nw-ab-critique-dimensi…
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
Apple LeanUX++ design workflow, journey schema, emotional arc patterns, and CLI UX patterns. Load when transitioning from discovery to visualization or when designing journey artifacts.
$ npx -y skills add nWave-ai/nWave --skill nw-design-methodology --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/nw-design-methodologyContext preview
The summary Claude sees to decide when to auto-load this skill.
Apple LeanUX++ design workflow, journey schema, emotional arc patterns, and CLI UX patterns. Load when transitioning from discovery to visualization or when designing journey artifacts.
name: nw-design-methodology description: Apple LeanUX++ design workflow, journey schema, emotional arc patterns, and CLI UX patterns. Load when transitioning from discovery to visualization or when designing journey artifacts. user-invocable: false disable-model-invocation: true
PHASE 1 PHASE 2 PHASE 3 PHASE 4
Journey Mapping Emotional Design TUI Prototyping Integration Check
| | | |
v v v v
"What's the flow?" "How should it feel?" "What does it look?" "Does it connect?"schema_version: 1
journey:
name: "{Goal Name}"
goal: "{What user is trying to accomplish}"
persona: "{User persona reference}"
emotional_arc:
start: "{Initial emotional state}"
middle: "{Journey emotional state}"
end: "{Final emotional state}"
steps:
- id: 1
name: "{Step Name}"
command: "{CLI command or action}"
tui_mockup: |
+-- Step N: {Name} -----------------------------------------+
| {ASCII representation of CLI output} |
| ${variable} <-- tracked artifact |
+------------------------------------------------------------+
shared_artifacts:
- name: "{artifact_name}"
source: "{single source of truth file}"
displayed_as: "${variable}"
consumers: ["{list of places this appears}"]
emotional_state:
entry: "{How user feels entering step}"
exit: "{How user feels after step}"
integration_checkpoint: |
{What must be validated before proceeding}
failure_modes:
- "{What can go wrong at this step — used by DISTILL for error scenario generation}"
- "{Another failure scenario}"
gherkin: |
Scenario: {Step description}
Given {precondition}
When {action}
Then {observable outcome}
And shared artifact "${variable}" matches source
integration_validation:
shared_artifact_consistency:
- artifact: "{name}"
must_match_across: [1, 2, 3]
failure_message: "{Integration error description}"
changelog:
- date: "{YYYY-MM-DD}"
feature: "{feature-id}"
change: "{What changed in this update}"Start: Anxious/Uncertain | Middle: Focused/Engaged | End: Confident/Satisfied Use when: Complex multi-step operations
Start: Curious | Middle: Exploring | End: Delighted Use when: Learning new features
Start: Frustrated | Middle: Hopeful | End: Relieved Use when: Fixing issues or debugging
Responsive: print something in <100ms | Progress: show for long operations | Transparent: show what is happening | Recoverable: clear errors with suggested fixes
Implement --help on every command | Make help discoverable | Provide contextual suggestions
Three artifact types produced:
1. **Visual Journey** (`journey-{name}-visual.md`): ASCII flow diagram with emotional annotations and TUI mockups per step 2. **Structured Schema** (`journey-{name}.yaml`): Machine-readable journey definition following schema above 3. **Gherkin Scenarios** (`journey-{name}.feature`): Testable acceptance scenarios from each journey step
All artifacts go to `docs/feature/{feature-id}/discuss/`.
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…