nw-ab-critique-dimensi…
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
Mom Test questioning toolkit, JTBD analysis, interview conduct, assumption testing framework, and hypothesis design
$ npx -y skills add nWave-ai/nWave --skill nw-interviewing-techniques --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/nw-interviewing-techniquesContext preview
The summary Claude sees to decide when to auto-load this skill.
Mom Test questioning toolkit, JTBD analysis, interview conduct, assumption testing framework, and hypothesis design
name: nw-interviewing-techniques description: Mom Test questioning toolkit, JTBD analysis, interview conduct, assumption testing framework, and hypothesis design user-invocable: false disable-model-invocation: true
Understand if problem is real and worth solving.
Map the job-to-be-done and desired outcomes.
Challenge beliefs and uncover truth.
Distinguish interest from commitment.
Understand impact and urgency.
**Do**: Ask about past specifics | Open, non-directive questions | Seek commitment not praise | Keep informal | 80% listening | Talk about their life first
**Avoid**: Future behavior questions | Leading questions | Accepting compliments as validation | Talking >20% | Mentioning idea before understanding problem | Formal settings
Challenge when: belief without evidence | prediction about future | negative feedback dismissed | skipping to solution | single data point relied on
1. "What evidence supports this?" -- specific past examples 2. "What would disprove this?" -- falsification criteria 3. "What's the opposite assumption?" -- explore alternatives 4. "Who would disagree and why?" -- disconfirming perspectives
Tone: curious and supportive, not confrontational -- goal is truth-seeking.
| Category | Core Question | |----------|--------------| | Value | Will customers want this? | | Usability | Can customers use this? | | Feasibility | Can we build this? | | Viability | Does this work for our business? |
| Factor | Weight | Low (1) | Medium (2) | High (3) | |--------|--------|---------|------------|----------| | Impact if wrong | 3 | Minor adjustment | Significant rework | Solution fails | | Uncertainty | 2 | Have data | Mixed signals | Speculation | | Ease of testing | 1 | Days, low cost | Weeks, moderate | Months, high cost |
**Risk Score** = (Impact x 3) + (Uncertainty x 2) + (Ease x 1)
| Priority | Score | Action | |----------|-------|--------| | Test first | > 12 | Immediate | | Test soon | 8-12 | Schedule | | Test later | < 8 | Backlog |
We believe [doing X] for [user type] will achieve [outcome]. We will know this is TRUE when we see [measurable signal]. We will know this is FALSE when we see [counter-signal or absence of signal].
| Category | Methods | |----------|---------| | Value | Landing page, Fake door, Mom Test interviews | | Usability | Prototype testing, 5-second tests, Task completion | | Feasibility | Spike, Technical prototype, Expert review | | Viability | Lean Canvas review, Stakeholder interviews |
| Result | Criteria | Action | |--------|----------|--------| | Proven | >80% meet success criteria | Proceed | | Disproven | <20% meet criteria | Pivot or kill | | Inconclusive | 20-80% | Increase sample, try different method, segment |
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…