Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/kyleve/stuff/building-uinpx skills add kyleve/Stuff --skill building-uigit clone --depth 1 https://github.com/kyleve/StuffWhat 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 | $0.00088 | $0.02489 |
| Opus 5 | $0.00044 | $0.01244 |
| Sonnet 5 | $0.00018 | $0.00498 |
| Haiku 4.5 | $0.00009 | $0.00249 |
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 yesterday.
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 — 209 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.
- 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.
- 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.
- yesterday First seen · 209 lines · 88 tokens per session scan A 364337814943
building-ui is a skill published in the GitHub repository kyleve/Stuff (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 88 tokens to every session and 2,489 once invoked, about $0.0004 per session on Opus 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
remotion-to-hyperframes
Port an existing Remotion (React) composition's source to HyperFrames HTML. Use ONLY on an explicit ask to port/convert/migrate/translate a Remotion source — one-way, Remotion-only. A passing Remotion mention, reference-only code, or "make something like my Remotion video" is a fresh build (/general-video). Unclear →…
apple-design
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading)…
transformers-js
Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in browsers and…
gemini-live-api-dev
Use this skill when building real-time, bidirectional streaming applications with the Gemini Live API. Covers WebSocket-based audio/video/text streaming, voice activity detection (VAD), native audio features, function calling, session management, ephemeral tokens for client-side auth, live translation, and all Live…
advanced-dubbing-studio
Submit audio or video for multilingual dubbing, poll status, and download dubbed audio. Use when the user asks for dubbing, 多语言配音, 视频翻译配音, 译制片, or wants a source clip dubbed into another language.
swiftui-expert-skill
Use when writing, reviewing, or refactoring SwiftUI code for iOS or macOS, including state management and @Observable data flow, view composition and invalidation/performance, lists and ForEach identity, environment usage, localization, animations, Liquid Glass adoption, migrating soft-deprecated APIs, or Instruments…