skills-library/skills/design-thinking/define.md

Skill: Design Thinking - Define

Description

Transform empathy insights into clear, actionable problem statements that guide solution development.

Input

• empathy_data: User research, pain points, personas from empathize phase (required)
• business_context: Business goals and constraints (optional)
• success_metrics: How to measure if problem is solved (optional)

Problem Framing Techniques

1. How Might We (HMW) Questions

Transform insights into opportunity questions:

Formula:

How might we [ACTION] for [USER] so that [BENEFIT]?

Examples:

• Too broad: "How might we improve the product?"
• Too narrow: "How might we add a red button?"
• Just right: "How might we reduce campaign setup time for marketing managers so they can focus on creative work?"

Best Practices:

• Start with user pain point
• Frame as opportunity, not solution
• Make it actionable and inspiring
• Generate 5-10 HMW variations
• Vote on most impactful

2. User Persona Creation

Template:

## [Name] - [Role/Title]

**Demographics:**
- Role: [Job title/context]
- Experience: [Years/skill level]
- Tech savvy: [Low/Medium/High]

**Context:**
- Frequency: [How often they use product]
- Environment: [Where/when they work]
- Tools: [Current tools in workflow]

**Goals:**
1. [Primary goal]
2. [Secondary goal]
3. [Tertiary goal]

**Frustrations:**
1. [Critical pain point]
2. [High priority pain]
3. [Medium priority pain]

**Quote:**
"[Most revealing user quote]"

**Success looks like:**
- [Specific outcome 1]
- [Specific outcome 2]

3. Journey Mapping

5-Stage Journey:

1. AWARENESS
   Current: How do they discover the problem?
   Pain: What friction exists?

2. CONSIDERATION
   Current: How do they evaluate options?
   Pain: What makes decision hard?

3. ONBOARDING
   Current: First interaction with solution
   Pain: Where do they get stuck?

4. USAGE
   Current: Day-to-day interaction
   Pain: What slows them down?

5. MASTERY
   Current: Advanced use cases
   Pain: What limitations hit them?

For each stage identify:

• User actions
• Pain points
• Emotions
• Opportunities

4. Insight Synthesis

Pattern Recognition:

• What do 3+ users complain about?
• What workarounds exist everywhere?
• What causes universal frustration?
• What do users wish for?

Insight Template:

[USER SEGMENT] needs a way to [USER NEED]
because [UNDERLYING CAUSE]
but currently [OBSTACLE/PAIN POINT]
which makes them feel [EMOTION].

This matters because [BUSINESS IMPACT].

Output Format

{
  "status": "success",
  "problem_statement": {
    "hmw": "How might we reduce campaign setup from 2 hours to 5 minutes for marketing managers so they can focus on creative work instead of manual data entry?",
    "user_need": "Fast, error-free campaign creation",
    "current_obstacle": "Manual multi-step process across 3 tools",
    "why_it_matters": "6 users waste 12+ hours/week on repetitive setup"
  },
  "primary_persona": {
    "name": "Sarah - Marketing Manager",
    "role": "Creates 10+ campaigns/month",
    "tech_level": "medium",
    "goals": ["Speed", "Accuracy", "Consistency"],
    "frustrations": ["2-hour manual setup", "Copy-paste errors", "No templates"],
    "quote": "I spend more time on setup than on actual creative work",
    "success_criteria": "Setup in <5 minutes with zero errors"
  },
  "journey_pain_points": {
    "awareness": "Doesnt know better solution exists",
    "consideration": "Afraid to change familiar workflow",
    "onboarding": "Learning curve interrupts daily work",
    "usage": "Repetitive steps feel wasteful",
    "mastery": "No way to save or reuse configurations"
  },
  "key_insights": [
    "Users value speed over features",
    "Fear of errors drives defensive behavior",
    "Templates would eliminate 80% of manual work"
  ],
  "success_metrics": [
    "Campaign setup time: 2 hours -> 5 minutes",
    "Setup errors: 15% -> 0%",
    "User satisfaction: 3/10 -> 9/10"
  ],
  "next_step": "Generate solutions with /dt ideate"
}

Quality Gates

• Problem statement is specific and measurable
• HMW question is actionable and inspiring
• Persona based on real user data
• Journey map identifies 3+ major pain points
• Success metrics are quantifiable
• Insights synthesized from patterns, not single users

Token Budget

• Max input: 1200 tokens
• Max output: 1800 tokens

Model

• Recommended: sonnet (synthesis and analysis)

Philosophy

"A problem well-stated is a problem half-solved." Clarity in definition prevents wasted effort in ideation.

Keep it simple:

• One clear problem per HMW
• Personas grounded in research
• Measurable success criteria
• User language, not jargon