prototype
# Parallel Prototype Orchestration
What this skill does
# Parallel Prototype Orchestration
Build and compare multiple web app prototypes simultaneously using sub-agents. Design first, spawn parallel builders, serve all variants, then iterate or finalize.
## When to Use
- User says "PROTOTYPE", "WEBAPP", or wants to explore multiple approaches
- Need to compare different design directions
- Want rapid parallel development with live preview
- Orchestra MCP is available for sub-agent spawning
## Overview
This skill orchestrates a multi-prototype workflow:
1. **Propose** n prototype variants (default: 3)
2. **Spawn** executor sub-agents to build each in parallel git worktrees
3. **Serve** all prototypes on different ports with live preview
4. **Select** the winning prototype, iterate, or kill all servers
---
## Phase 1: Design Variants (10-15 min)
Before spawning any agents, design multiple distinct approaches. Each variant should explore a different:
- **Visual style** (minimal vs rich, dark vs light)
- **Interaction pattern** (modals vs inline, tabs vs panels)
- **Architecture approach** (SPA vs multi-page, stateful vs stateless)
- **Feature focus** (speed vs features, simplicity vs power)
### Variant Proposal Template
Present variants to the user in this format:
```
## Prototype Variants
### Variant A: [Name] - [One-liner]
**Focus**: [Primary design goal]
**Visual**: [Style description]
**Interaction**: [How user interacts]
**Trade-off**: [What it optimizes for vs sacrifices]
### Variant B: [Name] - [One-liner]
**Focus**: [Primary design goal]
**Visual**: [Style description]
**Interaction**: [How user interacts]
**Trade-off**: [What it optimizes for vs sacrifices]
### Variant C: [Name] - [One-liner]
**Focus**: [Primary design goal]
**Visual**: [Style description]
**Interaction**: [How user interacts]
**Trade-off**: [What it optimizes for vs sacrifices]
Which variants would you like me to build? (A/B/C/all/suggest more)
```
### Example Variants for a Note-Taking App
```
### Variant A: "Zen" - Distraction-free writing
**Focus**: Minimal UI, maximum focus
**Visual**: White background, single centered column, no sidebar
**Interaction**: Everything via keyboard shortcuts, hidden toolbar
**Trade-off**: Speed over discoverability
### Variant B: "Dashboard" - Power user's command center
**Focus**: Information density, quick navigation
**Visual**: Dark theme, three-column layout, visible sidebar
**Interaction**: Click-driven with command palette (⌘K)
**Trade-off**: Features over simplicity
### Variant C: "Mobile-First" - Touch-optimized responsive
**Focus**: Works great on all devices
**Visual**: Large touch targets, bottom navigation, swipe gestures
**Interaction**: Thumb-friendly actions, pull-to-refresh
**Trade-off**: Mobile experience over desktop power features
```
---
## Phase 2: Spawn Parallel Builders (2-3 min)
Once user approves variants, spawn executor sub-agents in parallel using Orchestra MCP.
### Pre-Spawn Checklist
1. Confirm Orchestra MCP is available
2. Get source path from project config
3. Generate unique session names for each variant
### Spawning Pattern
For each approved variant, call `spawn_subagent` with:
```python
spawn_subagent(
parent_session_name="main",
child_session_name="prototype-{variant_letter}",
source_path="/path/to/project",
agent_type="executor",
instructions="""
# Prototype {Variant Letter}: {Variant Name}
## Your Mission
Build a working prototype implementing this specific design direction.
## Design Spec
{Full design specification from Phase 1}
## Tech Stack
- Frontend: React + Vite
- Backend: FastAPI (if needed) or static
- Database: SQLite (if needed)
- Styling: Tailwind CSS or vanilla CSS
## Requirements
1. Must run on port {assigned_port}
2. Create in: src/prototypes/variant-{letter}/
3. Include a launcher script that starts the dev server
4. Implement core features only (no gold plating)
5. Add ⌘S (save) and ⌘/ (help) keyboard shortcuts
## Success Criteria
- App runs on http://localhost:{port}
- Core user flow works end-to-end
- No console errors
- Clean, readable code
## When Done
Message the main session with:
- Confirmation prototype is running
- The URL to access it
- Brief summary of implementation choices
"""
)
```
### Port Assignment
Use this port scheme to avoid conflicts:
| Variant | Frontend Port | Backend Port |
|---------|--------------|--------------|
| A | 5173 | 8001 |
| B | 5174 | 8002 |
| C | 5175 | 8003 |
| D | 5176 | 8004 |
| E | 5177 | 8005 |
### Parallel Spawn Example
```python
# Spawn all variants in parallel (single message with multiple tool calls)
spawn_subagent(
parent_session_name="main",
child_session_name="prototype-a",
source_path=source_path,
instructions="... Variant A spec ..."
)
spawn_subagent(
parent_session_name="main",
child_session_name="prototype-b",
source_path=source_path,
instructions="... Variant B spec ..."
)
spawn_subagent(
parent_session_name="main",
child_session_name="prototype-c",
source_path=source_path,
instructions="... Variant C spec ..."
)
```
---
## Phase 3: Monitor & Serve (During Build)
### Tracking Progress
While executors build, periodically check:
1. `.orchestra/messages.jsonl` for status updates
2. Git worktrees at `/Users/wz/.orchestra/subagents/{session-id}/`
3. Port availability for each prototype
### Status Dashboard (Show to User)
```
## Prototype Status
| Variant | Session | Status | URL |
|---------|-----------------|-------------|------------------------|
| A | prototype-a | ⏳ Building | http://localhost:5173 |
| B | prototype-b | ✅ Running | http://localhost:5174 |
| C | prototype-c | ⏳ Building | http://localhost:5175 |
Last updated: [timestamp]
```
### Opening Prototypes
When an executor reports completion:
1. Verify the dev server is running on the assigned port
2. Open in browser: `open http://localhost:{port}`
3. Update status dashboard
4. Notify user: "Variant {X} is now live at http://localhost:{port}"
### Bulk Open Command
Once all prototypes are ready:
```bash
# Open all prototypes in browser tabs
open http://localhost:5173 http://localhost:5174 http://localhost:5175
```
---
## Phase 4: Selection & Iteration
### Presenting Options
Once all prototypes are running, ask the user:
```
## All Prototypes Ready!
🅰️ Variant A "Zen" - http://localhost:5173
🅱️ Variant B "Dashboard" - http://localhost:5174
🅲️ Variant C "Mobile-First" - http://localhost:5175
**What would you like to do?**
1. **Select winner** - Choose one to continue developing
2. **Iterate** - Request changes to specific variants
3. **Combine** - Merge features from multiple variants
4. **More variants** - Generate n more prototype ideas
5. **Kill all** - Stop all servers and clean up
```
### User Choice Handling
#### Choice 1: Select Winner
```
User: "I like Variant B"
Action:
1. Kill dev servers for A and C
2. Merge Variant B branch to main (with user approval)
3. Continue development on selected prototype
4. Clean up unused worktrees
```
#### Choice 2: Iterate
```
User: "Can you make Variant A have a sidebar like B?"
Action:
1. Send iteration instructions to prototype-a executor:
send_message_to_session(
session_name="prototype-a",
message="Add a collapsible sidebar similar to Variant B's implementation...",
source_path=source_path,
sender_name="main"
)
2. Wait for completion
3. Refresh browser / notify user
```
#### Choice 3: Combine
```
User: "I want A's minimal editor with B's sidebar and C's mobile responsiveness"
Action:
1. Create new variant specification combining features
2. Spawn new executor: prototype-combined
3. Use existing code as reference
```
#### Choice 4: More Variants
```
User: "Show me 2 more ideas"
Action:
1. Return to Phase 1
2. Generate 2 new distinct variantsRelated in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.