AI UI Generation
Patterns for generating, reviewing, and integrating UI components produced by AI tools (json-render, v0.app, Google Stitch, Bolt Cloud, Cursor). json-render is the first choice for multi-surface, MCP visual output, and type-safe catalog workflows. AI-generated UI is 80% boilerplate, 20% custom — the human reviews, refactors, and owns the output. These rules ensure AI output meets design system, accessibility, and quality standards before shipping.
Tool landscape as of 2026-04:
- v0.dev → v0.app (Jan 2026 rebrand) — expanded from component scaffolding to full-stack app generation with shipping targets (Vercel, Cloudflare, Railway). v0.app MCP server (
@vercel/v0-mcp) exposes generation as an MCP tool, so agents can call it programmatically.
- Google Stitch — design-first generation via
stitch.withgoogle.com/docs/mcp. Produces multi-screen apps (up to 5 interconnected screens) with React/HTML + PNG. Strong when input is a screenshot, URL, or DESIGN.md file.
- Bolt Cloud (StackBlitz, 2026) — Bolt now runs the dev environment in the cloud (no local WebContainer). Integrates with GitHub and supports persistent databases. Best for full-stack prototypes with backend + deploy.
- v0.app and Stitch both integrate with shadcn/ui styles; pair with the
shadcn apply <style> CLI (v4) to reuse generated output.
Quick Reference
Total: 8 rules across 5 categories
Decision Table — json-render vs v0.app vs Stitch vs Bolt Cloud vs Cursor
| Scenario |
Tool |
Why |
| Multi-surface / MCP visual output |
json-render |
Single catalog renders to any surface — FIRST CHOICE |
| Type-safe component catalog |
json-render |
Schema-driven specs with per-platform registries |
| Streaming UI from AI agents |
json-render |
Structured JSON specs render progressively |
| New component from scratch |
v0.app |
Full scaffold with shadcn/ui, Tailwind, a11y. Pair with shadcn apply <style> for style consistency |
| Full-stack app with deploy |
v0.app |
Jan 2026 expansion — routes, DB, auth, Vercel/Cloudflare deploy in one generation |
| Design-driven (screenshot/URL/DESIGN.md) |
Google Stitch |
generate_screen_from_text (once; no retry) + get_screen(name="projects/{project}/screens/{screen}") |
| Multi-screen flow from a visual source |
Google Stitch |
Strongest when grounded in an existing design |
| Full-stack prototype with persistent backend |
Bolt Cloud |
Cloud dev env, GitHub integration, databases |
| Incremental change in existing codebase |
Cursor |
Understands project context, imports, tokens |
| Refactor existing component |
Cursor |
Reads surrounding code, respects conventions |
| Explore visual design variations |
v0.app or Stitch |
v0.app for freeform, Stitch when grounded in a reference |
| Add feature to running app |
Bolt Cloud |
Cloud preview, full environment, persists between sessions |
| Fix bug in existing component |
Cursor |
Inline edits with full project awareness |
Quick Start
Structured Prompt Example
Generate a React signup form component using:
- Framework: React 19 + TypeScript
- Styling: Tailwind CSS v4 + shadcn/ui (Luma style — rounded-4xl, shadow-md elevation)
- Style: run `npx shadcn@latest apply luma` (CLI v4, Apr 2026) after generation
- Tokens: use color.primary, color.destructive, spacing.md from our design system
- A11y: ARIA labels on all inputs, error announcements via aria-live
- States: default, loading (disabled + spinner), error (inline messages), success
- Responsive: stack on mobile (<640px), 2-col on desktop
Review Example — After AI Generation
// AI generated: hardcoded hex value
<button className="bg-[#3b82f6] text-white px-4 py-2">Submit</button>
// After human review: design token applied
<Button variant="default" size="md">Submit</Button>
Rule Details
json-render Integration
json-render is the first choice for AI UI generation when output must render across multiple surfaces (web, mobile, CLI, MCP). Define a catalog of components once, generate JSON specs from AI, and render on any target surface. See ork:json-render-catalog for catalog authoring patterns.
| Rule |
File |
Key Pattern |
| json-render Patterns |
rules/json-render-patterns.md |
Catalog-first: define once, render anywhere via per-platform registries |
Prompt Engineering
Structured prompts that specify framework, tokens, a11y, and states upfront.
| Rule |
File |
Key Pattern |
| Prompt Patterns |
rules/ai-prompt-patterns.md |
Constraint-first prompts with framework, tokens, a11y |
| Iteration Patterns |
rules/ai-iteration-patterns.md |
Multi-pass prompts for complex interactive states |
Quality Assurance
Systematic review and CI gating for AI-generated components.
| Rule |
File |
Key Pattern |
| Review Checklist |
rules/ai-review-checklist.md |
10-point checklist for every AI-generated component |
| CI Gate |
rules/ai-ci-gate.md |
Automated quality gates before merge |
Design System Integration
Ensuring AI output uses design tokens and conforms to the design system.
| Rule |
File |
Key Pattern |
| Token Injection |
rules/ai-token-injection.md |
Pass token names in prompts, reject hardcoded values |
| Refactoring Conformance |
rules/ai-refactoring-conformance.md |
Steps to refactor raw AI output for design system |
Tool Selection & Workflow
Choosing the right AI tool and iterating effectively.
| Rule |
File |
Key Pattern |
| Tool Selection |
rules/ai-tool-selection.md |
Match tool to use case: v0, Bolt, Cursor |
| Iteration Patterns |
rules/ai-iteration-patterns.md |
Iterative refinement for complex states |
Key Principles
- Own the output — AI generates a draft; the engineer reviews, refactors, and is accountable for what ships.
- Tokens over literals — Never accept hardcoded colors, spacing, or typography values. Always map to design tokens.
- Constraint-first prompts — Specify framework, tokens, shadcn style (Luma/Nova/etc.), a11y, and states upfront. Vague prompts produce vague output.
- Iterative refinement — Complex components need 2-3 prompt passes: structure first, states second, polish third.
- CI is non-negotiable — Every AI-generated component goes through the same CI pipeline as hand-written code.
- Accessibility by default — Include a11y requirements in every prompt; verify with automated checks post-generation.
Anti-Patterns (FORBIDDEN)
- Shipping raw AI output — Never merge AI-generated code without human review and design system refactoring.
- Vague prompts — "Make a nice form" produces inconsistent, non-conformant output. Always specify constraints.
- Hardcoded hex/rgb values — AI tools default to arbitrary colors. Replace with OKLCH design tokens.
- Skipping CI for "simple" components — AI-generated code has the same bug surface as hand-written code.
- Using v0.app for incremental changes — v0.app generates from scratch; use Cursor for changes within an existing codebase.
- Single-pass complex components — Multi-state components (loading, error, empty, success) need iterative prompting.
- Trusting AI a11y claims — AI tools add ARIA attributes inconsistently. Always verify with axe-core or Storybook a11y addon.
Detailed Documentation
| Resource |
Description |
| references/ai-ui-tool-comparison.md |
json-render vs v0 vs Bolt vs Cursor vs Copilot comparison |
| references/prompt-templates-library.md |
Copy-paste prompt templates for common components |
| references/ai-ui-failure-modes.md |
Top 10 failure modes and fixes |
Related Skills
ork:json-render-catalog — json-render catalog authoring, schema validation, and registry patterns
ork:mcp-visual-output — MCP visual output rendering with json-render specs
ork:multi-surface-render — Cross-platform rendering from a single component catalog
ork-extras:ui-components — shadcn/ui component patterns and CVA variants
ork-extras:accessibility — WCAG compliance, ARIA patterns, screen reader support
ork-extras:animation-motion-design — Motion library animation patterns
ork-extras:responsive-patterns — Responsive layout and container query patterns
ork:design-system-tokens — Design token architecture and theming
1---2name: ai-ui-generation3license: MIT4compatibility: "Claude Code 2.1.277+."5description: "AI UI generation with json-render, v0.app, Stitch, Bolt, and Cursor: prompt engineering, review checklists, design system conformance, CI gates. Use when generating UI components with AI tools, reviewing AI-generated code, or rendering MCP visual output."6user-invocable: false7metadata:8 source: https://skillmd.com/skills/yonatangross/ai-ui-generation9 owner-agent: "frontend-ui-developer"10 category: document-asset-creation11 version: "1.1.0"12 author: "OrchestKit"13 complexity: "medium"14 tags: "ai-ui, json-render, v0, v0-app, stitch, bolt, bolt-cloud, cursor, prompt-engineering, code-generation, design-tokens, component-generation, ai-review, shadcn-ui"15allowed-tools: "Read Glob Grep WebFetch WebSearch mcp__stitch__generate_screen_from_text mcp__plugin_hq-ext_stitch__generate_screen_from_text mcp__stitch__get_screen mcp__plugin_hq-ext_stitch__get_screen"16 # Stitch: body names generate_screen_from_text and get_screen.17 # Grant BOTH prefixes: standalone stitch (mcp__stitch__*) and hq-ext plugin18 # (mcp__plugin_hq-ext_stitch__*). See https://code.claude.com/docs/en/mcp-servers19---2021# AI UI Generation2223Patterns for generating, reviewing, and integrating UI components produced by AI tools (json-render, v0.app, Google Stitch, Bolt Cloud, Cursor). **json-render is the first choice** for multi-surface, MCP visual output, and type-safe catalog workflows. AI-generated UI is **80% boilerplate, 20% custom** — the human reviews, refactors, and owns the output. These rules ensure AI output meets design system, accessibility, and quality standards before shipping.2425> **Tool landscape as of 2026-04:**26> - **v0.dev → v0.app** (Jan 2026 rebrand) — expanded from component scaffolding to full-stack app generation with shipping targets (Vercel, Cloudflare, Railway). v0.app MCP server (`@vercel/v0-mcp`) exposes generation as an MCP tool, so agents can call it programmatically.27> - **Google Stitch** — design-first generation via `stitch.withgoogle.com/docs/mcp`. Produces multi-screen apps (up to 5 interconnected screens) with React/HTML + PNG. Strong when input is a screenshot, URL, or DESIGN.md file.28> - **Bolt Cloud** (StackBlitz, 2026) — Bolt now runs the dev environment in the cloud (no local WebContainer). Integrates with GitHub and supports persistent databases. Best for full-stack prototypes with backend + deploy.29> - **v0.app** and **Stitch** both integrate with shadcn/ui styles; pair with the `shadcn apply <style>` CLI (v4) to reuse generated output.3031## Quick Reference3233| Category | Rules | Impact | When to Use |34|----------|-------|--------|-------------|35| [json-render Integration](#json-render-integration) | 1 | HIGH | Multi-surface output, MCP visual output, type-safe catalogs |36| [Prompt Engineering](#prompt-engineering) | 2 | HIGH | Writing prompts for component generation |37| [Quality Assurance](#quality-assurance) | 2 | CRITICAL/HIGH | Reviewing and gating AI-generated code |38| [Design System Integration](#design-system-integration) | 2 | HIGH | Injecting tokens, refactoring for conformance |39| [Tool Selection & Workflow](#tool-selection--workflow) | 2 | MEDIUM | Choosing the right AI tool, iterating prompts |4041**Total: 8 rules across 5 categories**4243## Decision Table — json-render vs v0.app vs Stitch vs Bolt Cloud vs Cursor4445| Scenario | Tool | Why |46|----------|------|-----|47| Multi-surface / MCP visual output | json-render | Single catalog renders to any surface — FIRST CHOICE |48| Type-safe component catalog | json-render | Schema-driven specs with per-platform registries |49| Streaming UI from AI agents | json-render | Structured JSON specs render progressively |50| New component from scratch | v0.app | Full scaffold with shadcn/ui, Tailwind, a11y. Pair with `shadcn apply <style>` for style consistency |51| Full-stack app with deploy | v0.app | Jan 2026 expansion — routes, DB, auth, Vercel/Cloudflare deploy in one generation |52| Design-driven (screenshot/URL/DESIGN.md) | Google Stitch | `generate_screen_from_text` (once; no retry) + `get_screen(name="projects/{project}/screens/{screen}")` |53| Multi-screen flow from a visual source | Google Stitch | Strongest when grounded in an existing design |54| Full-stack prototype with persistent backend | Bolt Cloud | Cloud dev env, GitHub integration, databases |55| Incremental change in existing codebase | Cursor | Understands project context, imports, tokens |56| Refactor existing component | Cursor | Reads surrounding code, respects conventions |57| Explore visual design variations | v0.app or Stitch | v0.app for freeform, Stitch when grounded in a reference |58| Add feature to running app | Bolt Cloud | Cloud preview, full environment, persists between sessions |59| Fix bug in existing component | Cursor | Inline edits with full project awareness |6061## Quick Start6263### Structured Prompt Example6465```66Generate a React signup form component using:67- Framework: React 19 + TypeScript68- Styling: Tailwind CSS v4 + shadcn/ui (Luma style — rounded-4xl, shadow-md elevation)69- Style: run `npx shadcn@latest apply luma` (CLI v4, Apr 2026) after generation70- Tokens: use color.primary, color.destructive, spacing.md from our design system71- A11y: ARIA labels on all inputs, error announcements via aria-live72- States: default, loading (disabled + spinner), error (inline messages), success73- Responsive: stack on mobile (<640px), 2-col on desktop74```7576### Review Example — After AI Generation7778```tsx79// AI generated: hardcoded hex value80<button className="bg-[#3b82f6] text-white px-4 py-2">Submit</button>8182// After human review: design token applied83<Button variant="default" size="md">Submit</Button>84```8586## Rule Details8788### json-render Integration8990json-render is the **first choice** for AI UI generation when output must render across multiple surfaces (web, mobile, CLI, MCP). Define a catalog of components once, generate JSON specs from AI, and render on any target surface. See `ork:json-render-catalog` for catalog authoring patterns.9192| Rule | File | Key Pattern |93|------|------|-------------|94| json-render Patterns | `rules/json-render-patterns.md` | Catalog-first: define once, render anywhere via per-platform registries |9596### Prompt Engineering9798Structured prompts that specify framework, tokens, a11y, and states upfront.99100| Rule | File | Key Pattern |101|------|------|-------------|102| Prompt Patterns | `rules/ai-prompt-patterns.md` | Constraint-first prompts with framework, tokens, a11y |103| Iteration Patterns | `rules/ai-iteration-patterns.md` | Multi-pass prompts for complex interactive states |104105### Quality Assurance106107Systematic review and CI gating for AI-generated components.108109| Rule | File | Key Pattern |110|------|------|-------------|111| Review Checklist | `rules/ai-review-checklist.md` | 10-point checklist for every AI-generated component |112| CI Gate | `rules/ai-ci-gate.md` | Automated quality gates before merge |113114### Design System Integration115116Ensuring AI output uses design tokens and conforms to the design system.117118| Rule | File | Key Pattern |119|------|------|-------------|120| Token Injection | `rules/ai-token-injection.md` | Pass token names in prompts, reject hardcoded values |121| Refactoring Conformance | `rules/ai-refactoring-conformance.md` | Steps to refactor raw AI output for design system |122123### Tool Selection & Workflow124125Choosing the right AI tool and iterating effectively.126127| Rule | File | Key Pattern |128|------|------|-------------|129| Tool Selection | `rules/ai-tool-selection.md` | Match tool to use case: v0, Bolt, Cursor |130| Iteration Patterns | `rules/ai-iteration-patterns.md` | Iterative refinement for complex states |131132## Key Principles1331341. **Own the output** — AI generates a draft; the engineer reviews, refactors, and is accountable for what ships.1352. **Tokens over literals** — Never accept hardcoded colors, spacing, or typography values. Always map to design tokens.1363. **Constraint-first prompts** — Specify framework, tokens, shadcn style (Luma/Nova/etc.), a11y, and states upfront. Vague prompts produce vague output.1374. **Iterative refinement** — Complex components need 2-3 prompt passes: structure first, states second, polish third.1385. **CI is non-negotiable** — Every AI-generated component goes through the same CI pipeline as hand-written code.1396. **Accessibility by default** — Include a11y requirements in every prompt; verify with automated checks post-generation.140141## Anti-Patterns (FORBIDDEN)142143- **Shipping raw AI output** — Never merge AI-generated code without human review and design system refactoring.144- **Vague prompts** — "Make a nice form" produces inconsistent, non-conformant output. Always specify constraints.145- **Hardcoded hex/rgb values** — AI tools default to arbitrary colors. Replace with OKLCH design tokens.146- **Skipping CI for "simple" components** — AI-generated code has the same bug surface as hand-written code.147- **Using v0.app for incremental changes** — v0.app generates from scratch; use Cursor for changes within an existing codebase.148- **Single-pass complex components** — Multi-state components (loading, error, empty, success) need iterative prompting.149- **Trusting AI a11y claims** — AI tools add ARIA attributes inconsistently. Always verify with axe-core or Storybook a11y addon.150151## Detailed Documentation152153| Resource | Description |154|----------|-------------|155| [references/ai-ui-tool-comparison.md](references/ai-ui-tool-comparison.md) | json-render vs v0 vs Bolt vs Cursor vs Copilot comparison |156| [references/prompt-templates-library.md](references/prompt-templates-library.md) | Copy-paste prompt templates for common components |157| [references/ai-ui-failure-modes.md](references/ai-ui-failure-modes.md) | Top 10 failure modes and fixes |158159## Related Skills160161- `ork:json-render-catalog` — json-render catalog authoring, schema validation, and registry patterns162- `ork:mcp-visual-output` — MCP visual output rendering with json-render specs163- `ork:multi-surface-render` — Cross-platform rendering from a single component catalog164- `ork-extras:ui-components` — shadcn/ui component patterns and CVA variants165- `ork-extras:accessibility` — WCAG compliance, ARIA patterns, screen reader support166- `ork-extras:animation-motion-design` — Motion library animation patterns167- `ork-extras:responsive-patterns` — Responsive layout and container query patterns168- `ork:design-system-tokens` — Design token architecture and theming