Google Stitch Skills

Community

podo

google-stitch-skills

Official Google Stitch skills for the design-to-code pipeline: generate and edit Stitch screens, DESIGN.md and SITE.md management, prompt enhancement, React / React Native / shadcn/ui component generation, code-to-design upload, and iterative Stitch build loops.

Overview

Publisher	podo
Repository	`design-agent-skills`
Skill name	`google-stitch-skills`
Stars	27
Forks	3
Bundled files	1
License	MIT
Links	Skill source Repository Homepage

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.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by podo on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/podo/design-agent-skills/tree/main/skills/google-stitch-skills
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.

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/podo/design-agent-skills.git /tmp/design-agent-skills
mkdir -p .claude/skills
cp -r /tmp/design-agent-skills/skills/google-stitch-skills .claude/skills/google-stitch-skills

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Google Stitch Skills 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 Google Stitch Skills 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 Google Stitch Skills 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-skills

Catalogue stub — full package: google-labs-code/stitch-skills

Decision tree

Is the full skill already installed? This package installs 16 skills (stitch-loop, design-md, enhance-prompt, site-md, taste-design, stitch-extract-design-md, stitch-extract-static-html, stitch-generate-design, stitch-code-to-design, stitch-manage-design-system, stitch-upload-to-stitch, stitch-react-components, stitch-react-native, react-vite-dashboard, shadcn-ui, remotion); checking the first.
- Global: f=~/.agents/skills/stitch-loop/SKILL.md; [ -f "$f" ] && ! grep -q "^das:" "$f" && echo "installed" || echo "pointer"
- Project: f=.agents/skills/stitch-loop/SKILL.md; [ -f "$f" ] && ! grep -q "^das:" "$f" && echo "installed" || echo "pointer"
- installed → the skill is installed as stitch-loop, invoke it and proceed
- pointer → go to step 2

Detect scope, then install:

bash
[ -e ~/.agents/skills/google-stitch-skills ] && echo "global" || echo "project"

Global:

bash
npx skills add google-labs-code/stitch-skills -g -y

Project:

bash
npx skills add google-labs-code/stitch-skills -y

Claude Code: send a command as a chat message starting with ! to run it without leaving the conversation.

Heads-up

Requires: Stitch MCP server configured with its credentials (Stitch MCP setup guide: https://stitch.withgoogle.com/docs/mcp/setup/); upstream says the skills need it running
License: Apache-2.0
Name collision: shadcn-ui is also written by shadcn-ui (its install or its catalogue pointer); installing both overwrites the earlier one.
Name collision: remotion is also written by remotion (its install or its catalogue pointer); installing both overwrites the earlier one.

Invoke after install

Skills prefixed stitch:: install into a stitch-… directory (for example stitch::react-components becomes stitch-react-components). Upstream says the skills depend on each other, so install the package rather than single skills.

stitch-loop — "stitch loop", "iterate design"
design-md — "DESIGN.md", "create design spec"
site-md — a SITE.md project constitution for the Stitch build loop
enhance-prompt — "enhance my prompt", "improve UI prompt"
taste-design — a DESIGN.md that enforces premium, anti-generic UI standards
stitch::generate-design — generate and edit screens and variants through the Stitch MCP
stitch::manage-design-system — manage Stitch design systems and apply them to screens
stitch::extract-design-md (installed as stitch-extract-design-md) — "extract design md", "Stitch to DESIGN.md"
stitch::react-components (installed as stitch-react-components) — "Stitch to React", "convert to React"
stitch::react-native (installed as stitch-react-native) — Stitch HTML to React Native components
react-vite-dashboard — Stitch designs to React + Vite dashboards
shadcn-ui — "Stitch to shadcn", "build with shadcn"
remotion — walkthrough videos from Stitch projects
stitch::code-to-design, stitch::extract-static-html, stitch::upload-to-stitch — move existing web code into a Stitch project

What it does

Google Labs' official Stitch skill collection for the complete design-to-code pipeline: manages DESIGN.md and SITE.md specification files, enhances prompts with UI/UX vocabulary, generates and edits Stitch screens, converts Stitch output to React, React Native or shadcn/ui components, extracts design specs, uploads existing code into Stitch, and runs iterative improvement loops. The skills drive the Stitch MCP server.

Upstream also recommends its plugin suite (npx plugins add google-labs-code/stitch-skills --scope project --target claude-code); the command above installs the same skills without plugin packaging.

When NOT to use

Designs that do not live in Google Stitch — use figma-official-skills for Figma, or design-consultation to build a design system from scratch
Only the shadcn/ui component workflow, not the Stitch pipeline — use the official shadcn-ui stub; this package installs a different (Stitch-specific) skill into the directory shadcn-ui, the same name the catalogue pointer for that stub uses, so installing both overwrites one
Only the Remotion video workflow — use the remotion stub; the Stitch remotion skill is Stitch-specific and installs into a directory with the same name as that stub

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

stub.yaml1 KB

Frequently asked questions

What does the Google Stitch Skills AI skill do?

Why use Google Stitch Skills on TypingMind?

Because you install it once and use it with any model. Google Stitch Skills 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 Google Stitch Skills in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/podo/design-agent-skills/tree/main/skills/google-stitch-skills. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Google Stitch Skills?

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 Google Stitch Skills?

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

Is the Google Stitch Skills AI skill free?

Yes. It is published on GitHub by podo under the MIT license. 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

Competitive Platform Analysis

affaan-m

CommunityPopular

Use when scoping a competitive landscape — identifying, categorising, and score-filtering a competitor set before any benchmarking begins. Decides who counts as a competitor, which tier they belong…

Frontend Slides

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a…

Plan Canvas

Open plans and HTML artifacts in a local browser canvas where the human annotates elements, chats, and approves or requests changes without leaving the page. Use when presenting a plan for review, or…

Improve Codebase Architecture

mattpocock

CommunityPopular

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

google-stitch-skills

Decision tree

Invoke after install

What it does

When NOT to use

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now