agentleFS
PyModelPyModel/designer-skill/skills/ux-designer/SKILL.md

ux-designer

Skill46 starsChanged 47 days agoMITView on GitHub

UX principles for planning or auditing an interface: accessibility (WCAG, EAA), information architecture, microcopy, i18n/RTL, and AI or voice UX.

18 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use product-manager and ui-designer.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • JohnJBorenSkill

    product-manager

    Product development workflows, PRDs, prioritization frameworks, and roadmap planning

    Also in 5 projects that use this

  • nilecuiSkill

    ui-designer

    Extract design systems from reference UI images and generate implementation-ready UI design prompts. Use when users provide UI screenshots/mockups and want to create consistent designs, generate design systems, or build MVP UIs matching reference aesthetics.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 16 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every interface, whatever the task:

    line 21
  2. Distinctive:

    Every interactive element is reachable and operable by keyboard, with a visible focus state and an accessible name and role.

    line 23
  3. Very specific:

    Every action produces a visible response.

    line 25

“Common” is measured: kept by at least 6 in 10 of the 16 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

UX Designer Skill

A UX depth library. Read the reference for the task before designing or reviewing; each number and pattern has one home there, so cite the reference rather than restating values from memory.

Lens

Rank every decision by the UX hierarchy of needs: functional, then reliable, usable, convenient, and only then pleasurable.

  • Calm over busy. Motion, color and density earn their place by aiding understanding.
  • AI as copilot, not autopilot. AI help is optional, labeled, reversible and transparent.
  • Responsible adaptation. Adapt to real user needs and context; never manipulate through opaque personalization.
  • Judgment over polish. Research, correctness and knowing when not to add something are the value.

Baseline

Every interface, whatever the task:

  • Every interactive element is reachable and operable by keyboard, with a visible focus state and an accessible name and role.
  • Color never carries information alone; images have text alternatives.
  • Every action produces a visible response; motion respects prefers-reduced-motion.
  • Errors appear next to their field in plain language.
  • Consent is symmetric: equal-prominence accept and reject, nothing pre-checked, cancellation as easy as sign-up, neutral decline copy.
  • Strings are externalized and layouts survive translation and dir="rtl".

References

TaskReference
Usability heuristics, mental models, anti-pattern audit index01-core-principles
Laws of UX (Fitts, Hick, Miller, Jakob)02-laws-of-ux
WCAG 2.2 AA and EAA accessibility03-accessibility
Visual hierarchy, typography, spacing04-visual-design
Navigation, wayfinding, content structure05-information-architecture
Feedback, states, gestures, modal vs panel vs page06-interaction-design
Forms, validation, input types07-forms-and-inputs
Mobile ergonomics and thumb zones08-mobile-ux
UX writing and microcopy09-ux-writing
User research methods10-user-research
Design system foundations and governance11-design-systems
Presence, live cursors, avatars12a-presence-awareness
Conflicts, sync, sharing, offline12b-conflict-resolution-sync
Canvas zoom, pan, selection13a-canvas-navigation
Canvas objects, layers, performance13b-canvas-objects-performance
AI chat, copilots, agents, generative UI14-ai-ux-patterns
Dark patterns and consent15-ethical-design
Onboarding and activation16-onboarding
Notifications, toasts, attention17-notifications
Dashboards and data visualization18-data-visualization
Search and autocomplete19-search-ux
Emotional design and trust20-emotional-design
Data tables, pagination, bulk actions21-data-tables
Loading, skeletons, optimistic updates22-performance-ux
Internationalization and RTL23-internationalization
Voice, multimodal, cross-device input24-voice-and-multimodal

For an audit, walk the anti-pattern index in 01-core-principles and report each hit with its reference.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.