agentleFS
nisarthnisarth/claude-skills-store/skills/product-management/product-brainstorming/SKILL.md

product-brainstorming

Skill1 starsChanged 7 months agoMITView on GitHub

Structured product ideation: problem framing, solution exploration, feasibility assessment, and prioritization. Use when exploring a new opportunity, generating solutions to a product problem, stress-testing an idea, or running a structured ideation session. Trigger phrases: "product ideation", "generate product ideas", "solution exploration", "ideation session", "what could we build", "explore solutions for", "structured brainstorm", "feasibility assessment", "idea generation", "product concept"

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run a structured ideation process from problem framing through prioritized concept selection.

    line 12
  2. Distinctive:

    Use four lenses to generate breadth:

    line 40
  3. Distinctive:

    Desirability: Do people want this? Is there evidence of demand?

    line 88
  4. Distinctive:

    Involve diverse perspectives: If ideating solo, deliberately take opposing viewpoints: the skeptic, the user, the engineer, the business …

    line 163

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Structured Product Ideation

Run a structured ideation process from problem framing through prioritized concept selection. Unlike freeform brainstorming, this skill follows a disciplined framework to produce actionable product concepts.

Workflow

Step 1: Problem Framing

Define the problem space before generating solutions:

Problem Statement Canvas:

## Problem Statement

**Who**: [Specific user segment with context]
**Situation**: [When and where this problem occurs]
**Problem**: [What they struggle with or cannot do]
**Impact**: [Consequence of the problem -- time, money, frustration, risk]
**Current alternatives**: [How they cope today]
**Why now**: [What makes this timely -- market shift, tech change, regulation]

Validate the problem statement by checking:

  • Is this a real problem (observed) or assumed?
  • How many people have this problem? How often?
  • Are people actively looking for solutions?
  • Would they pay to solve it?

Step 2: Explore the Solution Space

Use four lenses to generate breadth:

Lens 1: User-Centered

  • What would the user's ideal experience look like?
  • Where in their workflow is the highest-friction moment?
  • What do they wish they could delegate or automate?

Lens 2: Technology-Enabled

  • What has become possible in the last 2 years that was not before?
  • What existing technology is underutilized for this problem?
  • What would a 10x improvement look like, not just incremental?

Lens 3: Business Model

  • Can the business model itself be the innovation?
  • What if this were free? What if it were 10x more expensive?
  • What adjacent revenue opportunities exist?

Lens 4: Competitive Gap

  • What do existing solutions get wrong?
  • What segment is underserved by current offerings?
  • What would a new entrant build from scratch?

Generate at least 6 distinct concepts. Each should be a different approach, not a variation.

Step 3: Concept Definition

For each promising concept, write a concept card:

### Concept: [Name]

**One-liner**: [What it is in 15 words or less]
**How it works**: [2-3 sentences on the core mechanism]
**Key insight**: [The non-obvious belief that makes this work]
**Target user**: [Specific segment]
**Differentiator**: [Why this wins vs. alternatives]
**Biggest risk**: [What could make this fail]

Step 4: Feasibility Assessment

Score each concept on three dimensions:

ConceptDesirabilityFeasibilityViabilityTotal
[A]H/M/LH/M/LH/M/L
[B]H/M/LH/M/LH/M/L

Desirability: Do people want this? Is there evidence of demand? Feasibility: Can we build this? Do we have the skills, tech, and data? Viability: Does this make business sense? Revenue model, unit economics, market size.

For each Low score, note whether it is fixable or fundamental.

Step 5: Prioritize and Recommend

Rank concepts and provide a recommendation:

## Recommendation

### Top Pick: [Concept Name]
**Why**: [2-3 sentences on why this is the best bet]
**Next step**: [Specific action to validate -- prototype, user test, market test]
**Timeline to validation**: [Days/weeks to get a signal]

### Runner Up: [Concept Name]
**Why**: [Why this is worth keeping alive]
**What would change the ranking**: [Condition that would make this the top pick]

### Parked Ideas
- [Concept]: [Why it is parked and what would revive it]

### Killed Ideas
- [Concept]: [Why it was eliminated]

Output Format

The full ideation output follows this structure:

## Product Ideation: [Topic]
Date: [Date]

### Problem Space
[Problem statement canvas]

### Concepts Generated
[Concept cards for each idea]

### Evaluation Matrix
[Scoring table]

### Recommendation
[Top pick with next steps]

### Open Questions
[Unanswered questions that affect the decision]

Examples

Example 1: New Product

User: "We want to build a product for freelance designers." Response: Start with problem framing -- freelance designers have very different problems (finding clients, managing projects, getting paid, learning new tools). Narrow to a specific pain point, then generate 6-8 concepts ranging from a marketplace to a portfolio builder to an invoicing tool. Assess each against the user's team capabilities.

Example 2: Feature Expansion

User: "Our analytics product needs AI features. What should we build?" Response: Frame the problem from the user's perspective -- what analytics tasks are tedious, error-prone, or require expertise? Generate concepts like anomaly detection, natural language queries, auto-generated insights, predictive forecasting. Assess feasibility based on existing data infrastructure.

Example 3: Problem Exploration

User: "Our users keep asking for X but I'm not sure it's the right solution." Response: Step back from the requested solution. What problem are they trying to solve? Interview the request: when do they need X, what happens without it, what have they tried? Often the underlying need suggests a different, better solution.

Best Practices

  1. Separate divergent and convergent phases. Generate ideas without judging them. Evaluate only after the list is complete.
  2. One concept per idea. Each concept should be a distinct approach, not a feature list. "AI-powered analytics" is too vague; "Anomaly detection that alerts you when metrics deviate from forecasts" is a concept.
  3. Include at least one wild card. Force one concept that feels risky or unconventional. These often reveal assumptions worth challenging.
  4. Test desirability first. Most failed products had feasibility and viability but not desirability. Validate demand before investing in engineering assessment.
  5. Define the smallest testable version. For the top concept, what is the minimum experiment that would give a meaningful signal?
  6. Document what you killed and why. Killed ideas are valuable context for future ideation. Conditions change and previously bad ideas become good ones.
  7. Involve diverse perspectives. If ideating solo, deliberately take opposing viewpoints: the skeptic, the user, the engineer, the business lead.
  8. Set a time constraint. Ideation without a deadline produces diminishing returns. Allocate specific time to each phase.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.