Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create detailed user personas based on research and data. Develop realistic representations of target users to guide product decisions and ensure user-centered design.
.claude/skills/nicepkg-user-persona-creation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-17 | ✗→✓ | ▲ Improved | 138% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 154% | 0% |
| case-04 | ✓→✗ | ▼ Worse | 134% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 166% | 0% |
| case-06 | ✓→✓ | = Same ✓ | 96% | 0% |
User personas synthesize research into realistic user profiles that guide design, development, and marketing decisions.
python# Gather data for persona development class PersonaResearch: def conduct_interviews(self, target_sample_size=12): """Interview target users""" interview_guide = { 'demographics': [ 'Age, gender, location', 'Job title, industry, company size', 'Experience level, education', 'Salary range, purchasing power' ], 'goals': [ 'What are you trying to achieve?', 'What's most important to you?', 'What does success look like?' ], 'pain_points': [ 'What frustrates you about current solutions?', 'What takes too long or is complicated?', 'What prevents you from achieving goals?' ], 'behaviors': [ 'How do you currently solve this problem?', 'What tools do you use?', 'How do you learn about new solutions?' ], 'preferences': [ 'How do you prefer to communicate?', 'What communication channels do you use?', 'When are you most responsive?' ] } return { 'sample_size': target_sample_size, 'interview_guide': interview_guide, 'output': 'Interview transcripts, notes, recordings' } def analyze_survey_data(self, survey_data): """Synthesize survey responses""" return { 'demographics': self.segment_demographics(survey_data), 'pain_points': self.extract_pain_points(survey_data), 'goals': self.identify_goals(survey_data), 'needs': self.map_needs(survey_data), 'frequency_distribution': self.calculate_frequencies(survey_data) } def analyze_user_data(self): """Use product analytics data""" return { 'feature_usage': 'Which features are most used', 'user_segments': 'Behavioral groupings', 'conversion_paths': 'How users achieve goals', 'churn_patterns': 'Why users leave', 'usage_frequency': 'Active vs inactive users' } def synthesize_data(self, interview_data, survey_data, usage_data): """Combine all data sources""" return { 'primary_personas': self.identify_primary_personas(interview_data), 'secondary_personas': self.identify_secondary_personas(survey_data), 'persona_groups': self.cluster_similar_users(usage_data), 'confidence_level': 'Based on data sources and sample size' }
yamlUser Persona: Premium SaaS Buyer --- ## Demographics Name: Sarah Chen Age: 34 Location: San Francisco, CA Job Title: VP Product Management Company: Series B SaaS startup (50 employees) Experience: 8 years in product management Education: MBA from Stanford, BS in Computer Science Income: $180K salary + 0.5% equity --- ## Professional Context Industry: B2B SaaS (Project Management) Company Size: 50-200 employees Budget Authority: Can approve purchases up to $50K Buying Process: 60% solo decisions, 40% committee Evaluation Time: 4-6 weeks average --- ## Goals & Motivations Primary Goals: 1. Improve team productivity by 25% 2. Reduce project delivery time by 30% 3. Increase visibility into project status 4. Improve team collaboration across remote locations Success Definition: - Team using tool daily - 20% reduction in status meetings - Faster decision-making - Higher team satisfaction --- ## Pain Points Current Challenges: - Existing tool is slow and outdated - Poor mobile experience - Limited reporting capabilities - Difficult to customize for company needs - Vendor is unresponsive to feature requests Frustrations: - Wasting time in status update meetings - Lack of real-time visibility into project health - Can't easily identify bottlenecks - Integration with other tools is difficult --- ## Behaviors & Preferences Daily Tools: - Slack: Constant communication - Google Workspace: Document collaboration - Jira: Technical work tracking - Spreadsheets: Status reporting (workaround) Work Patterns: - Typically works 8am-6pm Pacific - Checks email every 15 minutes - In meetings 50% of day - Works 20% of time outside office hours Information Gathering: - Reads G2/Capterra reviews: High trust - Asks for peer recommendations: Very influential - Requests demos: Hands-on evaluation - Wants to see case studies: Similar companies Decision Drivers: - ROI and measurable impact: 40% - User adoption potential: 30% - Ease of implementation: 20% - Price: 10% --- ## Technology Comfort Tech Savviness: High (uses 15+ tools daily) Mobile Usage: 40% of work on mobile Prefers: Intuitive UI, minimal training Adoption Speed: Fast (new tools in 1-2 weeks) Integration Importance: Very high --- ## Customer Journey Awareness: Product recommendations from peers Consideration: Reviews, demos, talk to customers Decision: Cost-benefit analysis, team input Onboarding: Expects self-service + minimal support Ongoing: Wants regular feature updates, responsive support --- ## Communication Preferences Prefers: Email and Slack (avoid calls) Response Time: 4-24 hours typical Best Time: Tuesday-Thursday mornings Frequency: Weekly updates during evaluation Format: Data-driven, executive summaries preferred --- ## Key Quotes "I need something that my team will actually use, not something I have to force them to adopt." "Show me the data on time savings, not just promises." "Our tool should work as hard as we do - seamlessly across all our devices and workflows." --- ## Persona Importance Primary Persona: YES (key decision maker) Frequency in User Base: 35% of customers Influence: High (recommends to peers) Revenue Impact: $30K ARR average --- ## Marketing & Sales Strategy Messaging: - Emphasize productivity gains and ROI - Highlight ease of adoption - Show mobile-first experience - Demonstrate integrations Sales Approach: - Provide customer references (similar companies) - Offer flexible demo (self-service + guided) - Focus on time-to-value - Provide ROI calculator Success Metrics: - 50% adoption within 2 months - Net Promoter Score >50 - Upsell to higher tier within 6 months
javascript// Create persona set for comprehensive coverage class PersonaFramework { createPersonaSet(research_data) { return { primary_personas: [ { name: 'Sarah (VP Product)', percentage: '35%', influence: 'High', role: 'Decision maker' }, { name: 'Mike (Team Lead)', percentage: '40%', influence: 'High', role: 'Daily user, key influencer' }, { name: 'Lisa (Admin)', percentage: '25%', influence: 'Medium', role: 'Setup and management' } ], secondary_personas: [ { name: 'John (Executive)', percentage: '10%', influence: 'Medium', role: 'Budget approval' } ], anti_personas: [ { name: 'Enterprise IT Director', reason: 'Not target market, different needs', avoid: 'Marketing to large enterprise buyers' } ] }; } validatePersonas(personas) { return { coverage: personas.reduce((sum, p) => sum + p.percentage, 0), primary_count: personas.filter(p => p.influence === 'High').length, recommendations: [ 'Personas cover 100% of target market', 'Focus on 2-3 primary personas', 'Plan for secondary use cases', 'Define clear anti-personas' ] }; } createPersonaMap(personas) { return { influence_x_axis: 'Low → High', adoption_y_axis: 'Slow → Fast', sarah_vp: { influence: 'High', adoption: 'Fast' }, mike_lead: { influence: 'Very High', adoption: 'Very Fast' }, lisa_admin: { influence: 'Medium', adoption: 'Medium' }, john_executive: { influence: 'Very High', adoption: 'Slow' }, strategy: 'Focus on Mike (influencer), design for Sarah (buyer), support Lisa (user)' }; } }
yamlApplying Personas to Product Decisions: --- ## Feature Prioritization Feature: Offline Mobile Access Sarah's Need: Medium (works with wifi) Mike's Need: Very High (field work, poor connectivity) Lisa's Need: Low (office based) Decision: PRIORITIZE (high-value user needs it) Feature: Advanced Reporting Sarah's Need: Very High (executive visibility) Mike's Need: Low (not his responsibility) Lisa's Need: Medium (setup reporting) Decision: PRIORITIZE (key buyer needs it) Feature: Bulk Import Sarah's Need: Medium (initial setup) Mike's Need: Low (day-to-day use) Lisa's Need: Very High (admin task) Decision: PRIORITIZE (admin enablement) --- ## Journey Mapping Sarah's Evaluation Journey: 1. Becomes aware (peer recommendation) → Email request 2. Reads reviews (G2, Capterra) → Schedule demo 3. Watches demo → Reviews case studies 4. Wants reference → Talks to 2 customers 5. Creates RFP → Evaluates pricing 6. Gets team input → Makes decision → Timeline: 6-8 weeks Mike's Adoption Journey: 1. Learns about tool → Demo from Sarah 2. Gets access → Starts with 1 project 3. Learns through hands-on → Gradually adopts 4. Becomes power user → Recommends to others → Timeline: 4 weeks --- ## Marketing Message by Persona For Sarah (VP Product): Headline: "Increase project delivery speed by 30%" Focus: ROI, team productivity, visibility Channel: LinkedIn, industry publications CTA: "See ROI calculator" For Mike (Team Lead): Headline: "Work faster, stress less" Focus: Ease of use, mobile, collaboration Channel: Twitter, Slack communities CTA: "Try free 30-day trial" For Lisa (Admin): Headline: "Setup in 1 day, not 1 month" Focus: Easy administration, integrations Channel: Admin webinars CTA: "Download admin guide"
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 20,692 | 24,655 | +19% | 1 | 1 | 0% | 3,080 | 5,656 | +84% | 0 | 0 | — |
case-02 | fail→fail | 23,491 | 26,988 | +15% | 1 | 1 | 0% | 3,720 | 7,200 | +94% | 0 | 0 | — |
case-03 | fail→fail | 16,973 | 15,744 | -7% | 1 | 1 | 0% | 2,522 | 5,363 | +113% | 0 | 0 | — |
case-04 | pass→fail | 13,389 | 12,640 | -6% | 1 | 1 | 0% | 2,046 | 4,782 | +134% | 0 | 0 | — |
case-05 | pass→pass | 13,183 | 13,662 | +4% | 1 | 1 | 0% | 1,813 | 4,823 | +166% | 0 | 0 | — |
case-06 | pass→pass | 18,086 | 16,825 | -7% | 1 | 1 | 0% | 2,848 | 5,582 | +96% | 0 | 0 | — |
case-07 | fail→fail | 16,172 | 13,888 | -14% | 1 | 1 | 0% | 2,487 | 5,077 | +104% | 0 | 0 | — |
case-08 | pass→pass | 19,708 | 18,062 | -8% | 1 | 1 | 0% | 3,002 | 5,664 | +89% | 0 | 0 | — |
case-09 | pass→pass | 17,033 | 15,365 | -10% | 1 | 1 | 0% | 2,700 | 5,475 | +103% | 0 | 0 | — |
case-10 | fail→fail | 14,294 | 16,080 | +12% | 1 | 1 | 0% | 2,208 | 5,313 | +141% | 0 | 0 | — |
case-11 | fail→fail | 12,887 | 11,415 | -11% | 1 | 1 | 0% | 2,048 | 4,626 | +126% | 0 | 0 | — |
case-12 | pass→pass | 13,848 | 15,470 | +12% | 1 | 1 | 0% | 2,313 | 5,361 | +132% | 0 | 0 | — |
case-13 | pass→pass | 15,805 | 16,661 | +5% | 1 | 1 | 0% | 2,444 | 5,468 | +124% | 0 | 0 | — |
case-14 | pass→pass | 11,901 | 11,947 | +0% | 1 | 1 | 0% | 1,686 | 4,715 | +180% | 0 | 0 | — |
case-15 | pass→pass | 15,064 | 12,498 | -17% | 1 | 1 | 0% | 2,195 | 4,647 | +112% | 0 | 0 | — |
case-16 | fail→fail | 16,035 | 19,235 | +20% | 1 | 1 | 0% | 2,492 | 5,781 | +132% | 0 | 0 | — |
case-17 | fail→pass | 13,752 | 10,688 | -22% | 1 | 1 | 0% | 1,899 | 4,524 | +138% | 0 | 0 | — |
case-18 | fail→pass | 13,990 | 15,509 | +11% | 1 | 1 | 0% | 2,097 | 5,325 | +154% | 0 | 0 | — |
case-19 | fail→fail | 14,125 | 14,525 | +3% | 1 | 1 | 0% | 2,021 | 5,185 | +157% | 0 | 0 | — |
case-20 | pass→pass | 22,368 | 30,537 | +37% | 1 | 1 | 0% | 3,577 | 7,731 | +116% | 0 | 0 | — |
case-21 | pass→pass | 20,524 | 28,359 | +38% | 1 | 1 | 0% | 3,285 | 7,416 | +126% | 0 | 0 | — |
case-22 | pass→pass | 17,518 | 20,570 | +17% | 1 | 1 | 0% | 3,189 | 6,245 | +96% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +5 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.