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 kangarooking/system-prompt-skills --skill mobile-adaptationgit clone --depth 1 https://github.com/kangarooking/system-prompt-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/kangarooking/system-prompt-skills/mobile-adaptation)<a href="https://agentmods.dev/skills/kangarooking/system-prompt-skills/mobile-adaptation"><img src="https://agentmods.dev/badge/skills/kangarooking/system-prompt-skills/mobile-adaptation/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/kangarooking/system-prompt-skills/mobile-adaptation"><img src="https://agentmods.dev/badge/skills/kangarooking/system-prompt-skills/mobile-adaptation.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 | $0.00090 | $0.01669 |
| Opus 5 | $0.00045 | $0.00834 |
| Sonnet 5 | $0.00018 | $0.00334 |
| Haiku 4.5 | $0.00009 | $0.00167 |
Grade A, and why
mobile-adaptation 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 11d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
移动端适配
R — 原文 (Reading)
Claude Mobile iOS 基于屏幕尺寸设定响应层级:手机一次显示 6-8 句话,简单问题 1-2 句、操作指南短列表、实质问题 2-3 段、复杂问题不超过 2 屏。集成移动原生工具(日历、提醒、位置、图表)。Claude for Word 禁止管道分隔的 Markdown 表格(任务窗格太窄)。Gemini 实现移动端专项输出压缩。核心模式:屏幕尺寸响应分级、移动原生工具集成、格式限制、答案优先策略。
I — 方法论骨架 (Interpretation)
- 屏幕尺寸感知分级:根据目标设备屏幕容量将回答分为 4 个层级,每个层级有明确的长度上限(句数、段数或屏数)。
- 答案优先策略:移动端用户注意力碎片化,回答结构必须"结论先行、细节后置",禁止铺垫性开场白。
- 格式限制清单:在窄屏场景中禁用特定格式——管道表格、深层嵌套列表、宽代码块、大段引用。
- 移动原生工具集成:利用移动设备独有能力(日历、提醒事项、地理位置、本地时间、图表显示)增强交互。
- 扫描友好结构:使用短列表、加粗关键词、分段标题等格式,使用户在 3-5 秒内定位核心信息。
A1 — 案例分析 (Past Application)
案例: Claude Mobile iOS 的四层响应分级
- 问题: 移动端屏幕一次只能显示 6-8 句话,过长的回答需要大量滚动,严重影响移动场景下的信息获取效率。
- 设计模式的使用: Claude Mobile iOS 将回答分为四个层级并设定严格长度约束——简单问题 1-2 句话直接回答,操作指南用最短列表,实质性问题 2-3 段,复杂问题不超过 2 个屏幕。所有层级均遵循"先给答案、无前言"原则。
- 结论: 基于物理屏幕约束的量化分级比模糊的"尽量简短"指令有效得多,为模型提供了可执行的长度标准。
案例: Claude for Word 的表格格式禁令
- 问题: Word 插件的任务窗格宽度极窄(约 300-400px),管道分隔的 Markdown 表格会溢出或折行混乱。
- 设计模式的使用: Claude for Word 明确禁止在聊天中使用管道分隔的 Markdown 表格("No pipe-delimited markdown tables in chat"),改用结构化列表或自然语言描述替代。
- 结论: 格式限制需要具体到特定的 Markdown 语法元素,泛化的"注意格式"指令无法精准解决窄屏适配问题。
A2 — 触发场景 (Future Trigger) ★
用户在什么情境下需要?
- 设计手机 App 内嵌 AI 助手的系统提示
- 优化现有桌面端系统提示以适配移动端
- 构建跨平台 AI 产品,需针对不同屏幕尺寸差异化输出
- 开发集成移动原生功能(日历、位置)的 AI 助手
语言信号
- "移动端用户"
- "手机屏幕上显示"
- "小屏幕适配"
- "需要集成日历/提醒/定位"
- "App 内的 AI 助手"
与相邻 skill 的区分
- 与 voice-optimization 区别:语音优化关注听觉通道,移动适配关注视觉通道的物理约束;但两者共享简洁优先理念
- 与 citation-system 区别:引用在移动端需要特殊展示(如简化标记、折叠引用),但移动适配不涉及引用格式设计本身
E — 可执行步骤 (Execution)
- 步骤 1:定义屏幕响应分级表 - 完成标准:基于目标设备屏幕容量,定义 4 级响应策略(简单/操作/中等/复杂),每级规定最大句数、段数或屏数,并附具体示例。
- 步骤 2:编写格式限制清单 - 完成标准:列出在移动端禁止使用的格式类型(管道表格、深层嵌套列表、超过 60 字符的代码行等),并为每种禁止格式提供替代方案(表格→结构化列表、嵌套列表→扁平列举)。
- 步骤 3:设计答案优先输出结构 - 完成标准:在系统提示中声明"结论先行"原则,规定回答结构为:直接答案 → 关键细节 → 可选扩展,并禁止铺垫性开场白。
- 步骤 4:规划移动原生工具集成点 - 完成标准:列出可调用的移动原生能力(日历创建、提醒设置、位置查询、时间获取),为每个能力定义触发条件和调用格式。
- 步骤 5:添加扫描友好格式规范 - 完成标准:规定移动端输出的格式增强规则——关键信息加粗、列表项不超过一行、段落间空行分隔、使用 emoji 前缀(如适用)提升视觉扫描效率。
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.
- 11d ago First seen · 74 lines · 90 tokens per session scan A a52724a1d93a
mobile-adaptation is a skill published in the GitHub repository kangarooking/system-prompt-skills (183 stars, last pushed 4mo ago), licensed MIT. It adds 90 tokens to every session and 1,669 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
mobile-onboarding
A visual template showing three mobile-app onboarding screens side by side: a splash screen, a feature introduction, and sign-in.
ios-development
Comprehensive iOS app development skill. Use this skill for ANY iOS-related task: writing Swift/SwiftUI/UIKit code, architecting apps, debugging crashes, setting up navigation, networking, data persistence, animations, performance optimization, App Store submission, Xcode configuration. Trigger when user mentions…
swiftui-expert-skill
Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, macOS-specific APIs, and iOS 26+ Liquid Glass adoption. Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns.
gpt-image-2-prompt-engine
A structured prompt-writing tool for GPT-Image-2, using reusable JSON templates and a four-step workflow. It is designed for controlled commercial images such as product photos, posters, infographics, brand visuals, UI screenshots, and character designs.
expo-app-design
Build beautiful cross-platform mobile apps with Expo Router, NativeWind, and React Native.
expo-deployment
Deploy Expo apps to iOS App Store, Android Play Store, and web.