/brainstorm

name: brainstorm
type: workflow
description: "Facilitates structured product ideation to define user needs, core value, and product direction. Use when the user wants to explore a new product idea, has a vague concept to develop, or mentions brainstorming or ideation."
argument-hint: "[product type or problem hint, or 'open' for fully open brainstorm]"
user-invocable: true
allowed-tools: Read, Glob, Grep, Write, WebSearch, AskUserQuestion
context: fork
agent: product-manager
effort: 3
when_to_use: "When starting a new product idea from scratch or needing structured creative ideation for a product concept"

When this skill is invoked:

1. **Parse the argument** for an optional product type or problem hint (e.g., `productivity app`, `API service`, `developer tool`, `marketplace`). If `open` or no argument, start from scratch.

2. **Check for existing concept work**:

• Read `design/docs/product-concept.md` if it exists (resume, don't restart)
• Read `design/docs/product-pillars.md` if it exists (build on established pillars)

3. **Run through ideation phases** interactively, asking the user questions at each phase. Do NOT generate everything silently — the goal is **collaborative exploration** where the AI acts as a product thinking facilitator, not a replacement for the human's vision.

**Use `AskUserQuestion`** at key decision points throughout brainstorming:

• Constrained taste questions (product type, target users, scope)
• Concept selection ("Which 2-3 concepts resonate?") after presenting options
• Direction choices ("Develop further, explore more, or start sprint planning?")
• Pillar ranking after concepts are refined

Write full analysis in conversation text first, then use `AskUserQuestion` to capture the decision with concise labels.

Professional product brainstorming principles to follow:

• Withhold judgment — no idea is bad during exploration
• Encourage unusual ideas — outside-the-box thinking sparks better products
• Build on each other — "yes, and..." responses, not "but..."
• Use constraints as creative fuel — limitations often produce the best ideas
• Time-box each phase — keep momentum, don't over-deliberate early

---

Phase 1: Creative Discovery

Start by understanding the person and their context, not the product. Ask these questions conversationally (not as a checklist):

**Problem anchors**:

• What's a frustrating problem you personally experience that no existing tool solves well?
• Is there a workflow, process, or task you've always wished was easier or more automated?

**Experience profile**:

• What 3 products (apps, tools, APIs, services) do you use most? What keeps you coming back?
• Are there product categories you love or actively avoid? Why?
• Do you prefer products that save time, reduce complexity, enable creativity, or connect people?

**Practical constraints** (shape the sandbox before brainstorming):

• Solo developer or team? What skills and resources are available?
• Timeline: weeks (MVP), months (v1), or years (full product)?
• Any platform constraints? (Web only? Mobile? API-first? Desktop?)
• First product or experienced builder?
• Revenue model in mind? (SaaS, open source, freemium, one-time purchase?)

**Synthesize** the answers into a **Product Brief** — a 3-5 sentence summary of the person's goals, experience context, and constraints. Read the brief back and confirm it captures their intent.

---

Phase 2: Concept Generation

Using the product brief as a foundation, generate **3 distinct concepts** that each take a different creative direction. Use these ideation techniques:

**Technique 1: Verb-First Design** Start with the core user verb (build, track, automate, connect, analyze, manage, discover, share, deploy) and build the product outward from there. The verb IS the product.

**Technique 2: Problem-Inversion Method** Take an existing frustration in a market and invert it. "What if [pain point] just... didn't exist?" Then design backward from that ideal state. Find the simplest product that bridges the current reality to that ideal.

**Technique 3: Intersection Design** Combine two unexpected domains: [Audience A] + [Workflow B]. The intersection creates the unique hook. (e.g., "developers + financial compliance", "designers + data pipelines", "small teams + enterprise security")

For each concept, present:

• **Working Title**
• **Elevator Pitch** (1-2 sentences — must pass the "10-second test")
• **Core User Action** (the single most frequent thing a user does)
• **Core Value Promise** (the outcome users pay/sign-up for)
• **Unique Angle** (passes the "AND ALSO" test: "Like X, AND ALSO Y")
• **Target User** (who specifically? Not "developers" — "backend engineers at 50-person startups")
• **Estimated Scope** (small / medium / large)
• **Why It Could Work** (1 sentence on market/timing fit)
• **Biggest Risk** (1 sentence on the hardest unanswered question)

Present all three. Ask the user to pick one, combine elements, or request new concepts. Never pressure toward a choice — let them sit with it.

---

Phase 3: Core User Flow Design

For the chosen concept, use structured questioning to build the core user flow. The core flow is the beating heart of the product — if it isn't valuable in isolation, no amount of features or polish will save the product.

**First-Use Flow** (the critical first 5 minutes):

• What's the first action a new user takes?
• When do they first experience value? (The "aha moment")
• What friction exists between sign-up and first value? How to minimize it?

**Core Usage Loop** (the repeating cycle):

• What does a typical usage session look like from start to finish?
• What triggers the user to open/use the product? (External trigger? Internal habit?)
• What output or result makes the session feel successful?

**Retention Hook** (why they come back):

• What makes users return daily / weekly?
• What accumulates over time that makes the product mor