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 skills add memi-design/design-skills --skill mobile-craftgit clone --depth 1 https://github.com/memi-design/design-skillsWrote 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/memi-design/design-skills/mobile-craft)<a href="https://agentmods.dev/skills/memi-design/design-skills/mobile-craft"><img src="https://agentmods.dev/badge/skills/memi-design/design-skills/mobile-craft/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/memi-design/design-skills/mobile-craft"><img src="https://agentmods.dev/badge/skills/memi-design/design-skills/mobile-craft.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 | $0.00039 | $0.00298 |
| Opus 5.5 | $0.00016 | $0.00119 |
| Sonnet 5.5 | $0.00008 | $0.00060 |
| Haiku 4.5 | $0.00004 | $0.00030 |
Grade A, and why
mobile-craft 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 1mo 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.
What it actually says
Mobile craft
Read the mobile design guide. Start from the target platforms, device classes, input modes, and critical user journeys. Protect touch-target size, gesture discoverability, safe areas, keyboard behavior, loading and recovery states, and reduced motion. Reuse platform and product primitives before inventing controls. Verify on representative small and large viewports and, when possible, real devices.
Platform routing
- For native SwiftUI work, load
swiftui-design-engineeringfirst. - Add
swiftui-liquid-glassonly when the feature uses iOS 26+ glass APIs. - Add
ios-app-intentsfor Siri, Shortcuts, Spotlight, widgets, or Apple Intelligence surfaces. - Add
swiftdata-persistence,swift-concurrency-safety, orswift-testingonly when the feature crosses those boundaries. - Use
xcode-build-reliabilityandios-performance-debuggingfor build, simulator, trace, and release proof.
Do not translate web breakpoints, hover behavior, or ARIA patterns directly into native iOS code. Preserve the shared product intent, then use Apple platform controls, Dynamic Type, VoiceOver, safe areas, and navigation conventions.
What ships with it
2 files 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.
- 1mo ago First seen · 19 lines · 39 tokens per session scan A 26dbbb7a74a0
mobile-craft is a skill published in the GitHub repository memi-design/design-skills (7 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 298 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
swiftui-native-first
The single most important quality skill. Enforces native SwiftUI components and rejects unnecessary custom code. Use this skill as a reference throughout the entire build process. Include its core rules in every CLAUDE.md. This is what prevents Claude Code from building janky custom UI when a native component exists.
pixel-and-stroke-geometry
How strokes, anti-aliasing, and pixel boundaries actually behave in SwiftUI Canvas and Shape rendering. Covers stroke centering, inset-vs-outset, anti-alias-induced flicker on animating strokes, and 1pt vs 0.5pt strokes on retina displays. Use this skill for any app that draws on a grid or canvas — pattern designers…
polish-and-refinement
Take a working app from "it works" to "it feels right." Covers Figma matching, Liquid Glass, animations, haptics, dark mode, and the subjective quality that separates a good app from a great one. Use this skill after all screens are built and data persistence is working. This is where Figma enters the workflow if you…
figma-to-code
Translate Figma designs into SwiftUI code using the Figma MCP, without exporting PNGs or screenshots. Use this skill when you have Figma frames you want Claude Code to match, when you're in the polish phase and want pixel-level accuracy, or when you're adding a new screen that was designed in Figma first. Requires…
gamified-app
A multi-frame gamified mobile-app prototype — three phone frames on a dark showcase stage. Frame 1: cover / poster, Frame 2: today's quests with XP ribbons and a level bar, Frame 3: quest detail. Vivid quest tiles, level ribbon, bottom tab bar. Use when the brief asks for a "gamified app", "habit tracker", "RPG-style…
mobile-app
A mobile-app screen rendered inside a pixel-accurate iPhone 15 Pro frame on the page. Built by copying the seed assets/template.html and pasting one screen archetype from references/layouts.md. Use when the brief asks for "mobile app", "iOS app", "Android app", "phone screen", or "app UI".