iron-edge 1.0.0

package/squads/squad-product/tasks/run-client-product-workshop.md

@@ -0,0 +1,179 @@
+---
+task: run-client-product-workshop
+responsavel: "@ps-client-product-manager"
+responsavel_type: Agent
+atomic_layer: Task
+elicit: false
+
+Entrada:
+  - campo: context
+    tipo: object
+    origem: "workflow ou manual"
+    obrigatorio: true
+
+Saida:
+  - campo: resultado
+    tipo: document
+    destino: "stakeholders"
+
+Checklist:
+  - "[ ] Validar inputs e pre-condicoes"
+  - "[ ] Executar steps conforme documentado"
+  - "[ ] Verificar criterios de qualidade"
+  - "[ ] Gerar output no formato especificado"
+---
+
+# Run Client Product Workshop
+
+## Metadata
+- **Agent:** ps-client-product-manager (Proxy)
+- **Complexity:** Medium-High
+- **Estimated Time:** 2-3 hours (workshop) + 2-3 hours (prep)
+- **Produces:** Workshop outputs, aligned priorities, action plan, relationship strengthening
+
+## Purpose
+Facilitar workshop colaborativo com cliente para alinhar prioridades, explorar oportunidades ou resolver problemas de produto. Workshops constroem alinhamento e ownership compartilhado.
+
+## Steps
+
+### Step 1: Define Workshop Type & Objective
+**Workshop Types:**
+| Type | When to Use | Duration | Participants |
+|------|-----------|----------|-------------|
+| Kickoff | Start of engagement | 3-4h | Full teams both sides |
+| Priority Alignment | Quarterly planning | 2-3h | PMs + stakeholders |
+| Problem Solving | Specific challenge | 2h | Relevant experts |
+| Discovery | New opportunity | 2-3h | Product trio + client |
+| Retrospective | End of phase/quarter | 1.5-2h | Full team |
+| Roadmap | Strategic direction | 3-4h | PMs + leadership |
+
+**Workshop Objective (ONE clear objective):**
+```
+By the end of this workshop, we will have:
+[specific, tangible output]
+
+This matters because:
+[why this output is needed now]
+```
+
+### Step 2: Pre-Workshop Preparation
+**Logistics:**
+- [ ] Date/time confirmed with all participants
+- [ ] Remote tool set up (Miro/FigJam/Notion)
+- [ ] Pre-read material sent 48h in advance
+- [ ] Agenda shared with participants
+- [ ] Roles assigned (facilitator, note-taker, timekeeper)
+
+**Pre-Work for Participants:**
+```
+Please prepare the following before the workshop:
+1. [Specific preparation item — e.g., "Top 3 priorities for next quarter"]
+2. [Specific preparation item — e.g., "Biggest product concern"]
+3. [Specific preparation item — e.g., "One user story from recent feedback"]
+
+This should take approximately 15-20 minutes.
+```
+
+### Step 3: Workshop Facilitation
+**Universal Structure:**
+
+**Opening (10 min):**
+- Welcome and introductions (if new participants)
+- Workshop objective and agenda
+- Ground rules: "All ideas welcome, park debates, timebox strictly"
+- Icebreaker (1 min each): "One word to describe how you feel about [product topic]"
+
+**Core Exercise Block (60-120 min):**
+*Select 2-4 exercises based on workshop type*
+
+**Exercise Library:**
+| Exercise | Purpose | Duration | Best For |
+|---------|---------|----------|---------|
+| Hopes & Fears | Surface expectations | 15 min | Kickoff |
+| Rose/Thorn/Bud | Current state assessment | 20 min | Retro, Alignment |
+| Dot Voting | Prioritize options | 10 min | Any decision point |
+| How Might We | Problem reframing | 20 min | Problem Solving |
+| 2x2 Matrix | Evaluate trade-offs | 20 min | Priority Alignment |
+| Crazy 8s | Rapid solution generation | 15 min | Discovery |
+| Impact/Effort Map | Prioritize actions | 20 min | Roadmap, Planning |
+| RACI Matrix | Clarify responsibilities | 20 min | Kickoff, Alignment |
+| MoSCoW | Scope definition | 20 min | Roadmap, MVP |
+| Assumption Mapping | Risk identification | 20 min | Discovery |
+
+**Synthesis (20-30 min):**
+- Summarize key outputs
+- Confirm decisions made
+- Identify open questions
+- Define next steps
+
+**Closing (10 min):**
+- Each participant: "One thing I am taking away from today"
+- Thank participants
+- Preview next steps and follow-up timeline
+
+### Step 4: Facilitation Best Practices
+**Remote Workshop Tips:**
+- Use video ON (builds connection)
+- Breakout rooms for small group work (3-4 people)
+- Timer visible on screen
+- Use sticky notes/cards in Miro/FigJam (individual before group)
+- Call on quiet participants by name
+- Take breaks every 60 min
+
+**Managing Difficult Dynamics:**
+| Situation | Response |
+|-----------|---------|
+| One person dominates | "Thank you [name]. Let us hear from others. [Name], what is your view?" |
+| Client disagrees with recommendation | "Help me understand your perspective. What are you seeing?" |
+| Conversation goes off track | "Great point. Let me park that for later. Back to our objective..." |
+| No one participates | Switch to individual writing first, then share |
+| Conflict between client stakeholders | "Both perspectives are valid. Let us capture both and evaluate with data." |
+
+### Step 5: Post-Workshop Deliverables
+**Within 24h:**
+```
+WORKSHOP SUMMARY
+─────────────────
+Date: [date]
+Participants: [list]
+Objective: [what we set out to achieve]
+
+KEY DECISIONS:
+1. [Decision + rationale]
+2. [Decision + rationale]
+
+PRIORITIES ALIGNED:
+1. [Priority — agreed by consensus]
+2. [Priority]
+3. [Priority]
+
+OPEN QUESTIONS:
+1. [Question — owner to resolve by date]
+
+ACTION ITEMS:
+| Action | Owner | Deadline |
+|--------|-------|----------|
+| [action] | [name] | [date] |
+
+NEXT STEPS:
+[What happens after this workshop]
+```
+
+### Step 6: Measure Workshop Effectiveness
+**Quick Post-Workshop Survey (2 questions):**
+1. "How valuable was this workshop?" (1-5)
+2. "What would make it better?"
+
+**Workshop Success Criteria:**
+- [ ] Objective achieved (tangible output produced)
+- [ ] All key participants engaged
+- [ ] Decisions documented
+- [ ] Action items assigned
+- [ ] Follow-up sent within 24h
+- [ ] Satisfaction score >= 4/5
+
+## Output Artifacts
+- `workshop-plan-[topic].md` | `workshop-summary-[date].md` | `workshop-actions.md` | `workshop-feedback.md`
+
+## Quality Criteria
+- Clear objective stated upfront | Pre-work sent 48h before | Exercises matched to objective | All participants contributed | Decisions and actions documented | Follow-up within 24h | Feedback collected

package/squads/squad-product/tasks/run-funnel-drop-off-analysis.md

@@ -0,0 +1,147 @@
+---
+task: run-funnel-drop-off-analysis
+responsavel: "@ps-product-analyst"
+responsavel_type: Agent
+atomic_layer: Task
+elicit: false
+
+Entrada:
+  - campo: context
+    tipo: object
+    origem: "workflow ou manual"
+    obrigatorio: true
+
+Saida:
+  - campo: resultado
+    tipo: document
+    destino: "stakeholders"
+
+Checklist:
+  - "[ ] Validar inputs e pre-condicoes"
+  - "[ ] Executar steps conforme documentado"
+  - "[ ] Verificar criterios de qualidade"
+  - "[ ] Gerar output no formato especificado"
+---
+
+# Run Funnel Drop-off Analysis
+
+## Metadata
+- **Agent:** ps-product-analyst (Delta)
+- **Complexity:** Medium
+- **Estimated Time:** 2-3 hours
+- **Produces:** Funnel analysis report, drop-off diagnosis, conversion optimization recommendations
+
+## Purpose
+Analisar funis de conversao para identificar onde e por que usuarios abandonam. Cada ponto de drop-off e uma oportunidade de melhoria de conversao.
+
+## Steps
+
+### Step 1: Define Funnel
+**Funnel Specification:**
+```
+Funnel Name: [e.g., Signup-to-Activation, Purchase, Onboarding]
+Business Goal: [what success looks like at the end]
+Date Range: [analysis period]
+Segment: [all users or specific segment]
+Platform: [web/mobile/all]
+```
+
+**Steps Definition:**
+| Step | Event | Description | Time Limit |
+|------|-------|-------------|-----------|
+| 1 | [event_name] | [user action] | — |
+| 2 | [event_name] | [user action] | within [N hours/days] of step 1 |
+| 3 | [event_name] | [user action] | within [N hours/days] of step 2 |
+| ... | | | |
+| Final | [event_name] | [conversion event] | within [N hours/days] |
+
+### Step 2: Calculate Conversion Rates
+**Step-by-Step Conversion:**
+```
+Step 1: [event] .............. [N users] (100%)
+    ↓ [X% convert, Y% drop]
+Step 2: [event] .............. [N users] ([%])
+    ↓ [X% convert, Y% drop]
+Step 3: [event] .............. [N users] ([%])
+    ↓ [X% convert, Y% drop]
+Step N: [event] .............. [N users] ([%])
+
+Overall Conversion: [%]
+Biggest Drop-off: Step [X] → Step [Y] ([Z% lost])
+```
+
+**Benchmark Comparison:**
+| Step Transition | Current Rate | Industry Benchmark | Gap |
+|----------------|-------------|-------------------|------|
+| Step 1 → 2 | [%] | [%] | [pp] |
+| Step 2 → 3 | [%] | [%] | [pp] |
+| Overall | [%] | [%] | [pp] |
+
+### Step 3: Diagnose Drop-off Points
+**For each major drop-off (>20% loss), investigate:**
+
+**Quantitative Diagnosis:**
+| Factor | Analysis | Finding |
+|--------|----------|---------|
+| Time spent at step | [avg time before dropping] | [too fast = confusion, too slow = friction] |
+| Device/browser | [conversion by device] | [mobile vs desktop gap?] |
+| Traffic source | [conversion by acquisition channel] | [quality issue?] |
+| User segment | [conversion by persona/plan] | [segment-specific issue?] |
+| Day/time | [conversion by day of week] | [timing pattern?] |
+| Error rate | [errors at this step] | [technical issue?] |
+| Page load time | [performance at this step] | [speed issue?] |
+
+**Qualitative Diagnosis:**
+| Source | Method | What to Look For |
+|--------|--------|-----------------|
+| Session recordings | Watch 20+ drop-off sessions | Confusion, rage clicks, back button |
+| Heatmaps | Click/scroll maps at drop-off page | Missed CTAs, dead clicks, scroll depth |
+| User interviews | Ask users who dropped off | "Why did you stop?" |
+| Support tickets | Filter by related complaints | Common friction themes |
+| Exit surveys | Micro-survey at drop-off point | Stated reasons for leaving |
+
+### Step 4: Root Cause Classification
+**Per Drop-off Point:**
+| Root Cause Category | Indicators | Example |
+|--------------------|-----------|---------|
+| **UX Friction** | Confusion, wrong clicks, back button | Unclear form labels |
+| **Value Gap** | Quick exit, no engagement | Users do not see why to continue |
+| **Trust Issue** | Hesitation at payment/data entry | No security indicators |
+| **Technical** | Errors, slow load, broken elements | Payment gateway timeout |
+| **Motivation** | Gradual disengagement | Too many steps, fatigue |
+| **External** | Drop-off correlates with external factor | Competitor promo, seasonality |
+
+### Step 5: Quantify Opportunity
+**Revenue/User Impact per Drop-off Fix:**
+```
+Drop-off Point: Step [X] → Step [Y]
+Current conversion: [%]
+Users lost per month: [N]
+If improved by [X percentage points]:
+  Additional conversions/month: [N]
+  Revenue impact: [$ estimate]
+  Annual impact: [$ estimate]
+```
+
+**Priority Matrix:**
+| Drop-off | Users Lost | Revenue Impact | Fix Complexity | Priority |
+|---------|-----------|---------------|---------------|----------|
+| [point 1] | [N/month] | [$] | Low/Med/High | P1/P2/P3 |
+| [point 2] | [N/month] | [$] | Low/Med/High | P1/P2/P3 |
+
+### Step 6: Recommendations
+**Per Priority Drop-off:**
+```
+DROP-OFF: Step [X] → Step [Y] ([Z% loss])
+ROOT CAUSE: [category + specific diagnosis]
+RECOMMENDATION: [specific change to implement]
+EXPECTED LIFT: [% improvement estimate]
+VALIDATION: [how to test — A/B test, prototype test, etc.]
+EFFORT: [T-shirt size]
+```
+
+## Output Artifacts
+- `funnel-analysis-[name].md` | `drop-off-diagnosis.md` | `conversion-opportunities.md` | `funnel-optimization-recommendations.md`
+
+## Quality Criteria
+- Funnel steps clearly defined with events | Conversion rates calculated per step | Biggest drop-offs diagnosed with multi-source evidence | Root causes classified | Revenue impact quantified | Recommendations specific with expected lift | Min 20 session recordings reviewed per drop-off

package/squads/squad-product/tasks/run-pmf-assessment.md

@@ -0,0 +1,67 @@
+---
+task: run-pmf-assessment
+responsavel: "@ps-product-strategist"
+responsavel_type: Agent
+atomic_layer: Task
+elicit: false
+
+Entrada:
+  - campo: context
+    tipo: object
+    origem: "workflow ou manual"
+    obrigatorio: true
+
+Saida:
+  - campo: resultado
+    tipo: document
+    destino: "stakeholders"
+
+Checklist:
+  - "[ ] Validar inputs e pre-condicoes"
+  - "[ ] Executar steps conforme documentado"
+  - "[ ] Verificar criterios de qualidade"
+  - "[ ] Gerar output no formato especificado"
+---
+
+# Run Product-Market Fit Assessment
+
+## Metadata
+- **Agent:** ps-product-strategist (Charter)
+- **Complexity:** High
+- **Estimated Time:** 1-2 weeks
+- **Produces:** PMF assessment report, score, action plan
+
+## Purpose
+Avaliar Product-Market Fit usando Sean Ellis Test e metricas complementares.
+
+## Steps
+
+### Step 1: Sean Ellis Test
+**Question:** "How would you feel if you could no longer use [product]?"
+Very disappointed | Somewhat disappointed | Not disappointed | N/A
+
+**PMF Threshold:** >40% "Very Disappointed" = PMF achieved
+**Methodology:** Active users (last 2 weeks), min 40 responses, post-activation timing
+
+**Scoring:** >40% PMF ACHIEVED | 25-40% APPROACHING | 15-25% NOT YET | <15% FAR FROM PMF
+
+### Step 2: Complementary Indicators
+Organic Growth Rate (>30% strong signal) | DAU/MAU (>0.2 good) | NRR (>100% expansion) | Viral k (>0.5 growth) | Time to Value (decreasing = improving) | Word of Mouth referral %
+
+### Step 3: Segment Analysis
+PMF varies by segment - identify which segment has strongest PMF and double down.
+
+### Step 4: Very Disappointed User Analysis
+Profile them: demographics, behavior, use case, features used, how they found us, benefit described.
+This profile = ideal customer. Build more for them.
+
+### Step 5: Action Plan by Score
+**>40%:** Document formula, identify ICP, focus growth, protect core value
+**25-40%:** Narrow focus to highest-PMF segment, reduce activation friction
+**<25%:** Return to discovery, interview Not Disappointed users, consider pivot
+
+## Output Artifacts
+- `pmf-assessment-[date].md` | `pmf-survey-results.md` | `pmf-action-plan.md`
+
+## Quality Criteria
+- Min 40 survey responses from active users | Segment analysis performed | Action plan specific to score band

package/squads/squad-product/tasks/run-product-operations-audit.md

@@ -0,0 +1,140 @@
+---
+task: run-product-operations-audit
+responsavel: "@ps-product-ops-specialist"
+responsavel_type: Agent
+atomic_layer: Task
+elicit: false
+
+Entrada:
+  - campo: context
+    tipo: object
+    origem: "workflow ou manual"
+    obrigatorio: true
+
+Saida:
+  - campo: resultado
+    tipo: document
+    destino: "stakeholders"
+
+Checklist:
+  - "[ ] Validar inputs e pre-condicoes"
+  - "[ ] Executar steps conforme documentado"
+  - "[ ] Verificar criterios de qualidade"
+  - "[ ] Gerar output no formato especificado"
+---
+
+# Run Product Operations Audit
+
+## Metadata
+- **Agent:** ps-product-ops-specialist (Mosaic)
+- **Complexity:** Medium-High
+- **Estimated Time:** 4-6 hours
+- **Produces:** Ops audit report, maturity assessment, improvement roadmap, efficiency metrics
+
+## Purpose
+Auditar maturidade e eficiencia das operacoes de produto para identificar gargalos, ineficiencias e oportunidades de melhoria sistematica.
+
+## Steps
+
+### Step 1: Ops Maturity Assessment
+**Product Ops Maturity Model (5 levels):**
+
+| Level | Name | Characteristics |
+|-------|------|----------------|
+| 1 | Ad-hoc | No standard processes, tribal knowledge, reactive |
+| 2 | Defined | Core processes documented, basic tools, some consistency |
+| 3 | Managed | Processes followed consistently, metrics tracked, templates used |
+| 4 | Optimized | Data-driven improvement, cross-client learning, automation |
+| 5 | Strategic | Ops as competitive advantage, predictive, self-improving |
+
+**Assessment per Dimension:**
+| Dimension | Score (1-5) | Evidence | Gap to Next Level |
+|-----------|------------|---------|-------------------|
+| Process Documentation | | [what exists] | [what is missing] |
+| Tool Utilization | | [tools and usage] | [underused/gaps] |
+| Template Library | | [templates available] | [missing templates] |
+| Metric Standardization | | [consistency across clients] | [inconsistencies] |
+| Knowledge Management | | [KB state] | [gaps/findability] |
+| Onboarding Efficiency | | [time to productive] | [bottlenecks] |
+| Cross-Client Learning | | [sharing mechanisms] | [silos] |
+| Automation | | [automated vs manual] | [automation opportunities] |
+
+### Step 2: Process Efficiency Audit
+**Per Core Process:**
+| Process | Cycle Time | Quality | Bottleneck | Waste |
+|---------|-----------|---------|-----------|-------|
+| Sprint planning | [hours] | [defects/rework] | [where it slows] | [unnecessary steps] |
+| Feature prioritization | [days] | [decision reversals] | [waiting for...] | [redundant reviews] |
+| Client request intake | [hours to response] | [reframe rate] | [approval delays] | [duplicate logging] |
+| Release process | [hours] | [rollback rate] | [testing bottleneck] | [manual steps] |
+| Research synthesis | [days] | [actionability] | [data gathering] | [unused findings] |
+| QBR preparation | [hours] | [client satisfaction] | [data collection] | [custom formatting] |
+
+**Waste Identification (Lean):**
+| Waste Type | Examples Found | Impact |
+|-----------|--------------|--------|
+| Waiting | [approval delays, dependency waits] | [hours/sprint wasted] |
+| Overprocessing | [unnecessary reviews, extra formatting] | [hours/sprint wasted] |
+| Defects | [rework, miscommunication] | [hours/sprint wasted] |
+| Motion | [context switching, tool hopping] | [hours/sprint wasted] |
+| Inventory | [unused docs, stale backlogs] | [maintenance overhead] |
+| Overproduction | [reports no one reads, unused templates] | [time wasted creating] |
+| Transport | [handoffs between tools, copy-paste] | [error risk + time] |
+
+### Step 3: Team Efficiency Metrics
+**Operational KPIs:**
+| KPI | Current | Target | Gap |
+|-----|---------|--------|-----|
+| Time to onboard new client | [days] | [target days] | [delta] |
+| Time to onboard new PM | [days] | [target days] | [delta] |
+| Sprint planning time | [hours] | [target hours] | [delta] |
+| Report generation time | [hours] | [target hours] | [delta] |
+| Information retrieval time | [minutes] | <2 min | [delta] |
+| Process adherence rate | [%] | >90% | [delta] |
+| Template usage rate | [%] | >80% | [delta] |
+| Tool utilization score | [%] | >70% | [delta] |
+
+### Step 4: Improvement Prioritization
+**Improvement Opportunities:**
+| Opportunity | Impact (1-5) | Effort (1-5) | Priority Score | Category |
+|------------|-------------|-------------|---------------|----------|
+| [improvement 1] | [score] | [score] | Impact/Effort | Quick Win/Strategic/Deprioritize |
+| [improvement 2] | [score] | [score] | Impact/Effort | Quick Win/Strategic/Deprioritize |
+
+**Priority Matrix:**
+```
+HIGH IMPACT │ STRATEGIC    │ QUICK WINS
+            │ (Plan these) │ (Do these first!)
+            │              │
+────────────┼──────────────┼─────────────
+            │ DEPRIORITIZE │ FILL-INS
+LOW IMPACT  │ (Skip)       │ (If time allows)
+            │              │
+            LOW EFFORT      HIGH EFFORT
+```
+
+### Step 5: Improvement Roadmap
+**Phased Improvement Plan:**
+| Phase | Timeline | Improvements | Expected Impact |
+|-------|----------|-------------|----------------|
+| Quick Wins | Next 2 weeks | [list of low-effort, high-impact] | [metric improvement] |
+| Foundation | Month 1-2 | [process and template improvements] | [metric improvement] |
+| Optimization | Month 3-4 | [automation, advanced tooling] | [metric improvement] |
+| Strategic | Quarter 2+ | [cross-client learning, predictive ops] | [metric improvement] |
+
+### Step 6: Audit Report
+**Report Structure:**
+1. Executive Summary (current maturity + top 3 recommendations)
+2. Maturity Assessment (per dimension with evidence)
+3. Process Efficiency (per process with metrics)
+4. Waste Analysis (Lean waste types found)
+5. Improvement Opportunities (prioritized)
+6. Improvement Roadmap (phased plan)
+7. Success Metrics (how to measure improvement)
+8. Next Audit Date (typically quarterly)
+
+## Output Artifacts
+- `ops-audit-report-[date].md` | `maturity-assessment.md` | `improvement-roadmap.md` | `efficiency-metrics.md`
+
+## Quality Criteria
+- All dimensions assessed with evidence | Process cycle times measured | Waste types identified | Improvements prioritized by impact/effort | Roadmap phased and realistic | Success metrics defined | Next audit scheduled

package/squads/squad-product/tasks/run-prototype-usability-test.md

@@ -0,0 +1,149 @@
+---
+task: run-prototype-usability-test
+responsavel: "@ps-discovery-lead"
+responsavel_type: Agent
+atomic_layer: Task
+elicit: false
+
+Entrada:
+  - campo: context
+    tipo: object
+    origem: "workflow ou manual"
+    obrigatorio: true
+
+Saida:
+  - campo: resultado
+    tipo: document
+    destino: "stakeholders"
+
+Checklist:
+  - "[ ] Validar inputs e pre-condicoes"
+  - "[ ] Executar steps conforme documentado"
+  - "[ ] Verificar criterios de qualidade"
+  - "[ ] Gerar output no formato especificado"
+---
+
+# Run Prototype Usability Test
+
+## Metadata
+- **Agent:** ps-discovery-lead (Quorum)
+- **Complexity:** Medium
+- **Estimated Time:** 1-2 hours per session + 2h synthesis
+- **Produces:** Usability test results, task success rates, UX findings, design recommendations
+
+## Purpose
+Testar prototipos com usuarios reais para validar se a solucao proposta funciona antes de investir em desenvolvimento. Testar cedo e barato, falhar rapido.
+
+## Steps
+
+### Step 1: Define Test Objectives
+**What are we testing?**
+- Prototype type: Low-fi (wireframe) | Mid-fi (clickable) | High-fi (pixel-perfect)
+- Core assumption: "Users can [complete task] using [this design] in [acceptable time]"
+
+**Task List (3-5 tasks per test):**
+| # | Task | Success Criteria | Max Time | Critical? |
+|---|------|-----------------|----------|-----------|
+| 1 | [realistic scenario] | [what defines success] | [minutes] | Yes/No |
+| 2 | [realistic scenario] | [what defines success] | [minutes] | Yes/No |
+| 3 | [realistic scenario] | [what defines success] | [minutes] | Yes/No |
+
+**Task Writing Rules:**
+- Frame as realistic scenarios, not instructions ("You want to..." not "Click on...")
+- Do not reveal the expected path
+- Include context and motivation
+
+### Step 2: Recruit Participants (5-8)
+**Nielsen Norman Rule:** 5 users find ~85% of usability problems.
+- Match target persona
+- Mix of experience levels
+- No internal team members (they know too much)
+- Screen for recent relevant behavior
+
+### Step 3: Prepare Test Protocol
+**Session Structure (45-60 min):**
+
+**Intro (5 min):**
+- "We are testing the design, not you"
+- "There are no wrong answers"
+- "Think aloud — tell me what you are thinking as you go"
+- "I cannot help you during the task, but that is okay"
+
+**Warm-up (5 min):**
+- Background questions (role, relevant experience)
+- Current behavior related to tasks
+
+**Tasks (30-40 min):**
+- Read scenario aloud, let participant attempt
+- **During task observe:** Path taken, hesitations, errors, backtracking, comments
+- **After each task:** "How easy or difficult was that? (1-5)" + "What were you expecting?"
+- **Between tasks:** Brief debrief, then next scenario
+
+**Post-test (10 min):**
+- SUS (System Usability Scale) or SEQ (Single Ease Question)
+- "What was the most confusing part?"
+- "What would you change?"
+- "Would you use this? Why or why not?"
+
+### Step 4: Conduct Sessions & Capture Data
+**Per Session, Record:**
+| Metric | Task 1 | Task 2 | Task 3 |
+|--------|--------|--------|--------|
+| Completed? (Y/N) | | | |
+| Time to complete | | | |
+| Errors made | | | |
+| Assists needed | | | |
+| Ease rating (1-5) | | | |
+| Path taken | | | |
+
+**Observation Notes:**
+- Exact moments of confusion (timestamp if recording)
+- Verbatim quotes during think-aloud
+- Facial expressions / body language
+- Where they looked first (if eye-tracking or observation)
+
+### Step 5: Analyze Results
+**Quantitative Summary:**
+| Task | Success Rate | Avg Time | Avg Ease | Error Rate |
+|------|-------------|----------|----------|-----------|
+| [task 1] | [X/N] [%] | [min:sec] | [1-5] | [errors/session] |
+| [task 2] | [X/N] [%] | [min:sec] | [1-5] | [errors/session] |
+
+**Benchmarks:**
+- Task success rate target: >= 80%
+- Ease rating target: >= 3.5/5
+- SUS score target: >= 68 (above average)
+
+**Qualitative Findings (prioritized):**
+| Finding | Severity | Frequency | Recommendation |
+|---------|----------|-----------|----------------|
+| [usability issue] | Critical/Major/Minor/Cosmetic | [N/5 users] | [specific fix] |
+
+**Severity Scale (Nielsen):**
+- **Critical:** User cannot complete task, no workaround
+- **Major:** User struggles significantly, may find workaround
+- **Minor:** User notices issue but completes task
+- **Cosmetic:** Minor annoyance, does not affect task completion
+
+### Step 6: Generate Design Recommendations
+**Per Finding:**
+```
+Issue: [specific usability problem]
+Severity: [Critical | Major | Minor | Cosmetic]
+Evidence: [N users affected, specific behaviors observed]
+Root Cause: [why this happens — layout? labeling? flow?]
+Recommendation: [specific design change]
+Before/After: [describe current vs. proposed]
+Confidence: [High — clear pattern | Medium — some evidence | Low — single observation]
+```
+
+**Decision Framework:**
+- Critical + Major issues: MUST fix before development
+- Minor issues: FIX in design iteration
+- Cosmetic: LOG for polish phase
+
+## Output Artifacts
+- `usability-test-plan-[feature].md` | `usability-test-results.md` | `finding-cards/[id].md` | `design-recommendations.md`
+
+## Quality Criteria
+- 5-8 participants tested | Tasks realistic and scenario-based | Success rates calculated per task | All findings severity-rated | Recommendations specific (not "make it better") | Critical issues flagged for mandatory fix