeResolutionBest For
DESKTOP1280×1024Full layouts, sidebars, wide tables
MOBILE390×844Single column, bottom nav, touch targets
TABLET768×1024Hybrid layouts
AGNOSTICVariesResponsive components

Model Selection

  • GEMINI_3_FLASH: 30–60 seconds. Use for iteration.
  • GEMINI_3_PRO: 1–3 minutes. Use for final designs.

Iteration Workflow

  1. Create a project for your design system
  2. Generate initial screens with FLASH for rapid iteration
  3. Refine prompts based on output
  4. Generate final versions with PRO
  5. Extract code with fetch_screen_code

Maintain Consistency

Reference existing designs in subsequent prompts:

Following the same design system as the dashboard (dark mode, 
Inter font, blue accent #137fec, rounded-lg corners), 
create a user profile page with...

Response Handling

generate_screen_from_text

Returns:

  • screenId: Generated screen ID
  • output_components: Feedback or suggestions

If output_components contains suggestions (e.g., "Yes, make them all"), present them to the user. If accepted, call generate_screen_from_text again with the suggestion as the prompt.

Code Structure

Generated HTML includes:

  • Tailwind CSS via CDN
  • Custom Tailwind config (colors, fonts)
  • Responsive classes
  • Inline SVG icons

Errors

ErrorCauseFix
HTTP 401Expired authgcloud auth application-default login
HTTP 403API disabledgcloud beta services mcp enable stitch.googleapis.com
TimeoutSlow generationWait; check status with get_screen
Project ID not foundMissing env varSet GOOGLE_CLOUD_PROJECT

Examples

Complete Design Flow

bash
# Create project
mcporter call stitch.create_project title="SaaS Dashboard"

# Generate dashboard
mcporter call stitch.generate_screen_from_text \
  projectId="NEW_PROJECT_ID" \
  prompt="A SaaS analytics dashboard: header with logo and user avatar, left sidebar with nav (Dashboard, Analytics, Users, Settings), main area with 4 stat cards (Revenue, Users, Orders, Growth) and a line chart" \
  deviceType="DESKTOP" \
  modelId="GEMINI_3_PRO"

# List screens
mcporter call stitch.list_screens projectId="NEW_PROJECT_ID"

# Download code
mcporter call stitch.fetch_screen_code projectId="NEW_PROJECT_ID" screenId="SCREEN_ID"

Quick Mobile Mockup

bash
mcporter call stitch.generate_screen_from_text \
  projectId="PROJECT_ID" \
  prompt="Mobile login screen: app logo at top, email and password fields, 'Forgot password?' link, primary 'Sign In' button, 'Don't have an account? Sign up' at bottom" \
  deviceType="MOBILE" \
  modelId="GEMINI_3_FLASH"

Frequently asked questions

What does the Stitch AI skill do?

Generate UI designs and frontend code with Google Stitch via MCP. Use when asked to create screens, mockups, UI designs, or generate frontend code from text descriptions. Supports desktop, mobile, and tablet layouts.

Why use Stitch on TypingMind?

Because you install it once and use it with any model. Stitch is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Stitch in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Dicklesworthstone/pi_agent_rust/tree/main/tests/ext_conformance/artifacts/agents-mikeastock/skills/stitch. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Stitch?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Stitch?

As many as you like. As long as a model supports skills, you can use Stitch with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Stitch AI skill free?

It is published on GitHub by Dicklesworthstone. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇