ui-design
Skill0 starsChanged 25 days agoMITView on GitHub
Apply Master UI Design + Practical UI frameworks to build or audit interface designs (components, layouts, typography, color, forms, buttons, navigation, copywriting). Invoke when user says "use ui-design," "audit this UI," "review the design," or asks for help building/improving an interface, component, or screen. General-purpose (not Pesty-specific; use the pesty-design skill for that).
59 other projects use a version of this.
Adopted by
Most recently taken up by
- leek/agent-skillstheir own version, first seen Nov 8, 2026
- TencentCloudBase/skillstheir own version, first seen Nov 6, 2026
- Freakling/Director-Driven-Developmenttheir own version, first seen Nov 1, 2026
- pumpkit-io/sdlctheir own version, first seen Nov 1, 2026
- skdfndh/better-skill-managertheir own version, first seen Nov 1, 2026
- RHKfullstack/CLAUDE-SKILLStheir own version, first seen Nov 1, 2026
Used with
Projects with it also use harness-design, graphic-design and 10 more.
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.
VictoriakaeySkillharness-design
Use when designing or improving the action space, observation format, tool boundaries, and evaluation signals of an LLM agent. Covers the five layers of harness design: what tools the agent has, what it sees after acting, how each tool is scoped, how behavior is evaluated, and how to iterate when the agent misbehaves. Prevents the most common harness failures — agents that pick wrong tools, ignore critical information, or loop without progress.
Also in 3 projects that use this
travisjneumanSkillgraphic-design
Professional graphic design principles for digital and print media. Use when creating visual designs, choosing color palettes, typography, layouts, or providing design feedback.
Also in 3 projects that use this
soilmassSkilltypography
Typography and kinetic text animations including character reveals, typewriter effects, scramble/decode, wave motion, and animated gradients. Use when creating text reveals, headline animations, number counters, or any text-based motion effects.
Also in 3 projects that use this
MicrosoftSkilltypescript
TypeScript best practices for this monorepo. Use this skill when: (1) writing new TypeScript code, (2) reviewing TypeScript code, (3) working with API responses, fetch calls, or JSON parsing, (4) adding or modifying types and interfaces.
Also in 7 projects that use this
OpenAISkillauth
Authentication integration guidance — Clerk (native Vercel Marketplace), Descope, and Auth0 setup for Next.js applications. Covers middleware auth patterns, sign-in/sign-up flows, and Marketplace provisioning. Use when implementing user authentication.
Also in 3 projects that use this
VercelSkillreact
React renderer for json-render that turns JSON specs into React components. Use when working with @json-render/react, building React UIs from JSON, creating component catalogs, or rendering AI-generated specs.
Also in 4 projects that use this
Other versions59 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 59
- epicenter-md/epicenter★ 4.8ksame name
- EpicenterHQ/epicenter★ 4.8ksame name
- yunshu0909/yunshu_skillshub★ 760same name
- Mindrally/skills★ 275same name
- AnastasiyaW/claude-code-config★ 214same name
- AnastasiyaW/codex-claude-code-config★ 214same name
- mblode/agent-skills★ 189same name
- JayZeeDesign/awesome-claude-skills★ 169same name
- frappe/skills★ 162same name
- TencentCloudBase/skills★ 80same name
49 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
- ai-writing-tellsSkill
- animated-explainerSkill
- ann-handleySkill
- buyer-personasSkill
- desktop-mockupSkill
- linkedin-guest-kitSkill
- mobile-mockupSkill
- pesty-asana-tasksSkill
- pesty-designSkill
- pesty-explainerSkill
- pesty-frontendSkill
- presentation-structureSkill
- problem-solving-processSkill
- pyramid-principleSkill
- scrSkill
- storybrandSkill
- storytellingSkill
- transcript-cleanupSkill
- untangleSkill
- website-launch-impact-reportSkill
- youtube-thumbnailsSkill
- yt-structureSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 50 edited versions we read keep these.
6
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
- Distinctive: line 21
Before designing anything, answer these questions:
- Distinctive: line 32
Read the relevant reference files for the components you are building:
- Distinctive: line 47
Never use color as the only indicator of meaning: add icons, borders, or underlines.
- Very specific: line 59
Read references/scoring.md for the numeric rubric (100 points, 6 categories).
- Distinctive: line 66
Every detail has a logical reason.
- Distinctive: line 97
No placeholder text replacing labels.
- Distinctive: line 113
User asks about a specific component: read the most relevant reference file.
“Common” is measured: kept by at least 6 in 10 of the 50 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.
Files
UI Design Skill
Mode Detection
Determine mode before doing anything else:
- Write mode: User wants to CREATE or BUILD an interface, component, or screen.
- Audit mode: User wants to EVALUATE existing design against these frameworks.
WRITE MODE
Step 1: Establish requirements
Before designing anything, answer these questions:
- What is the interface trying to help the user accomplish?
- Who is the user? (Consider: poor eyesight, low computer literacy, reduced dexterity, cognitive impairments.)
- What screen sizes will this be used on? Start with the smallest.
- Are there brand colors or an existing design system?
Step 2: Start small, build up
Per Practical UI's modular design principle: start with the smallest components (buttons, inputs, avatars) and combine them into larger ones.
Read the relevant reference files for the components you are building:
- Fundamentals:
references/fundamentals.md. Covers interaction cost, cognitive load, WCAG, design systems. - Color:
references/color.md. Covers palette, contrast ratios, system colors, dark mode. - Typography:
references/typography.md. Covers type scale, line height, body size, alignment. - Layout and spacing:
references/layout-spacing.md. Covers spacing scale, grouping, white space, grids. - Forms and buttons:
references/components-forms-buttons.md. Covers labels, validation, button hierarchy, target sizes. - Navigation, cards, tables:
references/components-navigation-cards-tables.md. Covers navigation patterns, card layouts, table row styles. - Copywriting:
references/copywriting.md. Covers conciseness, sentence case, front-loading, descriptive links.
Step 3: Apply key non-negotiables
These rules apply to every interface, every time:
- WCAG 2.1 AA at minimum: 4.5:1 for text, 3:1 for UI components.
- Never use color as the only indicator of meaning: add icons, borders, or underlines.
- All interactive elements: at least 48pt by 48pt.
- Single column form layout with labels on top.
- One primary button per action group.
- Sentence case for all interface text.
- Minimum 18px body text. Line height at least 1.5.
- Left-align body text. Do not center or justify long text.
AUDIT MODE
Read references/scoring.md for the numeric rubric (100 points, 6 categories).
For each failure: state what is broken, cite which rule it violates and where in the reference files it is defined, and suggest the exact fix.
Audit checklist summary
Fundamentals (20 pts)
- Every detail has a logical reason.
- WCAG 2.1 AA contrast met everywhere.
- Color is never the only indicator.
- Common design patterns followed.
- 48pt by 48pt minimum target sizes.
Typography (15 pts)
- Consistent type scale (no more than 4 to 6 sizes).
- Body text at least 18px.
- Line height at least 1.5 for body text.
- Line length 40 to 80 characters.
- Long body text left-aligned.
Color (15 pts)
- Predefined palette with consistent action color.
- Visual hierarchy communicated via saturation and contrast.
- System colors (red/amber/green) for status with icon backup.
- Text not pure black or inaccessible light grey.
- Dark mode: no pure white on pure black.
Layout and hierarchy (20 pts)
- Clear visual hierarchy (not everything equal prominence).
- Consistent spacing scale applied.
- Generous white space (passes The Squint Test).
- Elements aligned to a consistent edge or grid.
- Related elements grouped by proximity.
Components (15 pts)
- At most one primary button per group; hierarchy not color-dependent.
- Button text is verb-noun format.
- Form: single column, labels on top.
- No placeholder text replacing labels.
- Appropriate controls (radio buttons for up to 10 options, steppers for numbers).
Copywriting (15 pts)
- Concise (no filler words, sentences under 20 words).
- Sentence case throughout.
- Front-loaded text.
- Descriptive links and button labels.
- Consistent vocabulary across the interface.
Troubleshooting
User provides a screenshot only: describe what you can observe. Note where you cannot verify contrast ratios without exact color codes and ask for them if the audit depends on it.
User asks about a specific component: read the most relevant reference file. Cite specific rules, not generic advice. If the rule has a number (48pt, 4.5:1, 18px, 1.5 line height), include it.
User pushes back on a rule: explain the rationale. Every rule in these reference files has a reason behind it (usability risk, cognitive load, accessibility, interaction cost). Share that reason, do not just repeat the rule.
User wants to break a rule intentionally: acknowledge the rule, acknowledge the tradeoff, and confirm the user understands what they are giving up (e.g., "using a dropdown here with 12 options increases interaction cost but saves vertical space; confirm that is the acceptable tradeoff").
Key numbers to memorise
These are the most cited specific values across both books:
| Rule | Value | Source |
| Target size minimum | 48pt x 48pt | Practical UI Ch.1, Ch.8; Master UI Buttons |
| Button spacing minimum | 8pt | Practical UI Ch.8 |
| Button gap for safety | 16pt | Practical UI Ch.8 |
| Small text contrast (WCAG AA) | 4.5:1 | Practical UI Ch.3 |
| Large text / UI elements contrast | 3:1 | Practical UI Ch.3 |
| Min body text size | 18px | Practical UI Ch.5 |
| Min line height (body text) | 1.5 | Practical UI Ch.5; Master UI Typography |
| Heading line height | 1 to 1.3 | Master UI Typography |
| Ideal line length | 40 to 80 characters | Practical UI Ch.5 |
| Mobile max line length | 9 words / 50 to 60 chars | Master UI Typography |
| Paragraph line height multiplier | 1.5x font size | Master UI Typography |
| Type scale multiplier (Major Third) | 1.250 | Practical UI Ch.5 |
| Spacing scale | 8, 16, 24, 32, 48, 80pt | Practical UI Ch.4 |
| Min column padding in tables | 16px each side | Master UI Tables |
| Dropdown threshold | 6 to 7 options | Master UI Selection Controls |
| Radio button threshold | Up to 10 options | Practical UI Ch.7 |
| iOS standard title size | 17px | Master UI Typography |
| Hamburger menu element minimum | 44px | Master UI Navigation |
Maintained by Pesty Marketing · Browse the full skill catalog.
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
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.

