Back to Brain Lab Skill · UX Expert · ux-expert/
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 Expert: Brain Lab skill for Claude Code

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

journey-empathy-and-prioritization.md
# Journey Maps, Empathy Maps, Prioritization & the Double Diamond

> **Source**: adapted from [tommyjepsen/awesome-ux-skills](https://github.com/tommyjepsen/awesome-ux-skills) (`general-design-review.md`).
> **Load when**: Synthesizing qualitative research into an artifact, sequencing what to fix first, or checking which design-process phase the team is actually in.

---

## Personas, Empathy, Journeys, And Storyboards

Use these artifacts only when they clarify design decisions.

### Personas

Personas should be research-grounded user archetypes, not imagined demographics. Keep:

- Goals
- Frustrations
- Current behaviors
- Context of use
- Design-relevant constraints

Cut details that would not change a product decision.

### Empathy Maps

Use empathy maps to synthesize qualitative research:

- **Says**: user language and quotes
- **Thinks**: beliefs, doubts, assumptions
- **Does**: observable behavior
- **Feels**: emotional state and reason

The most useful insights often come from contradictions, such as users saying they are satisfied while behaving as if they are frustrated.

### Journey Maps

Use journey maps for a specific actor trying to accomplish a specific goal over time. Include:

- Actor
- Scenario and expectation
- Phases
- Actions
- Mindsets
- Emotional highs and lows
- Opportunities

One journey map should represent one point of view. If there are multiple user types, create separate maps.

### Storyboards

Use storyboards when the team needs a visual sequence of a user scenario. Keep them narrow:

- One persona
- One scenario
- One path
- A few panels showing action, context, and emotion

Low fidelity is fine. The story matters more than polished art.

## Prioritization

When deciding what to build or fix first, use a simple 2D matrix. Pick two criteria that reflect project goals, such as:

- User impact vs. effort
- Business value vs. feasibility
- Frequency of use vs. complexity
- Strategic alignment vs. cost

Output:

- **Do first**: high value, low effort or high feasibility
- **Plan carefully**: high value, high effort
- **Quick wins**: lower value, low effort
- **Deprioritize**: low value, high effort

Avoid criteria chosen to justify a favorite solution. The matrix is a decision tool, not proof that the team was already right.

## Design Process Review

Use the Double Diamond as a lightweight process check:

- **Discover**: Do we understand the people, context, and problem space?
- **Define**: Is there a clear user-centered problem statement?
- **Develop**: Have multiple solutions been explored and tested?
- **Deliver**: Is there a plan for build quality, launch readiness, and measurement?

If the team is stuck, identify the phase they are actually in and recommend the next useful artifact: interview guide, research plan, problem statement, prototype, usability test, launch checklist, or measurement plan.