ClaudeCodeMod

All shelves / Skills

stitch::code-to-design

google-labs-code/stitch-skills · 9.4k installs · 8.5K stars

Skill

Install

In your shell
npx -y skills add google-labs-code/stitch-skills --skill stitch::code-to-design --agent claude-code

Run in a terminal. Claude loads the skill when a task calls for it. Check the repo's README before you run it.

Open the repo

Files

SKILL.md

Code to Design

Transform your existing frontend code (React + Vite, Next.js, Angular, Vue, etc.) into a Stitch Design so you can iterate and improve it using Stitch.

This skill orchestrates three other skills in sequence:

  1. extract-static-html: Extract a single self-contained HTML file from your build output or running dev server (e.g., Vite dev server or Angular CLI ng serve).
  2. extract-design-md: Analyze the source code (including Angular angular.json, external .html templates, theme files, and components) to create a design system (DESIGN.md).
  3. upload-to-stitch: Upload that HTML file and the design system to your Stitch project.

Workflow

Follow these steps to convert your existing code.

Prerequisites

  • A running local dev server (e.g. npm run dev, ng serve) OR a built web application directory containing index.html and assets.
  • Target Stitch projectId (use list_projects if unknown).

Steps

1. Extract Self-Contained HTML

Delegate to the extract-static-html skill to generate a standalone HTML file. Read skills/extract-static-html/SKILL.md for detailed instructions and script usage.

Expected output: A single file like /path/to/extracted/standalone.html.

2. Verify HTML (Optional — User-Driven)

After extraction, inform the user of the output file path so they can manually verify in a browser if desired. Do not block on verification — proceed directly to Step 3.

If the user reports issues after reviewing, fix them before continuing.

3. Extract Design System (File)

Delegate to the extract-design-md skill to analyze the project's source files (components, stylesheets, theme configs) and produce a design system. Read skills/extract-design-md/SKILL.md for the full analysis workflow.

Write .stitch/DESIGN.md following the extract-design-md skill's output structure.

4. Upload DESIGN.md and Create Design System in Stitch

Delegate to the manage-design-system skill to upload the DESIGN.md and create the design system in Stitch. Read skills/manage-design-system/SKILL.md for the full workflow (upload script usage, create_design_system_from_design_md call, and required schemas). Pass --generated-by 'stitch::code-to-design' when uploading.

5. Upload HTML to Stitch

Use the same upload-to-stitch skill's script to upload the extracted HTML file. Read skills/upload-to-stitch/SKILL.md for detailed instructions and script usage.

You will need:

  • The path to the standalone HTML file generated in Step 1.
  • Your Stitch API Key (same key used in Step 4).
  • The target projectId.
  • The --generated-by argument set to 'stitch::extract-static-html'.
  • The --title argument set to the route path of the page (e.g., '/dashboard', '/settings/profile', '/inbox') so that the screen name/title in Stitch clearly identifies its route in the application.

Facts

Kind
Skill
Repo
google-labs-code/stitch-skills
Group
Uncategorized
Installs
9.4k
Stars
8.5K

More on this shelf

  1. 1find-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.3.8M
  2. 2grill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.3M
  3. 3grill-with-docsmattpocock/skillsA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.1.1M
  4. 4agent-browservercel-labs/agent-browserBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.1.1M
  5. 5improve-codebase-architecturemattpocock/skillsScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.1.1M
  6. 6tddmattpocock/skillsTest-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.1.1M