stitch-design
Google Stitch design toolkit — DESIGN.md generation, screen-to-React conversion, shadcn/ui integration, prompt enhancement, and Remotion walkthroughs. Use when working with Stitch MCP design projects.
What this skill does
# Stitch Design
Comprehensive toolkit for Google Stitch projects — combining design system documentation, React component conversion, autonomous build loops, prompt engineering, video walkthroughs, and shadcn/ui component integration. Based on [google-labs-code/stitch-skills](https://github.com/google-labs-code/stitch-skills).
- Leverage native parallel subagent dispatch and 200k+ context windows where available.
## When to Use This Skill
Use symptom -> action triggers: when one matches, apply this skill and verify with the protocol below.
- Analyzing Stitch projects and generating DESIGN.md files
- Converting Stitch screens to modular React/TypeScript components
- Building multi-page websites autonomously via the Stitch build loop
- Enhancing vague UI prompts into Stitch-optimized structured prompts
- Creating walkthrough videos from Stitch projects using Remotion
- Integrating and customizing shadcn/ui components in React apps
---
## Part 1: Design System Documentation (design-md)
Analyze Stitch project screens and synthesize a semantic design system into `DESIGN.md`.
### Prerequisites
- Access to Stitch MCP Server
- A Stitch project with at least one designed screen
### Workflow
1. **Retrieval**: Use Stitch MCP to fetch project screens, HTML code, and metadata
2. **Extraction**: Identify design tokens — colors, typography, spacing, component patterns
3. **Translation**: Convert CSS/Tailwind values into descriptive design language
4. **Synthesis**: Generate comprehensive DESIGN.md
### Analysis Steps
1. **Extract Project Identity** — Title, Project ID from JSON
2. **Define the Atmosphere** — Evocative adjectives for mood (e.g., "Airy", "Minimalist")
3. **Map Color Palette** — Descriptive name + hex code + functional role
4. **Translate Geometry & Shape** — Corner roundness, spacing patterns
5. **Describe Depth & Elevation** — Shadows, layering
### DESIGN.md Output Structure
```markdown
**Project ID:** [ID]
## 1. Visual Theme & Atmosphere
## 2. Color Palette & Roles
## 3. Typography Rules
## 4. Component Stylings
## 5. Layout Principles
```
### Guidelines
- Use descriptive design language, not technical jargon
- Include exact hex codes alongside descriptive names
- Explain the "why" behind design decisions
### Pitfalls to Avoid
- Using raw CSS class names without translation
- Omitting color codes or using only descriptive names
- Being too vague in atmosphere descriptions
---
## Part 2: React Component Conversion (react-components)
Convert Stitch screens into modular Vite and React component systems with AST-based validation.
### Retrieval
1. Discover Stitch MCP prefix via `list_tools`
2. Fetch design JSON with `get_screen`
3. Download HTML using system-level curl for reliability
4. Check `screenshot.downloadUrl` for visual verification
### Architectural Rules
- **Modular components**: Independent files, avoid monoliths
- **Logic isolation**: Event handlers in custom hooks (`src/hooks/`)
- **Data decoupling**: Static text/URLs in `src/data/mockData.ts`
- **Type safety**: `Readonly` TypeScript interface for every component
- **Style mapping**: Extract Tailwind config from HTML `<head>`, use theme-mapped classes
### Execution Steps
1. Environment setup: `npm install` if needed
2. Create `src/data/mockData.ts` from design content
3. Draft components using template, replace `StitchComponent` with actual names
4. Wire up in `App.tsx`
5. Quality check: run validation, verify against architecture checklist
## Part 3: Build Loop (stitch-loop)
Autonomous baton-passing pattern for building complete multi-page websites.
### Execution Protocol
1. **Read the Baton** — `next-prompt.md` contains current task
2. **Consult Context Files** — `DESIGN.md` for visual system, `SITE.md` for site constitution
3. **Generate with Stitch** — Create/edit screens using Stitch MCP
4. **Integrate into Site** — Move from `queue/` to `site/public/`
5. **Update Site Documentation** — Keep SITE.md current
6. **Prepare Next Baton** — Write new `next-prompt.md` for the next iteration
### File Structure
```
project/
├── next-prompt.md # The baton — current task
├── stitch.json # Stitch project ID
├── DESIGN.md # Visual design system
├── SITE.md # Site vision, sitemap, roadmap
├── queue/ # Staging area for Stitch output
└── site/public/ # Production pages
```
---
## Part 4: Prompt Enhancement (enhance-prompt)
Transform vague UI ideas into polished, Stitch-optimized prompts.
### Enhancement Pipeline
#### Step 1: Assess the Input
| Element | Check for | If missing... |
|---------|-----------|---------------|
| Platform | "web", "mobile", "desktop" | Add based on context |
| Page type | "landing page", "dashboard" | Infer from description |
| Structure | Numbered sections | Create logical structure |
| Visual style | Adjectives, mood, vibe | Add appropriate descriptors |
| Colors | Specific values or roles | Add design system or suggest |
| Components | UI-specific terms | Translate to proper keywords |
#### Step 2: Check for DESIGN.md
- If exists: Extract color palette, typography, component styles
- If missing: Recommend creating one with the design-md workflow
#### Step 3: Apply Enhancements
- **UI/UX Keywords**: Replace vague terms with specific component names
- **Amplify the Vibe**: Add atmospheric adjectives
- **Structure the Page**: Create numbered section layout
- **Format Colors**: Use design system block
#### Step 4: Format the Output
- Stitch-optimized prompt with design system block and numbered structure
---
## Part 5: Remotion Video Walkthroughs (remotion)
Generate walkthrough videos from Stitch projects using Remotion.
### Prerequisites
- Stitch MCP Server and Remotion MCP Server (or CLI)
- Node.js and npm
### Workflow
1. **Gather Screen Assets** — List screens, download screenshots, create manifest
2. **Generate Remotion Components** — ScreenSlide.tsx, WalkthroughComposition.tsx
3. **Preview and Refine** — Open Remotion Studio, adjust timing
4. **Render Video** — Produce final MP4
### Video Architecture
- **ScreenSlide.tsx**: Individual screen with zoom/fade animations (3-5 sec per screen)
- **WalkthroughComposition.tsx**: Sequences slides with transitions
- **config.ts**: Frame rate (30fps), dimensions, duration calculation
### File Structure
```
project/
├── video/
│ ├── src/
│ │ ├── WalkthroughComposition.tsx
│ │ ├── ScreenSlide.tsx
│ │ └── components/
│ ├── public/assets/screens/
│ └── remotion.config.ts
├── screens.json
└── output.mp4
```
### Advanced Features
- Dynamic text extraction from Stitch HTML
- Interactive hotspots for clickable elements
- Voiceover integration
- Multiple video patterns (slideshow, feature highlight, user flow)
---
## Part 6: shadcn/ui Integration (shadcn-ui)
Expert guidance for integrating shadcn/ui components into React applications.
### Core Principles
- **Full ownership**: Components in your codebase, not node_modules
- **Complete customization**: Modify styling, behavior, structure freely
- **No version lock-in**: Update selectively
- **Zero runtime overhead**: Just the code you need
### Setup
```bash
npx shadcn@latest create
npx shadcn@latest init
npx shadcn@latest add button card dialog
```
### Component Architecture
```
src/
├── components/
│ ├── ui/ # shadcn components (don't modify directly)
│ └── [custom]/ # your composed components
├── lib/
│ └── utils.ts # cn() utility
└── app/
└── page.tsx
```
### The cn() Utility
```typescript
import { clsx, type ClassValue } from "clsx"
import { twMerge } from "tailwind-merge"
export function cn(...inputs: ClassValue[]) {
return twMerge(clsx(inputs))
}
```
### Customization
- **Theme**: Edit CSS variables in `globals.css`
- **Variants**: Use `class-variance-authority` (cva)
- **Extending**: Create wrapper components in `components/` (not `components/ui/`)
### Available Components (50+)
- **Layout**: Accordion, Card, SeRelated in Ads & Marketing
ads
IncludedMulti-platform paid advertising audit and optimization skill. Analyzes Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple Ads. 250+ checks with scoring, parallel agents, industry templates, and AI creative generation.
banana
IncludedAI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.
rpg-migration-analyzer
IncludedAnalyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies data structures (D-specs), file operations (F-specs), program dependencies (CALLB/CALLP), and converts RPG constructs to Java equivalents. Generates migration reports, complexity estimates, and Java implementation strategies with POJO classes, JPA entities, and service methods. Use when modernizing AS/400 or IBM i legacy systems, analyzing RPG source files (.rpg, .rpgle, .RPGLE), converting RPG to Java, mapping data specifications to Java classes, planning legacy system migration, or when user mentions RPG analysis, Report Program Generator, RPG III/IV/ILE, AS/400 modernization, IBM i migration, packed decimal conversion, or mainframe application rewrite.
brand-library-architect
IncludedBuild a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT), and a self-contained press kit. This skill should be used when the user asks to "build a brand library / brand kit / press kit / brand assets" for a product, "set up a brand library workflow," "create a positioning manifesto plus visual identity," or any combination of brand documentation + visual asset pipeline. Apply phase-by-phase or run end-to-end. Templates are product-agnostic and use {{TOKEN}} placeholders the skill prompts the user to fill.
writing-tech-post
IncludedAuthors engineering blog posts end-to-end: launch deep-dives, incident postmortems, architecture migrations, performance case studies, tutorials, AI/agent system writeups, security disclosures, and research-to-product translations. Picks the correct archetype, plans the abstraction ladder, enforces an evidence cadence (diagrams, benchmarks, profiles, traces, code, ablations), tunes voice against publisher house styles (Datadog, Vercel, GitHub, AWS, Meta, Cloudflare, Jane Street), and runs a pre-publish gate for narrative momentum and disclosure ethics. Use when drafting a new engineering post, restructuring a draft that feels flat, deciding which evidence form belongs where, validating that depth and product context are balanced, or preparing a postmortem, migration, or performance narrative for external publication. Do not use for API reference documentation, README authoring, marketing copy, release notes, generic SEO content, ghost-written executive thought leadership, or non-engineering long-form essays.
blog-google
IncludedGoogle API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".