mobile-instinct-v2

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Mobile Instinct v2 - Observational Learning

Mobile Instinct v2 - 观察式学习

Cross-session observational learning that extracts patterns from your development workflow over time.

跨会话观察式学习，可从你的长期开发工作流中提取模式。

Overview

概述

V2 instincts observe your sessions and extract patterns that emerge across multiple development activities. Unlike V1's immediate capture, V2 looks for:

Recurring architectural decisions
Problem-solving approaches
Code organization patterns
Testing strategies

V2本能功能观察你的开发会话，并提取在多个开发活动中出现的模式。与V1的即时捕获不同，V2重点关注：

重复出现的架构决策
问题解决方法
代码组织模式
测试策略

Session Analysis

会话分析

At session end, V2 analyzes:

Code changes: What was modified
Problem context: What issue was being solved
Solution approach: How it was resolved
Dependencies: What libraries/techniques were used

在会话结束时，V2会分析：

代码变更：修改了哪些内容
问题背景：正在解决的问题是什么
解决方案：如何解决问题
依赖项：使用了哪些库/技术

Pattern Categories

模式分类

Architectural Patterns

架构模式

Pattern	Detected By	Example
`layer-separation`	Consistent data/ui/domain separation	Repository + ViewModel + Composable
`dependency-injection`	Koin module patterns	factoryOf, viewModel
`navigation-pattern`	Compose Navigation usage	NavHost with routes
`state-management`	MVI/MVVM consistency	StateFlow + sealed classes

模式	检测依据	示例
`layer-separation`	一致的数据/UI/领域分层	Repository + ViewModel + Composable
`dependency-injection`	Koin模块模式	factoryOf, viewModel
`navigation-pattern`	Compose Navigation的使用	带路由的NavHost
`state-management`	MVI/MVVM一致性	StateFlow + 密封类

Problem-Solution Patterns

问题-解决方案模式

Pattern	Detected By	Example
`error-boundary`	Try-catch with UI feedback	Error state in Composable
`loading-state`	isLoading + Content pattern	Box with progress
`pagination`	LazyColumn with Pager	Paging 3 integration
`caching-strategy`	Repository layer caching	Cached repository pattern

模式	检测依据	示例
`error-boundary`	带UI反馈的Try-catch	Composable中的错误状态
`loading-state`	isLoading + 内容模式	带进度条的Box
`pagination`	结合Pager的LazyColumn	Paging 3集成
`caching-strategy`	仓储层缓存	缓存仓储模式

Code Organization Patterns

代码组织模式

Pattern	Detected By	Example
`feature-module`	Self-contained feature folders	feature/auth/ structure
`shared-UI`	Reusable Composables	ui/components/
`test-mirroring`	Test structure matching src	Parallel test folders
`naming-convention`	Consistent naming patterns	XxxViewModel, XxxScreen

模式	检测依据	示例
`feature-module`	独立的功能文件夹	feature/auth/ 结构
`shared-UI`	可复用的Composables	ui/components/
`test-mirroring`	与src匹配的测试结构	平行测试文件夹
`naming-convention`	一致的命名模式	XxxViewModel, XxxScreen

Observation Windows

观察窗口

V2 uses sliding windows for pattern detection:

Window 1 (Current Session):    Immediate patterns
Window 2 (Last 5 Sessions):    Emerging patterns
Window 3 (Last 20 Sessions):   Established patterns
Window 4 (All Time):           Core patterns

V2使用滑动窗口进行模式检测：

Window 1 (Current Session):    Immediate patterns
Window 2 (Last 5 Sessions):    Emerging patterns
Window 3 (Last 20 Sessions):   Established patterns
Window 4 (All Time):           Core patterns

Confidence Evolution

置信度演进

Session 1-3:    Experimental (0.1-0.3)
Session 4-10:   Validating (0.3-0.6)
Session 11-20:  Established (0.6-0.8)
Session 20+:    Best Practice (0.8-1.0)

Session 1-3:    Experimental (0.1-0.3)
Session 4-10:   Validating (0.3-0.6)
Session 11-20:  Established (0.6-0.8)
Session 20+:    Best Practice (0.8-1.0)

Commands

命令

View Observations

查看观察结果

/instinct-status --v2
/instinct-status --observations

Shows:

Recent session observations
Emerging patterns (low confidence)
Established patterns (high confidence)
Pattern clusters by domain

/instinct-status --v2
/instinct-status --observations

显示：

近期会话观察结果
新兴模式（低置信度）
已确立模式（高置信度）
按领域划分的模式集群

Manual Observation

手动观察

/instinct-observe "Used Ktor with retry pattern for API calls"

Manually add an observation for pattern learning.

/instinct-observe "Used Ktor with retry pattern for API calls"

手动添加观察结果用于模式学习。

Integration

集成

V2 instincts are evaluated by:

Session hooks:
```
hooks/instinct-hooks.json
```
Stop event
Pattern extractor:
```
agents/mobile-pattern-extractor.md
```
Pre-compact preservation: Maintains learning during context compression

V2本能功能通过以下组件实现：

会话钩子：
```
hooks/instinct-hooks.json
```
停止事件
模式提取器：
```
agents/mobile-pattern-extractor.md
```
预压缩保留：在上下文压缩过程中保留学习内容

Difference from V1

与V1的区别

Aspect	V1	V2
Trigger	Code write	Session observation
Scope	Single file	Cross-file patterns
Timing	Immediate	End of session
Focus	Code patterns	Architectural patterns

Remember: V2 needs multiple sessions to build confidence. The more you develop, the smarter it gets.

维度	V1	V2
触发条件	代码写入	会话观察
范围	单个文件	跨文件模式
时机	即时	会话结束时
重点	代码模式	架构模式

注意：V2需要多个会话来建立置信度。你的开发活动越多，它就越智能。