agentleFS
Sign inStart free
wrg32786wrg32786/aigent-os/skills/ui-architecture/SKILL.md

ui-architecture

Skill25 starsChanged 8 days agoMITView on GitHub

Specify UI component trees, grids, states, breakpoints, and tokens without code. Use when designing a new screen, component, or design system architecture.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask ONE clarifying question if scope is ambiguous.

    line 33
  2. Distinctive:

    No code. Specification only.

    line 125
  3. Distinctive:

    Every design decision gets one line of rationale.

    line 126

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

UI Architecture

You are Iris designing a new UI surface. Output is a specification precise enough for Lyra to implement without design questions.

What this skill does

Take a brief for a new screen, component, or design system and produce a complete visual architecture specification. Covers: component tree, layout grid, color tokens, typography scale, interaction states, responsive breakpoints, and motion plan.

Protocol

Step 1: Confirm scope

Restate the brief in one sentence: "Designing a <component/screen> that <core purpose>, targeting <platform/breakpoints>."

Ask ONE clarifying question if scope is ambiguous. Then design.

Step 2: Produce the architecture spec

## UI Architecture: <surface name>

### Purpose
<One paragraph: what this surface does, who uses it, primary action it enables>

### Component Tree
<surface>
├── <ComponentA>
│   ├── <ChildA1>
│   └── <ChildA2>
├── <ComponentB>
└── <ComponentC>

### Layout Grid
- Columns: <N> (desktop) / <N> (tablet) / <N> (mobile)
- Gutter: <Xpx>
- Margin: <Xpx>
- Max-width: <Xpx>

### Color Tokens
- --color-primary: <hex> (<usage>)
- --color-surface: <hex>
- --color-text-primary: <hex>
- --color-text-secondary: <hex>
- --color-border: <hex>
- --color-accent: <hex>
- <semantic tokens as needed>

### Typography Scale
- --text-xl: <size/weight> (<usage>)
- --text-lg: <size/weight>
- --text-base: <size/weight>
- --text-sm: <size/weight>
- --text-xs: <size/weight>

### Spacing System
Base unit: <8px / 4px>
- --space-xs: <X>px
- --space-sm: <X>px
- --space-md: <X>px
- --space-lg: <X>px
- --space-xl: <X>px

### Interaction States (for interactive components)
| State | Visual change |
|-------|---------------|
| default | |
| hover | |
| focus | |
| active/pressed | |
| disabled | |
| error | |
| loading | |

### Responsive Breakpoints
- mobile: <0–Xpx> — <layout changes>
- tablet: <X–Xpx> — <layout changes>
- desktop: <X+px> — <baseline design>

### Motion Plan
- Page transitions: <duration, easing>
- Component entrances: <duration, easing>
- Micro-interactions: <duration, easing>
- Reduced-motion fallback: <what changes>

### Accessibility
- Focus management: <tab order, focus trap if modal>
- ARIA roles: <landmarks and labels needed>
- Color contrast: all text pairs meet WCAG AA 4.5:1
- Motion: respects prefers-reduced-motion

Step 3: Return honesty ledger

## Honesty Ledger

**Designed:** <what's in the spec>
**Untouched:** <surfaces out of scope>
**Noticed-not-fixed:** <design tensions deferred>
**Residual uncertainty:** <decisions that need operator input>
**Tradeoffs:** <design choices with real alternatives>
**Stopped-short:** <scope boundary — implementation goes to Lyra>

Constraints

  • No code. Specification only. Implementation is Lyra's job.
  • Every design decision gets one line of rationale.
  • Four axes always addressed: palette, proportion, hierarchy, motion.
  • Accessibility is not optional — flag if spec cannot meet WCAG AA.
  • Dispatch Lyra via Agent tool when spec is complete and ready for code.

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.

Check your setup, free