prototype-interaction
Define and document prototype interactions, transitions, and hotspots
Best use case
prototype-interaction is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Define and document prototype interactions, transitions, and hotspots
Teams using prototype-interaction 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
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/prototype-interaction/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How prototype-interaction Compares
| Feature / Agent | prototype-interaction | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Define and document prototype interactions, transitions, and hotspots
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
# Prototype Interaction Skill
## Purpose
Define prototype interactions, map click/tap actions, configure transitions, and generate interaction specifications for design handoff.
## Capabilities
- Map click/tap interactions to destinations
- Define transition animations and timing
- Set up interactive hotspots
- Generate interaction specification documents
- Export to Figma prototype format
- Create interaction matrices
## Target Processes
- hifi-prototyping.js
- wireframing.js (interactivePrototypeTask)
## Integration Points
- Figma Prototype API
- InVision API
- ProtoPie specifications
## Input Schema
```json
{
"type": "object",
"properties": {
"screens": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": { "type": "string" },
"name": { "type": "string" },
"imagePath": { "type": "string" }
}
}
},
"interactions": {
"type": "array",
"items": {
"type": "object",
"properties": {
"sourceScreen": { "type": "string" },
"hotspot": {
"type": "object",
"properties": {
"x": { "type": "number" },
"y": { "type": "number" },
"width": { "type": "number" },
"height": { "type": "number" }
}
},
"trigger": {
"type": "string",
"enum": ["tap", "click", "hover", "drag", "swipe"]
},
"targetScreen": { "type": "string" },
"transition": {
"type": "object",
"properties": {
"type": { "type": "string" },
"duration": { "type": "number" },
"easing": { "type": "string" }
}
}
}
}
},
"outputFormat": {
"type": "string",
"enum": ["json", "figma", "invision", "markdown"],
"default": "json"
}
},
"required": ["screens", "interactions"]
}
```
## Output Schema
```json
{
"type": "object",
"properties": {
"interactionSpec": {
"type": "object",
"description": "Complete interaction specification"
},
"interactionMatrix": {
"type": "array",
"description": "Screen-to-screen interaction matrix"
},
"transitionGuide": {
"type": "object",
"description": "Transition timing and easing guide"
},
"hotspotOverlays": {
"type": "array",
"description": "Visual hotspot overlay data"
},
"exportPath": {
"type": "string",
"description": "Path to exported specification"
}
}
}
```
## Usage Example
```javascript
const result = await skill.execute({
screens: [
{ id: 'home', name: 'Home Screen', imagePath: './screens/home.png' },
{ id: 'detail', name: 'Detail View', imagePath: './screens/detail.png' }
],
interactions: [
{
sourceScreen: 'home',
hotspot: { x: 100, y: 200, width: 150, height: 50 },
trigger: 'tap',
targetScreen: 'detail',
transition: { type: 'slide-left', duration: 300, easing: 'ease-out' }
}
],
outputFormat: 'markdown'
});
```Related Skills
process-builder
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
babysitter
Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
yolo
Run Babysitter autonomously with minimal manual interruption.
user-install
Install the user-level Babysitter Codex setup.
team-install
Install the team-pinned Babysitter Codex workspace setup.
retrospect
Summarize or retrospect on a completed Babysitter run.
resume
Resume an existing Babysitter run from Codex.
project-install
Install the Babysitter Codex workspace integration into the current project.
plan
Plan a Babysitter workflow without executing the run.
observe
Observe, inspect, or monitor a Babysitter run.
model
Inspect or change Babysitter model-routing policy by phase.
issue
Run an issue-centric Babysitter workflow.