stitch-design

Generate UI designs using Google Stitch AI with optimized prompts

Best use case

stitch-design is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Generate UI designs using Google Stitch AI with optimized prompts

Teams using stitch-design should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/stitch-design/SKILL.md --create-dirs "https://raw.githubusercontent.com/nguyenthienthanh/aura-frog/main/aura-frog/skills/stitch-design/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/stitch-design/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How stitch-design Compares

Feature / Agentstitch-designStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Generate UI designs using Google Stitch AI with optimized prompts

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

> **AI-consumed reference.** Optimized for Claude to read during execution.
> Human-readable explanation: see [docs/architecture/HIERARCHICAL_PLANNING.md](../../../docs/architecture/HIERARCHICAL_PLANNING.md)
> or [docs/getting-started/](../../../docs/getting-started/) depending on topic.


# Skill: Google Stitch Design

Generate UI designs using Google Stitch AI (https://stitch.withgoogle.com).

```toon
stitch_info[1]{engine,limits,export}:
  Gemini 2.5 Flash/Pro,350 gen/month (Standard),Figma paste or HTML/CSS
```

---

## Workflow

```toon
workflow[5]{step,action,output}:
  1,Gather requirements,Requirements doc
  2,Generate prompt,Optimized Stitch prompt
  3,Create review doc,.claude/workflow/stitch-design-review-*.md
  4,Guide user,Instructions + link
  5,Process export,Component code
```

### 1. Gather Requirements

Ask: app type (dashboard/landing/mobile/ecommerce/forms), target audience, theme, key features, existing brand.

### 2. Generate Prompt

Load template from `references/prompt-templates.md` matching app type. Fill with gathered requirements.

### 3. Create Review Document

Save to `.claude/workflow/stitch-design-review-{project-name}.md` with specs, acceptance criteria, and checklists for: visual design, UX, technical, brand alignment.

### 4. Guide User

Provide optimized prompt (copy-paste ready), link to Stitch, step-by-step instructions, export guidance (Figma recommended vs HTML/CSS).

### 5. Process Exported Code

Review HTML/CSS, extract design tokens, map to project design system, generate component files per conventions.

---

## Design Types

```toon
design_types[5]{type,use_case,template}:
  dashboard,Admin panels; analytics,references/prompt-templates.md#dashboard
  landing,Marketing; product pages,references/prompt-templates.md#landing
  mobile,iOS/Android screens,references/prompt-templates.md#mobile
  ecommerce,Product; cart; checkout,references/prompt-templates.md#ecommerce
  forms,Multi-step wizards,references/prompt-templates.md#forms
```

---

## Related Files

- `references/prompt-templates.md` - Optimized prompts by type
- `references/design-checklist.md` - Detailed review checklist
- `references/export-guide.md` - Export from Stitch

**Note:** Stitch has no API -- user must manually paste prompt and export results.

---

Related Skills

design-expert

14
from nguyenthienthanh/aura-frog

UI/UX design expertise — component design, design system selection, responsive layout. Includes auto-detection from package.json and Context7 integration for library docs.

api-designer

14
from nguyenthienthanh/aura-frog

Designs RESTful APIs with endpoint naming, versioning strategies (URL path, header-based), pagination (offset and cursor), error response schemas, and OpenAPI conventions. Use when the user asks about REST API design, creating endpoints, URL structure, API versioning, status codes, Swagger, or OpenAPI specs.

vue-expert

14
from nguyenthienthanh/aura-frog

Vue 3 gotchas and decision criteria. Covers reactivity traps, Composition API pitfalls, and Pinia patterns.

typescript-expert

14
from nguyenthienthanh/aura-frog

TypeScript gotchas and decision criteria covering nullish coalescing pitfalls (|| vs ??), strict tsconfig settings (noUncheckedIndexedAccess, exactOptionalPropertyTypes), type guard patterns, discriminated unions, and as const vs enum. Use when writing TypeScript, configuring tsconfig, implementing type guards, or debugging null/undefined errors.

tree-of-thoughts

14
from nguyenthienthanh/aura-frog

Branch, evaluate, prune, expand — structured search over solution space. Use for architecture with multi-step decisions, refactor planning, or complex debug hypothesis trees. Paper: Yao et al. 2023.

test-writer

14
from nguyenthienthanh/aura-frog

Write tests with TDD following structured patterns. Ensures consistent AAA structure, proper coverage targets, and framework-specific conventions. Without this skill, tests lack consistent naming, miss coverage targets, and skip anti-pattern checks.

session-continuation

14
from nguyenthienthanh/aura-frog

Manage workflow state across sessions with handoff and resume. TOON-based state persistence.

sequential-thinking

14
from nguyenthienthanh/aura-frog

Structured thinking process for complex analysis. Supports revision, branching, and dynamic adjustment.

self-improve

14
from nguyenthienthanh/aura-frog

Apply learned improvements to the Aura Frog plugin. Updates rules, adjusts agent routing, modifies workflow configurations, and generates knowledge base entries.

self-healing-orchestrator

14
from nguyenthienthanh/aura-frog

Proposes patches for F2 (local-logic) and F3 (local-design) failures. NEVER applies without user approval. Confidence ≥0.7 to propose; below that, escalates raw findings. Counts toward replan_budget. Per-task: max 1; per-session: max 5.

self-consistency

14
from nguyenthienthanh/aura-frog

Generate N independent reasoning paths and vote on the answer. Use for architectural trade-offs, ambiguous design decisions, or when single-path reasoning risks locking onto the first plausible answer. Paper: Wang et al. 2022.

scalable-thinking

14
from nguyenthienthanh/aura-frog

Design for scale while keeping implementation simple (KISS).