UX Expert
ux-expert/
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
# Persona Craft
> **Source**: adapted from [tommyjepsen/awesome-ux-skills](https://github.com/tommyjepsen/awesome-ux-skills) (`ux-personas.md`).
> **Load when**: Building, improving, or critiquing personas — the research foundation rule, the required/optional field set, the relevance test, the output layout, the quality checklist.
---
Personas are fictional but realistic descriptions of typical or target users. They synthesize research data into a single, memorable character — making abstract user groups feel concrete and actionable for the whole product team.
---
## When You're Asked to Create Personas
Follow this process:
### 1. Establish the research foundation
Ask the user what research they have available. Personas must be grounded in real data — not assumptions. Accepted inputs:
- Interview notes or transcripts
- Survey results
- Field study observations
- Analytics segments
- Existing user segments or market research
If no research exists, flag this clearly: **a persona built without research is a assumption document, not a persona.** Offer to help design a lightweight research plan, or proceed with clearly labeled "proto-personas" that should be validated.
### 2. Identify user clusters
From the research, group users by shared:
- Behaviors and usage patterns
- Goals and motivations
- Frustrations and pain points
- Context of use (when, where, how often, on what device)
If clusters are too similar, merge them. If a cluster seems peripheral to the product, consider dropping it. Aim for **2–4 personas** for most products — enough to cover meaningful variation without diluting focus.
### 3. Build each persona
Each persona should include:
**Required (core to memorability and empathy):**
- **Name** — fictional but believable, not generic ("Anna", not "User A")
- **Photo** — describe one if you can't provide one (stock photo type, not a real person)
- **Age, location, occupation** — enough to anchor context
- **Tag line** — one punchy sentence capturing their essence. Keep it grounded, not clever.
- **Goals** — what are they ultimately trying to achieve? (2–3 items)
- **Frustrations / pain points** — what currently gets in their way? (2–3 items)
- **Behaviors** — how do they currently solve the problem? What tools, workarounds, habits?
- **Context of use** — how would they interact with your product? Required by job or by choice? How often? What device?
- **A quote** — one direct-voice sentence that captures their attitude toward the problem space
**Optional (include only if design-relevant):**
- Experience level with similar products
- Tech comfort level
- Key tasks they need to accomplish in the product
- Decision-making style
**Never include** details that don't affect design decisions. If a field doesn't make any design choice easier, cut it.
### 4. Apply the relevance test
Before finalizing any detail, ask: *"Would this change a design decision?"*
- If yes → include it
- If no → cut it
A persona's favorite coffee order is noise. Their preferred device and time of day for using the product is signal.
---
## Output Format
Present each persona as a structured profile. Use this layout:
```
## [Name], [Age]
[Occupation] · [Location]
> "[Their defining quote]"
**[Tag line]**
### Goals
- ...
- ...
### Frustrations
- ...
- ...
### Behaviors
- ...
- ...
### Context of use
[1–2 sentences on how, when, and where they'd use the product]
```
---
## Common Mistakes to Avoid
| Mistake | Fix |
|---|---|
| Building personas from assumptions, not research | Ground every trait in observed data |
| Too many personas | 2–4 is almost always enough |
| Including irrelevant details | Apply the relevance test to every field |
| Making the tag line too witty | It should be useful, not entertaining |
| Treating personas as a one-time deliverable | Revisit them as you learn more |
| Designing only for the primary persona | Secondary personas represent real edge cases |
---
## Using Personas Beyond the Design Phase
Once created, personas have several ongoing uses:
- **Expert reviews** — walk through a task flow as each persona to surface issues
- **Usability study recruiting** — use persona traits as screening criteria
- **Stakeholder alignment** — give teams a shared vocabulary ("Would Rosa actually do this?")
- **Analytics segmentation** — map real user segments to persona profiles to validate and refine
- **Agency/consultant briefs** — describe your audience concisely without exposing raw data
---
## Persona Quality Checklist
Before delivering personas to the user, verify:
- [ ] Each persona is grounded in real research (or clearly labeled as proto-persona)
- [ ] Name and photo aid memorability
- [ ] Goals and frustrations reflect user research, not product team assumptions
- [ ] Every included detail passes the relevance test
- [ ] Tag line is clear and useful, not just clever
- [ ] Personas feel like distinct characters, not slight variations of each other
- [ ] 2–4 personas total (flag if more are requested and explain the tradeoff)