Skill
Claude
UX Expert
ux-expert/
2 views
0 downloads
UX research and design critique for your agent: research plans, personas, storyboards, heuristic reviews and measured design forensics, with at most three priority actions.
UX research and design critique, the reasoning BEFORE a wireframe and the judgment AFTER a build.
Why use it
- Design decisions defended by taste instead of evidence.
- "Analyze this design" answered with guessed hex codes and invented font sizes.
- A reviewer who recites all ten heuristics and prioritizes nothing.
What it does
research, pick the method that fits the question × product stage, and mine the free evidence first.personas, 2-4 relevance-tested personas, each carrying its provenance (grounded, or clearly labelled proto).storyboard, one persona · one scenario · one path, with an emotion per panel.heuristics, Nielsen H1-H10 applied selectively: critique, or design guidance handed to the designer.review, the combined lens (usability · cognitive load/conversion · craft · a11y · AI-product) with a verdict and max 3 priority actions.analysis, design forensics: measured hexes, type scale, spacing ladder, contrast pairs, composition metrics, tokens.
Benefits
- Numbers, not opinions. Every hex, size and ratio is measured, anything inferred is labelled.
- Findings you can act on today: 3-5 issues, each with its cost, and max 3 priority actions.
- Know who you're designing for before the first wireframe, and whether the build served them after.
- No turf wars. It critiques and routes; it never touches your design system or your code.
Install
Download this skill and copy the ux-expert folder to .claude/skills/ux-expert/ in your project, or to ~/.claude/skills/ux-expert/ to use it in every project. Claude Code finds it on its own; you can also call it with /ux-expert.
Part of the Web Dev Design Pipeline bundle. To get the whole set as a Claude Code plugin: /plugin marketplace add endorphin-ai/hasbrains-agent-kit, then /plugin install web-dev@hasbrains-agent-kit.
Source: endorphin-ai/hasbrains-agent-kit. License: MIT.
Files (29)
Files
-
- ai-product-ux.md
- cognitive-load-and-conversion.md
- design-forensics-scripts.md
- eight-dimensions-and-tokens.md
- example.md
- honest-rendering.md
- journey-empathy-and-prioritization.md
- nielsen-heuristics.md
- persona-craft.md
- research-method-matrix.md
- storyboard-craft.md
- verification-instruments.md
- visual-craft-rules.md
- FORMAT.md
- README.md
- SKILL.md
- VOICE.md
# Cognitive Load, Conversion & Persuasive UX
> **Source**: adapted from [tommyjepsen/awesome-ux-skills](https://github.com/tommyjepsen/awesome-ux-skills) (`general-design-review.md`).
> **Load when**: A page renders correctly but does not convert — the load inventory, the four quick tests (squint / three-second / subtraction / memory), and the persuasion levers.
---
## Cognitive Load And Conversion
Conversion usually fails when users spend mental effort on things that do not help them complete the task.
Look for:
- **Visual clutter**: redundant elements, competing CTAs, decorative content that does not clarify value.
- **Mental model mismatch**: unfamiliar layouts, surprising button behavior, labels users would not use.
- **Unnecessary decisions**: choices the product could recommend, default, infer, or defer.
- **Memory burden**: information users must carry between steps instead of seeing in context.
- **Manual work**: typing, calculating, comparing, or re-entering data the product could handle.
Useful tests:
- **Squint test**: What stands out first? Is it the right thing?
- **Three-second test**: Would a first-time user know what to do?
- **Subtraction test**: If this element disappears, does anything important break?
- **Memory test**: Is the user forced to remember something the UI could show?
Do not remove all friction. Keep friction when it prevents irreversible, costly, or harmful mistakes.
## Persuasive UX
Use persuasion carefully: increase user ability and timely prompting without manipulation.
Review for:
- **Reduction**: Can the task be made shorter or easier?
- **Tunneling**: Is there a guided path when users need one?
- **Tailoring**: Can the experience adapt to the user's context or goal?
- **Suggestion**: Are prompts shown at the right moment, not just anywhere?
- **Self-monitoring**: Can users see progress, status, or improvement?
- **Social visibility**: Would social context help, or would it feel coercive?
- **Reinforcement**: Are desired actions acknowledged in a useful, lightweight way?
Recommend only the persuasive patterns that genuinely fit the behavior the product wants to drive.