stitch-mcp-upload-design-md

stitch-mcp-upload-design-md is a skill for Claude Code from gabelul/stitch-kit. It costs 50 tokens per session (977 once invoked), scanned A, original, Apache-2.0.

A tool that uploads a DESIGN.md file—a written description of a design’s visual rules—into a Stitch project. It is only the first step; it must be followed immediately by the matching design-system creation skill.

In plain words
What is it for?
Use it when you have a DESIGN.md file and want Stitch to use it as a design system, including after creating the file with stitch-design-md.
Why use it?
It prevents the design document from being left as an unused screen in Stitch. The required two-step process turns the document into a usable Stitch Design System.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the stitch-kit plugin — 36 skills, 1 agent, 2 hooks shipped together

Good fit Use it when you have a DESIGN.md file and want Stitch to use it as a design system, including after creating the file with stitch-design-md.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gabelul/stitch-kit/stitch-mcp-upload-design-md
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add gabelul/stitch-kit --skill stitch-mcp-upload-design-md
Clone the repo
git clone --depth 1 https://github.com/gabelul/stitch-kit

Made for: Claude Code.

Or install stitch-kit, the plugin that ships this one along with the rest of its 36 skills, 1 agent, 2 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for stitch-mcp-upload-design-md

README.md
[![agentmods](https://agentmods.dev/badge/skills/gabelul/stitch-kit/stitch-mcp-upload-design-md/github.svg)](https://agentmods.dev/skills/gabelul/stitch-kit/stitch-mcp-upload-design-md)
Your own site
<a href="https://agentmods.dev/skills/gabelul/stitch-kit/stitch-mcp-upload-design-md"><img src="https://agentmods.dev/badge/skills/gabelul/stitch-kit/stitch-mcp-upload-design-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for stitch-mcp-upload-design-md

Your own site · 80×15
<a href="https://agentmods.dev/skills/gabelul/stitch-kit/stitch-mcp-upload-design-md"><img src="https://agentmods.dev/badge/skills/gabelul/stitch-kit/stitch-mcp-upload-design-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 977 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.00977
Opus 5 $0.00025 $0.00489
Sonnet 5 $0.00010 $0.00195
Haiku 4.5 $0.00005 $0.00098

Measured 10d ago against content hash 2711aed76a72, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

stitch-mcp-upload-design-md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/stitch-mcp-upload-design-md/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stitch MCP — Upload DESIGN.md

Uploads a DESIGN.md file into a Stitch project. This is step one of a two-step pair: the upload creates a screen instance holding the design doc, and create_design_system_from_design_md then turns that instance into a real Design System.

On its own, this tool does nothing useful. Uploading without the follow-up leaves an orphan screen instance and no design system. Always run both.

Critical prerequisite

Only use this skill when the user explicitly mentions "Stitch" in their request. Never trigger Stitch operations silently during regular conversation.

When to use

  • The user has a DESIGN.md and wants it applied as a Stitch Design System
  • You've just produced a DESIGN.md with stitch-design-md and want it driving generation
  • The user says "use my design doc in Stitch", "make a design system from DESIGN.md"

Step 1: Read and encode the file

The tool takes base64, not raw markdown. The decoded content must be valid UTF-8 — uploads with invalid bytes are rejected outright.

# macOS (BSD base64 — no -w flag, and it does not wrap by default)
base64 -i DESIGN.md
# Linux (GNU base64 — -w 0 disables line wrapping)
base64 -w 0 DESIGN.md

Google's tool description says base64 -w 0, which fails on macOS with invalid option -- w. Use -i there. Getting this wrong produces a confusing shell error rather than an API error, so check your platform first.

Wrapped base64 (with embedded newlines) is a common cause of rejected uploads. Both commands above emit a single unbroken line.

Step 2: Call the MCP tool

{
  "name": "upload_design_md",
  "arguments": {
    "projectId": "3780309359108792857",
    "designMdBase64": "IyBEZXNpZ24gU3lzdGVtCgpDb2xvcnM6IC4uLg=="
  }
}

projectId is numeric only — no projects/ prefix. Passing the prefixed path here fails.

Step 3: Capture the screen instance — CRITICAL

The upload creates a screen instance, and the next tool needs two identifiers from it. Fetch them with get_project (which does take the projects/ prefix):

Read the full file on GitHub · 95 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 95 lines · 50 tokens per session scan A 2711aed76a72

Subscribe to this mod's changes

stitch-mcp-upload-design-md is a skill published in the GitHub repository gabelul/stitch-kit (45 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 977 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

design-to-code

Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts a screenshot, a description, or a URL and produces production-ready React components, checking existing Storybook components before generating anything new. Use when implementing UI from a mockup or screenshot. To call the MCP tool…

yonatangross/orchestkit · 86 tokens

kit-montar

Monta um site novo combinando peças já validadas do acervo pessoal do usuário — templates, design systems, componentes, animações, menus, prompts e receitas — em vez de gerar tudo do zero. Acervo vazio: constrói do zero e oferece guardar. Recebe o briefing, decide cor e tipografia antes da identidade, pergunta que…

harebeats/cannonball · 245 tokens

kit-buscar

Consulta o acervo pessoal de sites do usuário — o que ele já guardou: templates rodáveis, design systems com paleta e tipografia, componentes de UI e de IA, animações de scroll, texto e menu, efeitos WebGL, prompts de página inteira e receitas de composição que já deram certo. Responde "o que eu já tenho pronto pra…

harebeats/cannonball · 228 tokens

kit-cor

Define a paleta do site como decisão, não como consequência de ter escolhido um design system. Faz as perguntas que determinam cor (o que a marca promete, o que o setor já usa, para onde o olho tem que ir, o que ela NÃO pode parecer), monta a paleta por papel — fundo, tinta, superfície, acento — mede o contraste de…

harebeats/cannonball · 193 tokens

kit-tipo

Define a tipografia do site como decisão — e, principalmente, resolve se dá para ENTREGAR. Confere licença (site de marca paga por tipo, e acervo montado a partir de site de marca vem cheio de fonte comercial que não se pode servir), propõe substituto livre com critério de desenho, monta o par display + corpo, gera a…

harebeats/cannonball · 199 tokens

stitch-react-native

Convert Stitch HTML designs into React Native screens, or sync existing native components to updated Stitch designs, using native primitives, StyleSheet rules, and mobile platform checks.

PracticalSwan/agent-skills · 37 tokens