Borrowing it
Nothing to install: this file belongs to kyleve/Stuff. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kyleve/Stuff/main/.agents/skills/building-ui/SKILL.mdgit clone --depth 1 https://github.com/kyleve/StuffWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kyleve/stuff/building-ui)<a href="https://agentmods.dev/skills/kyleve/stuff/building-ui"><img src="https://agentmods.dev/badge/skills/kyleve/stuff/building-ui/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kyleve/stuff/building-ui"><img src="https://agentmods.dev/badge/skills/kyleve/stuff/building-ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00088 | $0.03812 |
| Opus 5.5 | $0.00035 | $0.01525 |
| Sonnet 5.5 | $0.00018 | $0.00762 |
| Haiku 4.5 | $0.00009 | $0.00381 |
Grade A, and why
building-ui scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building UI
Build repository UI through the existing model, design-system, and rendering
seams. Treat this skill as the repository-specific authority when generic
SwiftUI guidance conflicts with it. For example, use a Broadway stylesheet,
not a generic constants enum. Use swiftui-pro alongside this skill for
current SwiftUI API, performance, and platform guidance.
Start from the existing shape
- Read the root
AGENTS.md, then everyAGENTS.mdthat scopes the files being changed. Local files retain module-specific product, dependency, and lifetime invariants. - Inspect the feature's existing views, view models, reusable components, Broadway root, stylesheet, preview fixtures, and snapshot declarations before designing another path. Check supported themes and their local surface rules before choosing materials. For Where, follow the theme rules.
- Extend an existing view with a mode or shared subview when two surfaces express the same concept. Keep screen-specific registration and rendering declarations beside the represented screen. In-app examples and theme previews must reuse the production presentation component. If embedding needs a different size or interaction policy, add that input at the shared boundary.
- Identify the narrowest layer that owns the behavior before editing UI.
Keep views presentational
- Put persistence, domain rules, detection, aggregation, cache policy, and side
effects in Core/services. Put observable mirrors, lifecycle orchestration,
and intent methods in a view model. Let a
Viewrender state and route intents. - Extract an
@Observablemodel or focused child type when a view begins to own system logic, an internal state machine, or unrelated behavioral areas. - Model mutually dependent UI values as one enum or named value so invalid combinations cannot be represented.
- Bind directly to observable state. For a derived binding, expose a computed
get/set property on the model and bind to it. Do not build
Binding(get:set:)in a view. - Keep previews and tests on the production data flow. Inject a protocol fake or production-shaped fixture instead of adding DEBUG state or a parallel refresh path to product code.
- Scope presentation-driven work to actual visibility. Key tasks by every identity-relevant input and let cancellation return before changing durable presentation state, emitting haptics, or publishing late UI updates.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed · +8 lines ac5e1aa873bd
- 6d ago Changed · +14 lines 11a822362da0
- 9d ago Changed · +24 lines 67b6c59f9459
- 22d ago Changed · +17 lines 16b346a43505
- 1mo ago Changed · +45 lines 288459529821
- 2mo ago First seen · 209 lines · 88 tokens per session scan A 364337814943
building-ui is a skill published in the GitHub repository kyleve/Stuff (4 stars, last pushed today), licensed Apache-2.0. It adds 88 tokens to every session and 3,812 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
display-glasses-with-jetpack-compose-glimmer
Provides guidelines for developing projected Android XR apps for display glasses using the Jetpack Compose Glimmer UI toolkit. Covers Glimmer design principles, workflows, and interaction models for the glasses form factor. Use this skill to build an Android XR Augmented Experience app with Jetpack Compose Glimmer.…
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
expo-design-system
Build and maintain a design system inside an Expo app - a reusable theme of design tokens (color, spacing, typography, radius, shadow, motion), reusable component structure with variant/size/state prop conventions, and rules for when to extract a repeated view into a shared component. Use when creating or organizing…
flutter-build-responsive-layout
Use LayoutBuilder, MediaQuery, or Expanded/Flexible to create a layout that adapts to different screen sizes. Use when you need the UI to look good on both mobile and tablet/desktop form factors.
omh-apple-design
This is an OMH apple-design workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
axiom-audit-liquid-glass
Use when the user mentions Liquid Glass review, iOS 26 UI updates, toolbar improvements, or visual effect migration.