stitch-kit

Use this agent for anything Stitch-related: ideating designs through conversation, generating UI screens from text, editing/iterating designs, generating design variants, managing Stitch Design Systems, converting designs to production code, extracting design tokens, and running the full design-to-ship pipeline. Examples: (1) Generate a UI from a description or PRD using Stitch MCP; (2) Ideate a design — brainstorm, research trends, explore directions, produce a PRD; (3) Edit an existing screen with text prompts (change colors, layout, content); (4) Generate design variants with configurable creativity; (5) Upload screenshots and redesign them in Stitch; (6) Create and apply Stitch Design Systems for visual consistency; (7) Convert a Stitch screen to Next.js, Svelte, React, React Native, or SwiftUI components; (8) Extract design tokens and CSS variables from a generated screen; (9) Build a multi-page site iteratively with visual consistency across screens; (10) Audit components for WCAG 2.1 AA accessibility; (11) Parse a Stitch URL (stitch.withgoogle.com/projects/ID?node-id=SCREEN_ID) and go straight to conversion.

Audits Stitch-generated components for WCAG 2.1 AA accessibility issues and applies fixes — semantic HTML, ARIA attributes, keyboard navigation, focus management, and screen reader support.

Adds a purposeful animation layer to Stitch-generated components — CSS transitions, Framer Motion (React/Next.js), or Svelte transitions. Always respects prefers-reduced-motion.

Analyzes a Stitch project's screens and synthesizes a natural-language DESIGN.md — visual atmosphere, color palette with hex values, typography rules, and Stitch-ready prompt snippets. Use this before stitch-loop or any multi-page build to establish design consistency.

Extracts a Stitch design and generates production code artifacts — CSS custom properties with dark mode tokens, a Tailwind v4 @theme block, and a semantic design system document. Run this before framework conversion skills.

Converts Stitch designs into clean, platform-agnostic HTML5 + CSS — semantic markup, CSS custom properties for theming, dark mode via prefers-color-scheme, mobile-first responsive, zero framework dependencies. Works in browsers, WebViews, Capacitor, and Ionic.

Conversational design ideation agent that researches trends, explores visual directions, and refines ideas through adaptive questioning — then produces a rich PRD document and auto-generates Stitch screens. Your design buddy that thinks deeply before designing.

Iteratively build multi-page websites using Stitch. Reads next-prompt.md (the baton), generates the next page with Stitch MCP, integrates it into the site, then updates next-prompt.md to continue the loop. Works with stitch-design-md and stitch-ui-prompt-architect for consistent multi-page output.

Applies a Stitch Design System to existing screens — updates their colors, fonts, and roundness to match the design system's theme. Requires an assetId from list or create operations.

Creates a reusable Stitch Design System from theme tokens — colors, fonts, roundness, saturation. Can be applied to future screens for visual consistency.

Creates a new Stitch project container (a design workspace). Call this when starting a new design session to get a projectId for screen generation.

Permanently deletes a Stitch project and all its screens. Destructive — requires explicit user confirmation before calling.

Edits existing Stitch screens with text prompts — the iteration tool. Change colors, layout, content, or style without regenerating from scratch. Supports refinement loops via output_components suggestions.

Generates a high-fidelity UI screen or wireframe from a text prompt using Stitch. This is the core text-to-UI generation tool — the heart of the Stitch workflow.

Generates design variants of existing Stitch screens using the native variant API. Explore alternative layouts, color schemes, fonts, or content with configurable creativity levels.

Retrieves metadata for a specific Stitch project — title, theme, create/update time. Use to inspect a project before generating new screens. Do NOT use this if you already have a screenId — use stitch-mcp-get-screen instead.

Retrieves full details of a specific Stitch screen — HTML download URL, screenshot URL, dimensions. This is the final step in design retrieval before code conversion.

Lists all Stitch Design Systems, optionally filtered by project. Returns asset names needed for apply and update operations.

Lists all Stitch projects accessible to the user. Use this to find an existing project ID before resuming work or generating new screens in an existing project.

Lists all screens in a Stitch project. Use this after generate_screen_from_text to find the screenId of the newly generated screen, then call stitch-mcp-get-screen to retrieve it.

Updates an existing Stitch Design System's theme, tokens, or guidelines. Requires the asset name from create or list operations.

Uploads screenshots or mockup images into a Stitch project as new screens. Enables the "redesign from screenshot" workflow — import existing UI and then edit or convert.

Converts Stitch designs into production-ready Next.js 15 App Router components — Server vs Client split, dark mode via CSS variables, TypeScript strict, ARIA, and responsive mobile-first layout.

Master entry point for all Stitch design workflows. Routes from user request → design spec → prompt assembly → screen generation → iteration (edit, variants, design systems) → design system extraction → framework conversion (Next.js, Svelte, HTML, React Native, or SwiftUI) → optional quality pass.

Converts Stitch designs into modular Vite + React components — TypeScript, theme-mapped Tailwind, dark mode via CSS variables, and clean component architecture. Use this for Vite/React apps without App Router. For Next.js 15 App Router, use stitch-nextjs-components instead.

Converts Stitch mobile designs into React Native / Expo components — TypeScript, StyleSheet, Expo Router, dark mode via useColorScheme, and proper touch targets. Cross-platform iOS and Android.

Generates walkthrough videos from Stitch projects using Remotion. Downloads screenshots from Stitch screens, builds a Remotion composition with transitions and text overlays, and renders to MP4. Use with stitch-mcp-list-screens and stitch-mcp-get-screen for screen discovery.

Step-by-step installer for the stitch-kit plugin and Stitch MCP server. Use this when setting up the plugin for the first time, diagnosing connection issues, or helping a new user get Stitch running in Claude Code or Codex CLI.

Integrates shadcn/ui into React apps generated from Stitch designs. Component discovery and installation, token alignment with Stitch design system, customization patterns, and blocks (auth, dashboard, sidebar). Use with stitch-react-components or stitch-nextjs-components.

Meta-skill for creating new stitch-kit skills. Enforces naming conventions, SKILL.md structure, examples format, and the Design-First SOP. Use when adding new framework support, a new domain-specific prompt architect, or any new capability to the stitch-kit plugin.

Converts Stitch designs into Svelte 5 / SvelteKit components using the runes API — scoped CSS with custom properties, built-in transitions, TypeScript, dark mode, and accessible markup.

Converts Stitch mobile designs into SwiftUI views for native iOS apps — VStack/HStack/ZStack layout mapping, Color asset tokens with dark mode, NavigationStack/TabView routing, and Xcode project structure.

Visual vocabulary, design terminology, and prompt engineering strategy for Stitch. Reference this when you need layout pattern names, aesthetic style terms, color structure formulas, or device guidelines.

Translates a user request or PRD document into a structured Design Spec JSON — theme, color, typography, density, and device type. Call this before building Stitch generation prompts.

Generates 3 alternative Stitch prompts for A/B testing screen concepts — vary layout, visual style, or content while keeping the underlying information architecture consistent.

Builds Stitch-ready prompts via two paths — Path A enhances vague ideas into polished prompts, Path B merges a Design Spec JSON + user request into a structured [Context] [Layout] [Components] prompt.