nw-ab-critique-dimensi…
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
Opportunity Solution Trees, opportunity scoring, Lean Canvas, JTBD job mapping, and technique selection guide
$ npx -y skills add nWave-ai/nWave --skill nw-opportunity-mapping --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/nw-opportunity-mappingContext preview
The summary Claude sees to decide when to auto-load this skill.
Opportunity Solution Trees, opportunity scoring, Lean Canvas, JTBD job mapping, and technique selection guide
name: nw-opportunity-mapping description: Opportunity Solution Trees, opportunity scoring, Lean Canvas, JTBD job mapping, and technique selection guide user-invocable: false disable-model-invocation: true
Connects desired outcomes to opportunities to solution ideas:
Desired Outcome
|
+-- Opportunity 1 (score)
| +-- Solution Idea A
| +-- Solution Idea B
|
+-- Opportunity 2 (score)
| +-- Solution Idea C
|
+-- Opportunity 3 (score)
+-- Solution Idea D
+-- Solution Idea E1. Define desired outcome from customer research 2. Map opportunities from interview insights (min 5 distinct) 3. Score each using Opportunity Algorithm 4. Generate solution ideas for top 2-3 5. Seek real diversity in solutions (avoid variations of same idea)
**Formula**: Score = Importance + Max(0, Importance - Satisfaction) Importance: 1-10 | Satisfaction: 1-10 | Max score: 20
| Score | Meaning | Action | |-------|---------|--------| | >8 | High importance, satisfaction gap -- underserved | Pursue | | 5-8 | Moderate importance or partially served | Evaluate | | <5 | Low importance or well-served | Deprioritize |
Process: gather importance + satisfaction from 5+ interviews, calculate per opportunity, rank, select top 2-3.
| Step | Goal | Outcome Format | |------|------|---------------| | Define | Determine what needs doing | Minimize time to identify [object] | | Locate | Find inputs/information | Minimize time to gather [resources] | | Prepare | Ready inputs for use | Minimize likelihood of missing [requirements] | | Confirm | Verify readiness | Minimize likelihood of incorrect [categorization] | | Execute | Perform core task | Minimize time from [start] to [completion] | | Monitor | Track progress | Minimize uncertainty about [status] | | Modify | Adjust if needed | Minimize effort to correct [issues] | | Conclude | Complete the job | Minimize time from [completion] to [result] |
Outcome statement format: **[Direction] + [Metric] + [Object] + [Clarifier]** Example: "Minimize the time it takes to identify which project budget a new expense should be allocated to"
One-page business model for Phase 4 viability validation.
1. **Problem**: Top 3 problems (Phase 1 validated) | 2. **Customer Segments**: by JTBD 3. **UVP**: single clear message | 4. **Solution**: top 3 features for top problems 5. **Channels**: path to customers (Phase 4 validated) | 6. **Revenue Streams**: monetization 7. **Cost Structure**: key costs | 8. **Key Metrics**: activity metrics 9. **Unfair Advantage**: not easily copied
| Risk | Question | Validation | |------|----------|-----------| | Value | Will customers want this? | Interviews, fake doors | | Usability | Can customers use this? | Prototype testing, task completion | | Feasibility | Can we build this? | Spikes, expert review | | Viability | Business model works? | Lean Canvas, stakeholder review |
| Goal | Techniques | |------|-----------| | Validate problem | Mom Test, Job Mapping | | Understand needs | Outcome Statements, Opportunity Mapping | | Prioritize opportunities | OST, Opportunity Algorithm | | Generate solutions | Ideation with OST constraints | | Validate solution value | Hypothesis Testing, Prototypes | | Test usability | Prototype testing, Task completion | | Assess feasibility | 4 Risks, Spikes | | Structure business model | Lean Canvas | | Continuous learning | Weekly customer touchpoints |
AI agents that guide you from idea to working code, with human judgment at every gate. nWave runs inside Claude Code. It breaks feature delivery into seven waves (discover, diverge, discuss, design, devops, distill, deliver).
Repo: nWave-ai/nWave
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
Review dimensions for acceptance test quality - happy path bias, GWT compliance, business language purity, coverage completeness, walking skeleton…
Detailed 5-phase workflow for creating agents - from requirements analysis through validation and iterative refinement
5-layer testing approach for agent validation including adversarial testing, security validation, and prompt injection resistance
Architectural style selection decision matrices, trade-off analysis, structural enforcement rules, and combination patterns. Load when choosing or evaluating…