Core UX principles for product owners. Load when evaluating interface designs, writing acceptance criteria with UX requirements, or reviewing wireframes and mockups.
npx skills add https://github.com/nWave-ai/nWave --skill nw-ux-principles
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:
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 |
| Understandable | Readable text | predictable behavior | input assistance and error identification |
| Robust | Valid semantic HTML | ARIA roles where needed | screen reader compatibility |
Use when reviewing designs or writing AC.
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering.
Implement memory-safe programming with RAII, ownership, smart pointers, and resource management across Rust, C++, and C. Use when writing safe systems code, managing resources, or preventing memory bugs.
Python/HTSlib workflows for genomic files. Use when reading, querying, filtering, or writing SAM/BAM/CRAM, VCF/BCF, FASTA/FASTQ, or tabix data with pysam, including pileup, coverage, indexing, and CRAM references.
Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review writing use peer-review.
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.
> Create, build, deploy, and localize declarative agents for M365 Copilot and Teams. USE THIS SKILL for ANY task involving a declarative agent — including localization, scaffolding, editing manifests, adding capabilities, and deploying. Localization requires tokenized manifests and language files that only this skill knows how to produce. "scaffold an agent", "new agent project", "add a capability", "add a plugin", "configure my agent", "deploy my agent", "fix my agent manifest", "edit my agent", "localize my agent", "add localization", "translate my agent", "multi-language agent", "add an API plugin", "add an MCP plugin", "add OAuth to my plugin", "review instructions", "improve instructions", "fix my instructions"
Documentation generation workflow covering API docs, architecture docs, README files, code comments, and technical writing.
Take nwave-ai/nw-ux-principles from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.