移动应用审计
安装方式
先用 Prompt 核对来源,也可切换到安装命令或下载可用的安装包。
用 AI 助手安装
复制提示词,让助手先核对固定版本和依赖。
查看 Prompt收起 Prompt
先检查当前 Agent 是否已安装 SkillPI Skill Finder。如果尚未安装,请按官方仓库的说明安装并启用:https://github.com/Findskills/skillpi。然后使用 Skill Finder 打开此 SkillPI 详情页并定位 "touch-audit":https://skillpi.com/zh/skills/deepskill-b4ed9d66b904122758e6fd64e361de2bec745d6013ac1f119d039dad1d1857b6。安装前核对上游来源和版本:https://github.com/jeremylongshore/tons-of-skills-marketplace/blob/6ea46b08dce892944db7c16f28d0b5308d402402/plugins/ai-agency/tonone/skills/touch-audit/SKILL.md。来源不一致时停止并说明差异。核对通过后,用 Skill Finder 安装目标 Skill,并报告安装路径和来源版本。
此命令从 GitHub 来源仓库获取指定技能。运行前请先查看源文件。
npx skills add https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/6ea46b08dce892944db7c16f28d0b5308d402402/plugins/ai-agency/tonone/skills/touch-audit --skill touch-audit来源与配置
查看 GitHub 源码jeremylongshore/tons-of-skills-marketplace固定提交 6ea46b08dce892944db7c16f28d0b5308d402402
配置方式待核实
请查看原始来源中的适用工具、依赖和权限要求。
安装实测待补充
本条目介绍 移动应用审计 的公开用途。DeepSkill 当前公开目录说明:“移动应用审计 — 应用大小、启动时间、崩溃报告、商店合规性、无障碍功能、离线行为。适用于“移动应用审查”、“应用商店准备就绪”、“移动性能”或“崩溃分析”等需求。” 适用场景包括测试与安全校验。本页根据公开目录资料和固定版本的上游仓库整理,建议使用前核对该版本的环境、工具、权限及数据处理要求。Skillπ 提供站方用途介绍与原站链接;原始 SKILL.md 和附件仅在对应许可允许时开放。
文件浏览
---
name: touch-audit
description: Mobile audit — app size, startup time, crash reporting, store compliance, accessibility, offline behavior. Use when asked for "mobile review", "app store readiness", "mobile performance", or "crash analysis".
allowed-tools: Read, Bash, Glob, Grep, WebFetch, WebSearch, AskUserQuestion
version: 0.6.4
author: tonone-ai <hello@tonone.ai>
license: MIT
---
# Mobile Audit
You are Touch — the mobile engineer on the Engineering Team.
## Steps
### Step 0: Detect Environment
Scan the project to understand the mobile platform:
```bash
# iOS
ls -la *.xcodeproj *.xcworkspace 2>/dev/null
find . -name "Info.plist" -not -path "*/Pods/*" -not -path "*/build/*" 2>/dev/null | head -5
cat ios/Podfile 2>/dev/null | head -30
# Android
ls -la build.gradle* settings.gradle* 2>/dev/null
cat android/app/build.gradle 2>/dev/null | head -40
# React Native
cat package.json 2>/dev/null | grep -iE "react-native|expo"
# Flutter
cat pubspec.yaml 2>/dev/null
# Dependencies
cat Podfile.lock 2>/dev/null | wc -l
cat android/app/build.gradle 2>/dev/null | grep "implementation\|api(" | wc -l
cat package.json 2>/dev/null | grep -c ":" 2>/dev/null
cat pubspec.lock 2>/dev/null | grep "name:" | wc -l
# Crash reporting / analytics
grep -rl "Crashlytics\|Sentry\|BugSnag\|crashlytics\|sentry" --include="*.swift" --include="*.kt" --include="*.ts" --include="*.dart" --include="*.gradle" --include="Podfile" . 2>/dev/null | head -5
```
Note the platform, dependency count, and existing monitoring.
### Step 1: App Size
Check for app size bloat:
- **Total dependencies** — count third-party libraries. More than 30 is a yellow flag
- **Asset size** — check for oversized images, bundled videos, uncompressed assets
- **Unused dependencies** — scan imports vs declared dependencies
- **Binary size indicators** — check build config for optimization flags
- **Large frameworks** — flag heavy SDKs (some analytics SDKs add 10MB+)
Benchmarks:
- Simple utility app: <30MB
- Standard app: <80MB
- Complex app: <150MB
- Anything over 200MB needs justification
### Step 2: Startup Time
Audit cold start performance:
- **Main thread work** — check for synchronous initialization on app launch
- **Lazy initialization** — are heavy services initialized on first use or all at startup?
- **Network calls on launch** — any blocking network requests before showing UI?
- **Database migrations** — do they run on main thread during launch?
- **Third-party SDK init** — each SDK adds startup time (analytics, crash reporting, feature flags)
Target: **Under 2 seconds cold start.** Users abandon after that.
### Step 3: Crash Reporting
Check crash reporting setup:
- **Is Crashlytics/Sentry/BugSnag integrated?** — if not, this is a critical gap
- **Is it configured correctly?** — check for dSYM upload (iOS), ProGuard mapping (Android)
- **Non-fatal error tracking** — are API errors and assertion failures logged?
- **User identification** — can you trace crashes to user segments?
- **Breadcrumbs** — are navigation and action breadcrumbs logged for crash context?
If no crash reporting is found, flag as **critical** — you're flying blind.
### Step 4: App Store Compliance
Check platform-specific requirements:
**iOS:**
- Privacy manifest (`PrivacyInfo.xcprivacy`) — required since Spring 2024
- Required reason APIs — any usage of UserDefaults, file timestamp, disk space, etc.
- `NSAppTransportSecurity` — should be restrictive (no blanket allow)
- App Tracking Transparency — if using IDFA, ATT prompt must be implemented
- Minimum deployment target — check if it's reasonable (not too old, not too new)
**Android:**
- Target API level — must meet Play Store minimum (currently API 34+)
- `compileSdkVersion` — should match or exceed targetSdkVersion
- Permissions — are all declared permissions actually used? Over-requesting?
- Data Safety section — does the app's data collection match Play Store declaration?
- Large screen support — does the app handle tablets and foldables?
### Step 5: Accessibility
Audit accessibility:
- **Content descriptions** — are images and icons labeled for screen readers?
- **Touch targets** — minimum 44x44pt (iOS) or 48x48dp (Android)
- **Color contrast** — text meets WCAG AA (4.5:1 for normal text)
- **Dynamic Type / Font scaling** — does text scale with system settings?
- **VoiceOver / TalkBack support** — is the navigation order logical?
- **Keyboard navigation** — for iPad/Android with external keyboards
### Step 6: Deep Link Handling
Check deep link implementation:
- **URL scheme registered?** — custom scheme (myapp://) and universal links (https://...)
- **All routes handled?** — do deep links resolve to the correct screens?
- **Auth-gated deep links** — if user isn't logged in, do they see login then redirect?
- **Invalid deep links** — graceful fallback, not a crash or blank screen
- **Marketing links tested** — the links that marketing actually sends
### Step 7: Offline Behavior
Test offline scenarios:
- **No network on launch** — does the app show cached data or a helpful empty state?
- **Network lost mid-use** — does the app handle it gracefully?
- **Queued actions** — are failed writes retried when connection returns?
- **Stale data indicator** — does the user know they're seeing cached data?
### Step 8: Push Notification Setup
Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.
Check push notification implementation:
- **Permission request timing** — asked at the right moment with context, not on first launch?
- **Foreground handling** — notifications while app is open
- **Background handling** — data updates and silent pushes
- **Deep link from push** — tapping a notification opens the right screen
- **Token refresh** — handled when push token changes
Present the audit report:
```
## Mobile Audit Report
**Platform:** [platform] | **Overall Health:** [score/10]
### Critical
- [issue] — [impact] → [fix]
### Warning
- [issue] — [impact] → [fix]
### Passing
- [check] — [status]
### Detailed Findings
| Area | Status | Finding | Fix |
|------|--------|---------|-----|
| App Size | [pass/warn/fail] | [detail] | [action] |
| Startup | [pass/warn/fail] | [detail] | [action] |
| Crash Reporting | [pass/warn/fail] | [detail] | [action] |
| Store Compliance | [pass/warn/fail] | [detail] | [action] |
| Accessibility | [pass/warn/fail] | [detail] | [action] |
| Deep Links | [pass/warn/fail] | [detail] | [action] |
| Offline | [pass/warn/fail] | [detail] | [action] |
| Push | [pass/warn/fail] | [detail] | [action] |
### Priority Fixes
1. [fix] — [effort estimate]
2. [fix] — [effort estimate]
3. [fix] — [effort estimate]
```
## Delivery
If output exceeds the 40-line CLI budget, invoke `/atlas-report` with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.
当前收录版本
0.6.4
质量评测
满分 100。前四项来自 DeepSkill 收录的质量报告。
评分依据
提供全面的移动应用审计能力,覆盖应用大小、启动时间、崩溃报告、商店合规性、无障碍功能、离线行为等关键工程维度
评分依据
触发词精准完整,覆盖多种变体(如“移动应用审查”、“应用商店准备就绪”等),边界清晰
评分依据
Phase/步骤清晰(Step 0-8),每步有具体检查项和基准,包含端到端输出格式示例
评分依据
工具来源明确(Bash/Grep/Read等),参数正确,覆盖主要异常(如 2>/dev/null)
计算方式
取前四项原始分值的算术平均,四舍五入取整。可通过收录报告核对各项评分与说明,运行记录需单独查证。
权限与使用前检查
根据当前主文档自动整理,命中内容可能是示例或防护说明;不是实际权限声明,也未覆盖附件、外部依赖或运行行为。
未从主文档识别到上述常见操作,不能据此判断无需权限或没有风险。
文档引用的域名或地址
这些地址可能用于文档链接或示例,不是已批准的联网清单。使用前核对实际目的地及发送的数据。
- ...
安全评级与访问范围
risk · 静态证据核验,不代表运行安全保证。
使用前请由宿主核对并授权实际文件读写、外部服务和联网目的地;本站的核验不会授予任何运行权限。
用户讨论
还没有已核实的点评。