Common Stitch Design logo

Common Stitch Design

Community
HoangNguyen0403
common-stitch-design

Drive Google Stitch over MCP safely - read screens, write and lint DESIGN.md, create design systems, and fix designs through variants instead of overwriting. Use when reviewing, editing, or generating Stitch screens or DESIGN.md files.

Overview

PublisherHoangNguyen0403
Repositoryagent-skills-standard
Skill namecommon-stitch-design
Stars
573
Forks
166
Bundled files
5
LicenseMIT
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.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by HoangNguyen0403 on GitHub. Read the source before you install it.

Installation

Install the Common Stitch Design 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.
    https://github.com/HoangNguyen0403/agent-skills-standard/tree/develop/.agents/skills/common/common-stitch-design
  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/HoangNguyen0403/agent-skills-standard.git /tmp/agent-skills-standard
mkdir -p .claude/skills
cp -r /tmp/agent-skills-standard/.agents/skills/common/common-stitch-design .claude/skills/common-stitch-design
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Common Stitch Design 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 Common Stitch Design 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 Common Stitch Design 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.

Stitch Design

Priority: P1 (HIGH)

Preflight

  • Stitch tools (list_projects, list_screens, get_screen) must be in the tool list. Missing → BLOCKED (stitch-mcp).
  • Endpoint https://stitch.googleapis.com/mcp, header X-Goog-Api-Key. Config added mid-session loads only after restart. Setup: Stitch MCP.

Read

  • list_screens, then group by title: many versions share one title. Confirm the current one with the author; default most recent.
  • Screenshot screenshot.downloadUrl + =w390 (phone) or =w1280 (tablet); HTML htmlCode.downloadUrl. Save to .stitch/review/<YYYY-MM-DD>/.
  • Run node scripts/audit_html.js <dir>. Audit output is evidence; screenshots confirm visual judgement.

Write Safely

  • Never overwrite originals. Fix through generate_variants (creativeRange: REFINE, variantCount: 1) or a new design system.
  • Explicit approval before delete_project, update_design_system on an existing asset, or apply_design_system to original screens.
  • New design system: create_design_system with theme.designMd, then update_design_system on that new asset.
  • apply_design_system takes screen instance ids from get_project, not screen ids.
  • Generation takes minutes. On timeout do not retry; poll get_screen every 30 s, max 10.
  • Variant output includes illustration image screens with null deviceType: skip them. Check device class on the screenshot; a TABLET request can return DESKTOP.

DESIGN.md

  • Google design.md format. npx @google/design.md lint DESIGN.md must report 0 errors and 0 warnings before upload.
  • Every component backgroundColor/textColor pair must pass contrast. Rules: DESIGN.md.

Prompting

  • Generation prompts: layout and content only. Edit and variant prompts may carry hex values.
  • One shared fix block plus per-screen specifics; re-audit after each pass; max 2 edit_screens passes on variants only. See Prompting.

Anti-Patterns

  • No in-place fixes: editing originals destroys the baseline.
  • No trusting labels: titles and device labels drift; check screenshots.
  • No unlinted DESIGN.md: one bad colour pair ships to every screen.

Bundled files

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

Frequently asked questions

What does the Common Stitch Design AI skill do?

Drive Google Stitch over MCP safely - read screens, write and lint DESIGN.md, create design systems, and fix designs through variants instead of overwriting. Use when reviewing, editing, or generating Stitch screens or DESIGN.md files.

Why use Common Stitch Design on TypingMind?

Because you install it once and use it with any model. Common Stitch Design 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 Common Stitch Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/HoangNguyen0403/agent-skills-standard/tree/develop/.agents/skills/common/common-stitch-design. 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 Common Stitch Design?

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 Common Stitch Design?

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

Is the Common Stitch Design AI skill free?

Yes. It is published on GitHub by HoangNguyen0403 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

Set up your own AI workspace now

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