Validate ideas through interactive prototypes before writing code.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionprototype-designerExecute the skills CLI command in your project's root directory to begin installation:
Fetches prototype-designer from daffy0208/ai-dev-standards and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate prototype-designer. Access via /prototype-designer in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Automate repetitive workflows and reduce manual effort
Example
Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example
Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example
Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
0
total installs
0
this week
22
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
22
stars
Validate ideas through interactive prototypes before writing code.
Test before you build.
Prototypes let you:
| Tool | Best For | Learning Curve | Fidelity |
|---|---|---|---|
| Figma | Full designs, collaboration | Medium | High |
| Framer | Code-based, advanced interactions | High | Very High |
| ProtoPie | Complex interactions, sensors | Medium | Very High |
| Adobe XD | Adobe ecosystem users | Low | High |
| InVision | Design handoff, simple clicks | Low | Medium |
| Axure | Complex logic, documentation | High | High |
Beginner: Start with Figma
Advanced: Graduate to Framer or ProtoPie
A user flow shows the path users take through your app to complete a task.
Example: User Registration Flow
Start
↓
Landing Page
↓
Click "Sign Up"
↓
Email Entry → Validation
↓ [Valid]
Password Entry → Validation
↓ [Valid]
Success Screen
↓
Onboarding Flow
1. Create Flow Frames:
Frames needed:
├── 01-landing
├── 02-signup-form
├── 03-email-verification
├── 04-success
└── 05-onboarding-step-1
2. Add Interactions:
Click "Sign Up" button → Navigate to 02-signup-form
Click "Submit" → Navigate to 03-email-verification
Click "Continue" → Navigate to 04-success
3. Add Overlays:
Error states:
- Show "Error: Invalid email" overlay
- Show "Error: Password too weak" overlay
// user-flows.ts
interface UserFlow {
id: string
name: string
description: string
steps: FlowStep[]
alternativePaths: AlternativePath[]
}
interface FlowStep {
id: string
screen: string
action: string
nextStep: string
conditions?: string[]
}
interface AlternativePath {
trigger: string
steps: FlowStep[]
destination: string
}
export const signupFlow: UserFlow = {
id: 'signup',
name: 'User Registration',
description: 'User signs up for an account',
steps: [
{
id: '1',
screen: 'Landing Page',
action: 'Click "Sign Up"',
nextStep: '2'
},
{
id: '2',
screen: 'Sign Up Form',
action: 'Enter email and password',
nextStep: '3',
conditions: ['Email valid', 'Password strong']
},
{
id: '3',
screen: 'Email Verification',
action: 'Enter verification code',
nextStep: '4',
conditions: ['Code valid']
},
{
id: '4',
screen: 'Success',
action: 'Click "Get Started"',
nextStep: '5'
}
],
alternativePaths: [
{
trigger: 'Invalid email',
steps: [
{
id: 'error-1',
screen: 'Sign Up Form',
action: 'Show error message',
nextStep: '2'
}
],
destination: 'Step 2'
}
]
}
1. Basic Click Navigation:
Select element → Prototype panel → Add interaction
- Trigger: On click
- Action: Navigate to
- Destination: Screen name
- Animation: Instant / Dissolve / Slide / Push
2. Hover States:
Button → Prototype panel
- Trigger: While hovering
- Action: Change to
- Destination: Button-hover variant
3. Scroll Behavior:
Frame → Prototype panel
- Overflow behavior: Vertical scrolling
- Set scroll position (optional)
4. Smart Animate:
Two frames with matching layer names
- Animation: Smart animate
- Easing: Ease out
- Duration: 300ms
Conditional Logic (Variables):
// Figma Variables (Beta)
Variables:
- isLoggedIn: Boolean
- userType: String
- itemCount: Number
Conditional:
IF isLoggedIn = true
THEN Navigate to Dashboard
ELSE
THEN Navigate to Login
Multi-Step Forms:
Step 1 (Name) → Validation
↓ [Valid]
Step 2 (Email) → Validation
↓ [Valid]
Step 3 (Password) → Validation
↓ [Valid]
Success Screen
State Management:
Component: Button
States:
- Default
- Hover
- Pressed
- Disabled
- Loading
Prototype:
On click → Change to "Loading"
After delay → Navigate to next screen
Use Framer for:
// components/Counter.tsx
import { useState } from 'react'
export function Counter() {
const [count, setCount] = useState(0)
return (
<div
style={{
display: 'flex',
flexDirection: 'column',
alignItems: 'center',
gap: 16
}}
>
<h1 style={{ fontSize: 48 }}>{count}</h1>
<div style={{ display: 'flex', gap: 8 }}>
<button
onClick={() => setCount(count - 1)}
style={{
padding: '12px 24px',
fontSize: 16,
borderRadius: Prerequisites
Time Estimate
15-45 minutes depending on use case complexity
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
heyman333/atelier-ui
bencium/bencium-claude-code-design-skill
anthropics/claude-code
mblode/agent-skills
github/awesome-copilot
sickn33/antigravity-awesome-skills
prototype-designer has been reliable in day-to-day use. Documentation quality is above average for community skills.
Keeps context tight: prototype-designer is the kind of skill you can hand to a new teammate without a long onboarding doc.
Solid pick for teams standardizing on skills: prototype-designer is focused, and the summary matches what you get after install.
We added prototype-designer from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
We added prototype-designer from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
Keeps context tight: prototype-designer is the kind of skill you can hand to a new teammate without a long onboarding doc.
prototype-designer reduced setup friction for our internal harness; good balance of opinion and flexibility.
I recommend prototype-designer for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Solid pick for teams standardizing on skills: prototype-designer is focused, and the summary matches what you get after install.
Registry listing for prototype-designer matched our evaluation — installs cleanly and behaves as described in the markdown.
showing 1-10 of 32