product-engineer-agent
Use this skill to design new products, iterate on product ideas, or develop product specifications. Triggers: "design product", "new product idea", "product concept", "product development", "product spec", "iterate on product", "product design", "invention", "prototype spec", "product requirements", "product engineering", "develop product" Outputs: Product specification, BOM estimate, feature breakdown, differentiation analysis.
What this skill does
# Product Engineer Agent
Design and develop new product concepts with comprehensive specifications.
**This skill uses 5 specialized agents** that analyze product ideas from different engineering perspectives, then synthesizes into a complete product specification.
## What It Produces
| Output | Description |
|--------|-------------|
| **Product Spec** | Complete product specification document |
| **Feature Matrix** | Prioritized feature list with rationale |
| **BOM Estimate** | Bill of materials with rough cost estimates |
| **Differentiation** | How it differs from existing products |
| **Next Steps** | Recommended path to prototype/production |
| **Concept Renders** | Product visualization images (via image-generation) |
| **Engineering Drawings** | Exploded views, cross-sections, assembly diagrams |
## Prerequisites
- `GOOGLE_API_KEY` - For generating product visuals (uses image-generation skill)
- Works with any product category
## Workflow
### Step 1: Gather Product Idea (REQUIRED)
⚠️ **DO NOT skip this step. Use interactive questioning — ask ONE question at a time.**
#### Question Flow
⚠️ **Use the `AskUserQuestion` tool for each question below.** Do not just print questions in your response — use the tool to create interactive prompts with the options shown.
**Q1: Problem**
> "I'll help you design this product! First — **what problem does it solve?**
>
> *(The core user need)*"
*Wait for response.*
**Q2: User**
> "Who is the **target user**?
>
> *(Who will use this product?)*"
*Wait for response.*
**Q3: Features**
> "Any **must-have features** or key requirements?
>
> *(Or say 'help me figure it out')*"
*Wait for response.*
**Q4: Constraints**
> "Any **constraints** to consider?
>
> - Budget range
> - Size/form factor
> - Materials
> - Manufacturing method
> - Or describe"
*Wait for response.*
**Q5: Visuals**
> "Do you want me to **generate visuals**?
>
> - 🎨 Concept renders (what it looks like)
> - 🔧 Engineering drawings (exploded views, cross-sections)
> - Both
> - No visuals (spec document only)"
*Wait for response.*
#### Quick Reference
| Question | Determines |
|----------|------------|
| Problem | Core value proposition |
| User | User research focus |
| Features | Feature prioritization |
| Constraints | Manufacturing and design boundaries |
| Visuals | Whether to generate renders/drawings |
**Parse visual preferences:**
- "yes", "visuals", "show me", "render", "drawings" → Generate all visuals
- "concept only" → Just concept render + lifestyle
- "engineering only" → Just exploded/technical views
- "no visuals" or not mentioned → Skip visual generation
- Unclear → Default to generating visuals (they add value)
---
### Step 2: Run Specialized Engineering Agents in Parallel
Deploy 5 agents, each analyzing from a different perspective:
#### Agent 1: Industrial Designer
Focus: Form, ergonomics, aesthetics, user interaction
```
Consider:
- Physical form factor and dimensions
- Ergonomics and human factors
- Visual aesthetics and brand expression
- User interaction points (buttons, displays, etc.)
- Packaging and unboxing experience
```
#### Agent 2: Mechanical Engineer
Focus: How it works, materials, mechanisms
```
Consider:
- Core mechanism / how it functions
- Materials selection (strength, weight, cost)
- Manufacturing feasibility
- Durability and lifecycle
- Assembly and serviceability
```
#### Agent 3: User Researcher
Focus: User needs, pain points, usability
```
Consider:
- User journey with the product
- Pain points addressed
- Potential usability issues
- Onboarding and learning curve
- Accessibility considerations
```
#### Agent 4: Manufacturing Advisor
Focus: Feasibility, cost, production
```
Consider:
- Manufacturing methods (injection molding, CNC, etc.)
- Tooling requirements and costs
- Unit cost estimates at various volumes
- Supply chain considerations
- Quality control points
```
#### Agent 5: Innovation Scout
Focus: Existing solutions, patents, differentiation
```
Consider:
- Similar products in market
- Patent landscape (potential conflicts)
- Unique differentiators
- Technology trends to leverage
- Blue ocean opportunities
```
---
### Step 3: Synthesize into Product Specification
Combine all agent outputs into a structured specification:
```json
{
"product": {
"name": "Product Name",
"tagline": "One-line description",
"problem_solved": "Core problem it addresses",
"target_user": "Who it's for",
"category": "Product category"
},
"design": {
"form_factor": "Physical description",
"dimensions": "L x W x H",
"weight": "Estimated weight",
"materials": ["Material 1", "Material 2"],
"colors": ["Primary options"],
"key_interactions": ["How users interact with it"]
},
"features": {
"must_have": [
{"feature": "Feature 1", "rationale": "Why it's essential"}
],
"should_have": [
{"feature": "Feature 2", "rationale": "High value add"}
],
"could_have": [
{"feature": "Feature 3", "rationale": "Nice to have"}
]
},
"technical": {
"mechanism": "How it works",
"power_source": "Battery/plug/manual/etc.",
"electronics": "Any electronic components",
"software": "Any software/firmware needed"
},
"manufacturing": {
"primary_method": "Main manufacturing process",
"estimated_bom": [
{"component": "Part 1", "estimated_cost": "$X"}
],
"unit_cost_estimates": {
"100_units": "$XX",
"1000_units": "$XX",
"10000_units": "$XX"
},
"complexity": "Low/Medium/High"
},
"market": {
"similar_products": ["Competitor 1", "Competitor 2"],
"differentiators": ["What makes this unique"],
"price_positioning": "Budget/Mid/Premium",
"target_msrp": "$XX"
},
"next_steps": [
"1. Validate with potential users",
"2. Create detailed CAD model",
"3. Build first prototype",
"4. Patent search (if applicable)"
]
}
```
---
### Step 4: Generate Product Visuals (If Requested)
**Only generate visuals if user requested them in Step 1.**
If user wants visuals, generate using the `image-generation` skill:
| Visual Type | When to Generate |
|-------------|------------------|
| **Concept Render** | User said "yes", "visuals", "concept", or "both" |
| **Lifestyle/Context** | User said "yes", "visuals", "concept", or "both" |
| **Exploded View** | User said "engineering", "assembly", "exploded", or "both" |
| **Cross-Section** | User said "engineering" AND product has internal mechanism |
**From Industrial Designer:**
- `product_concept.png` - Main concept render (studio lighting, clean background)
- `product_context.png` - Product in-use/lifestyle shot
**From Mechanical Engineer:**
- `product_exploded.png` - Exploded view showing all components
- `product_section.png` - Cross-section (if internal mechanism is key)
**Visual Generation Order:**
1. Concept render first (shows overall design)
2. In-context shot (shows usage)
3. Exploded view (shows engineering)
4. Cross-section (if needed)
**If user didn't request visuals:** Skip to Step 5 with spec document only.
---
### Step 5: Deliver Complete Package
**Delivery message (with visuals):**
"✅ Product design complete!
**Product:** [Name]
**Problem:** [What it solves]
**Key Differentiator:** [What makes it unique]
**Estimated unit cost:** $XX at 1,000 units
**Suggested MSRP:** $XX
**Generated visuals:**
- Concept render ✓
- Lifestyle/context shot ✓
- Exploded assembly view ✓
**Next steps:**
1. [First recommended action]
2. [Second recommended action]
**Want me to:**
- Deep dive on any section?
- Generate additional views or angles?
- Explore alternative designs?
- Estimate costs for different volumes?
- Compare to specific competitors?"
---
**Delivery message (spec only, no visuals):**
"✅ Product specification complete!
**Product:** [Name]
**Problem:** [What it solves]
**Key Differentiator:** [What makes it unique]
**Estimated unit cost:** $XX at 1,000 units
**Suggested MSRelated 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.