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 wangjianqi/AppStore --skill 21-app-intents-apple-intelligencegit clone --depth 1 https://github.com/wangjianqi/AppStoreWrote 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/wangjianqi/appstore/21-app-intents-apple-intelligence)<a href="https://agentmods.dev/skills/wangjianqi/appstore/21-app-intents-apple-intelligence"><img src="https://agentmods.dev/badge/skills/wangjianqi/appstore/21-app-intents-apple-intelligence/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/wangjianqi/appstore/21-app-intents-apple-intelligence"><img src="https://agentmods.dev/badge/skills/wangjianqi/appstore/21-app-intents-apple-intelligence.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 | $0.00041 | $0.00907 |
| Opus 5 | $0.00020 | $0.00453 |
| Sonnet 5 | $0.00008 | $0.00181 |
| Haiku 4.5 | $0.00004 | $0.00091 |
Grade A, and why
app-intents-apple-intelligence 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 12d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Intents / Apple Intelligence
App Intents 框架
基本结构
struct SearchExpenseIntent: AppIntent {
static var title: LocalizedStringResource = "搜索记账记录"
static var description = IntentDescription("按关键词搜索记账记录")
@Parameter(title: "关键词")
var keyword: String
func perform() async throws -> some IntentResult {
let results = try await ExpenseService.search(keyword: keyword)
return .result(dialog: "找到 \(results.count) 条记录")
}
}
Intent 类型
- AppIntent:基本意图,执行操作
- AppShortcutsProvider:注册 App 快捷指令
- WidgetConfigurationIntent:Widget 配置意图
- AudioPlaybackIntent:音频播放意图
- ForegroundContinuableIntent:需要前台继续的意图
参数设计
- 使用 @Parameter 标注参数
- 支持 String、Int、Double、Bool、Date、URL 等基本类型
- 支持自定义 Enum(需实现 AppEnum 协议)
- 支持 Entity 查询(需实现 EntityQuery 协议)
App Shortcuts
注册快捷指令
struct ExpenseAppShortcuts: AppShortcutsProvider {
static var appShortcuts: [AppShortcut] {
AppShortcut(
intent: SearchExpenseIntent(),
phrases: [
"在\(.applicationName)中搜索\(\.$keyword)",
"用\(.applicationName)查账"
],
shortTitle: "搜索记账",
systemImageName: "magnifyingglass"
)
}
}
短语设计原则
- 提供多种自然语言表达方式
- 包含 App 名称占位符
- 短语应简洁自然
- 避免过于技术化的表达
Controls API(iOS 18+)
控件类型
- Widget:信息展示型控件
- Toggle:开关型控件
- Button:操作型控件
实现示例
struct QuickExpenseControl: ControlWidget {
var body: some ControlWidgetConfiguration {
StaticControlConfiguration(
kind: "com.example.expense.quick"
) {
ControlWidgetButton(action: QuickExpenseIntent()) {
Label("快速记账", systemImage: "plus.circle.fill")
}
}
}
}
设计要点
- 控件应在控制中心和锁屏可用
- 操作应一步完成,不需要额外输入
- 提供清晰的视觉反馈
Spotlight 索引
CSSearchableItem
import CoreSpotlight
func indexExpense(_ expense: Expense) {
let item = CSSearchableItem(
uniqueIdentifier: expense.id.uuidString,
domainIdentifier: "expenses",
attributeSet: {
let set = CSSearchableItemAttributeSet(contentType: .text)
set.title = expense.category
set.contentDescription = "¥\(expense.amount) - \(expense.note)"
set.keywords = [expense.category, expense.note]
return set
}()
)
CSSearchableIndex.default().indexSearchableItems([item])
}
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.
- 12d ago First seen · 139 lines · 41 tokens per session scan A fbdc9d372b6a
app-intents-apple-intelligence is a skill published in the GitHub repository wangjianqi/AppStore (11 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 907 once invoked, about $0.0002 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
ipaship-audit
Use when auditing iOS/Android app submissions for compliance with Apple App Store Review Guidelines or Google Play Developer Policies. Scan .ipa, .apk, or .zip files against official store policies, generate structured compliance reports, and identify violations with remediation steps.
view-specifications
Guide for writing view specification documents and a starter template for SwiftUI and cross-platform views.
project-structure
Directory layout, file responsibilities, and Xcode integration for meta-loop projects.
analyzing-ios-app-security-with-objection
Runtime iOS app security testing with Objection (Frida): inspect keychain and filesystem data, explore app internals at runtime, and validate/bypass client-side protections during authorized mobile assessments.
ios-simulator-skill
29 production-ready scripts for iOS app testing, building, and automation. Provides semantic UI navigation, build automation, accessibility testing, and simulator lifecycle management. Optimized for AI agents with minimal token output.
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…