nw-ab-critique-dimensi…
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
Core UX principles for product owners. Load when evaluating interface designs, writing acceptance criteria with UX requirements, or reviewing wireframes and mockups.
$ npx -y skills add nWave-ai/nWave --skill nw-ux-principles --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/nw-ux-principlesContext preview
The summary Claude sees to decide when to auto-load this skill.
Core UX principles for product owners. Load when evaluating interface designs, writing acceptance criteria with UX requirements, or reviewing wireframes and mockups.
name: nw-ux-principles description: Core UX principles for product owners. Load when evaluating interface designs, writing acceptance criteria with UX requirements, or reviewing wireframes and mockups. user-invocable: false disable-model-invocation: true
Evidence-based UX fundamentals for guiding interface design during requirements gathering. Use to evaluate designs, write better AC, and ask the right questions during discovery.
Apply when reviewing any interface design or writing AC.
| # | Heuristic | Product Owner Action | |---|-----------|---------------------| | 1 | **Visibility of system status** | Require feedback for every action within 100ms. Status indicators for all async ops. | | 2 | **Match system and real world** | Ban internal jargon from UI. Use domain language from user research. | | 3 | **User control and freedom** | Every destructive action needs undo or confirmation. Navigation always allows going back. | | 4 | **Consistency and standards** | Require design system. Audit for inconsistent terminology across features. | | 5 | **Error prevention** | Require input validation, constraints, confirmation for irreversible actions. | | 6 | **Recognition over recall** | Prefer dropdowns over free text when options known. Show recent items. Contextual help. | | 7 | **Flexibility and efficiency** | Require keyboard shortcuts for frequent actions. Support mouse and keyboard workflows. | | 8 | **Aesthetic and minimalist design** | Challenge every UI element: does it serve current task? Remove decorative clutter. | | 9 | **Help with errors** | Error messages state what happened, why, and what to do next. No raw error codes. | | 10 | **Help and documentation** | Require contextual help (tooltips, inline guidance). Documentation by task, not feature. |
For each screen or workflow under review:
1. Is system status visible? (loading, saving, errors, success) 2. Does language match user's vocabulary? 3. Can users undo or escape from any state? 4. Are similar things named and behaving consistently? 5. Are error-prone situations prevented or confirmed? 6. Are options visible rather than requiring recall? 7. Are there shortcuts for frequent actions? 8. Is every visible element necessary for current task? 9. Do error messages explain problem and solution? 10. Is contextual help available?
Score each 0 (no problem) to 4 (usability catastrophe). Fix 3s and 4s before launch.
Six principles explaining why some interfaces feel intuitive.
**Affordances**: What actions an object allows. Digital affordances must be made visible since screens lack physical properties. Button affords clicking; slider affords dragging.
**Signifiers**: Visual indicators communicating where and how to act. Blue underlined word signifies "clickable." Affordances define possibility; signifiers make it discoverable.
**Mapping**: Relationship between controls and effects. Natural mapping uses spatial correspondence (volume slider up = increase). Poor mapping forces memorization.
**Feedback**: Every action must produce perceptible feedback. Silence after action is most common source of confusion. Must be immediate, informative, proportional.
**Constraints**: Limitations guiding correct action. Graying out unavailable options (logical) | red means stop (cultural) | USB plug fits one way (physical).
**Conceptual Models**: Mental image users form about system behavior. When user's model matches system model, interface feels intuitive. Build accurate models through visible structure and consistent behavior.
Time to reach a target depends on distance and size.
Decision time increases with number and complexity of choices.
Working memory holds approximately 7 (plus or minus 2) items.
Resolves tension between simplicity for novices and power for experts.
**Core rule**: Show most important options first. Reveal specialized options on request.
**Two success factors**: 1. Correctly splitting features between initial and secondary views (requires user research) | 2. Making path to advanced features obvious through visible, well-labeled controls
**Design limits**: Most interfaces work best with max two disclosure levels. Three or more causes disorientation.
**Distinct from wizards**: Progressive disclosure uses hierarchical navigation (return to initial view). Wizards use linear sequences.
Four principles (POUR) -- the minimum a product owner must require.
| Principle | Key Requirements | |-----------|-----------------| | **Perceivable** | Text alternatives for images | captions for video | 4.5:1 contrast ratio | text resizable to 200% | | **Operable** | Full keyboard operation | no keyboard traps | adequate time limits | | **Understand
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…