continuous-learning-v2

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Continuous Learning v2 - Instinct-Based Architecture

持续学习v2 - 基于本能的架构

An advanced learning system that turns your Claude Code sessions into reusable knowledge through atomic "instincts" - small learned behaviors with confidence scoring.

这是一个高级学习系统，通过原子化的「本能」——带有置信度评分的小型习得行为，将你的Claude Code会话转化为可复用的知识。

What's New in v2

v2版本新特性

Feature	v1	v2
Observation	Stop hook (session end)	PreToolUse/PostToolUse (100% reliable)
Analysis	Main context	Background agent (Haiku)
Granularity	Full skills	Atomic "instincts"
Confidence	None	0.3-0.9 weighted
Evolution	Direct to skill	Instincts → cluster → skill/command/agent
Sharing	None	Export/import instincts

特性	v1版本	v2版本
观测方式	停止钩子（会话结束时触发）	PreToolUse/PostToolUse钩子（100%可靠）
分析方式	主上下文分析	后台Agent（Haiku）分析
颗粒度	完整技能	原子化「本能」
置信度	无	0.3-0.9加权评分
演化路径	直接生成技能	本能→聚类→技能/命令/Agent
共享功能	无	导出/导入本能

The Instinct Model

本能模型

An instinct is a small learned behavior:

yaml

---
id: prefer-functional-style
trigger: "when writing new functions"
confidence: 0.7
domain: "code-style"
source: "session-observation"
---

本能是一种小型的习得行为：

yaml

---
id: prefer-functional-style
trigger: "when writing new functions"
confidence: 0.7
domain: "code-style"
source: "session-observation"
---

Prefer Functional Style

Action

Use functional patterns over classes when appropriate.

Evidence

Observed 5 instances of functional pattern preference
User corrected class-based approach to functional on 2025-01-15


**Properties:**
- **Atomic** — one trigger, one action
- **Confidence-weighted** — 0.3 = tentative, 0.9 = near certain
- **Domain-tagged** — code-style, testing, git, debugging, workflow, etc.
- **Evidence-backed** — tracks what observations created it

Observed 5 instances of functional pattern preference
User corrected class-based approach to functional on 2025-01-15


**特性：**
- **原子化** — 一个触发条件，一个对应行为
- **带置信度加权** — 0.3=暂定，0.9=近乎确定
- **领域标记** — 代码风格、测试、Git、调试、工作流等
- **有证据支撑** — 记录生成该本能的观测来源

How It Works

工作流程

Session Activity
      │
      │ Hooks capture prompts + tool use (100% reliable)
      ▼
┌─────────────────────────────────────────┐
│         observations.jsonl              │
│   (prompts, tool calls, outcomes)       │
└─────────────────────────────────────────┘
      │
      │ Observer agent reads (background, Haiku)
      ▼
┌─────────────────────────────────────────┐
│          PATTERN DETECTION              │
│   • User corrections → instinct         │
│   • Error resolutions → instinct        │
│   • Repeated workflows → instinct       │
└─────────────────────────────────────────┘
      │
      │ Creates/updates
      ▼
┌─────────────────────────────────────────┐
│         instincts/personal/             │
│   • prefer-functional.md (0.7)          │
│   • always-test-first.md (0.9)          │
│   • use-zod-validation.md (0.6)         │
└─────────────────────────────────────────┘
      │
      │ /evolve clusters
      ▼
┌─────────────────────────────────────────┐
│              evolved/                   │
│   • commands/new-feature.md             │
│   • skills/testing-workflow.md          │
│   • agents/refactor-specialist.md       │
└─────────────────────────────────────────┘

会话活动
      │
      │ 钩子捕获提示词 + 工具使用记录（100%可靠）
      ▼
┌─────────────────────────────────────────┐
│         observations.jsonl              │
│   (提示词、工具调用、执行结果)           │
└─────────────────────────────────────────┘
      │
      │ 观测Agent读取记录（后台运行，基于Haiku模型）
      ▼
┌─────────────────────────────────────────┐
│          模式检测                       │
│   • 用户修正操作 → 生成本能              │
│   • 错误解决过程 → 生成本能              │
│   • 重复工作流 → 生成本能                │
└─────────────────────────────────────────┘
      │
      │ 创建/更新
      ▼
┌─────────────────────────────────────────┐
│         instincts/personal/             │
│   • prefer-functional.md (0.7)          │
│   • always-test-first.md (0.9)          │
│   • use-zod-validation.md (0.6)         │
└─────────────────────────────────────────┘
      │
      │ /evolve 聚类
      ▼
┌─────────────────────────────────────────┐
│              evolved/                   │
│   • commands/new-feature.md             │
│   • skills/testing-workflow.md          │
│   • agents/refactor-specialist.md       │
└─────────────────────────────────────────┘

Quick Start

快速开始

1. Enable Observation Hooks

1. 启用观测钩子

Add to your

~/.claude/settings.json

If installed as a plugin (recommended):

json

{
  "hooks": {
    "PreToolUse": [{
      "matcher": "*",
      "hooks": [{
        "type": "command",
        "command": "${CLAUDE_PLUGIN_ROOT}/skills/continuous-learning-v2/hooks/observe.sh pre"
      }]
    }],
    "PostToolUse": [{
      "matcher": "*",
      "hooks": [{
        "type": "command",
        "command": "${CLAUDE_PLUGIN_ROOT}/skills/continuous-learning-v2/hooks/observe.sh post"
      }]
    }]
  }
}

If installed manually to

~/.claude/skills

json

{
  "hooks": {
    "PreToolUse": [{
      "matcher": "*",
      "hooks": [{
        "type": "command",
        "command": "~/.claude/skills/continuous-learning-v2/hooks/observe.sh pre"
      }]
    }],
    "PostToolUse": [{
      "matcher": "*",
      "hooks": [{
        "type": "command",
        "command": "~/.claude/skills/continuous-learning-v2/hooks/observe.sh post"
      }]
    }]
  }
}

添加到你的

~/.claude/settings.json

文件中。

以插件形式安装（推荐）：

json

{
  "hooks": {
    "PreToolUse": [{
      "matcher": "*",
      "hooks": [{
        "type": "command",
        "command": "${CLAUDE_PLUGIN_ROOT}/skills/continuous-learning-v2/hooks/observe.sh pre"
      }]
    }],
    "PostToolUse": [{
      "matcher": "*",
      "hooks": [{
        "type": "command",
        "command": "${CLAUDE_PLUGIN_ROOT}/skills/continuous-learning-v2/hooks/observe.sh post"
      }]
    }]
  }
}

手动安装到
~/.claude/skills
目录：

json

{
  "hooks": {
    "PreToolUse": [{
      "matcher": "*",
      "hooks": [{
        "type": "command",
        "command": "~/.claude/skills/continuous-learning-v2/hooks/observe.sh pre"
      }]
    }],
    "PostToolUse": [{
      "matcher": "*",
      "hooks": [{
        "type": "command",
        "command": "~/.claude/skills/continuous-learning-v2/hooks/observe.sh post"
      }]
    }]
  }
}

2. Initialize Directory Structure

2. 初始化目录结构

The Python CLI will create these automatically, but you can also create them manually:

bash

mkdir -p ~/.claude/homunculus/{instincts/{personal,inherited},evolved/{agents,skills,commands}}
touch ~/.claude/homunculus/observations.jsonl

Python命令行工具会自动创建这些目录，你也可以手动创建：

bash

mkdir -p ~/.claude/homunculus/{instincts/{personal,inherited},evolved/{agents,skills,commands}}
touch ~/.claude/homunculus/observations.jsonl

3. Use the Instinct Commands

3. 使用本能相关命令

bash

/instinct-status     # Show learned instincts with confidence scores
/evolve              # Cluster related instincts into skills/commands
/instinct-export     # Export instincts for sharing
/instinct-import     # Import instincts from others

bash

/instinct-status     # 查看已学习的本能及其置信度评分
/evolve              # 将相关本能聚类为技能/命令
/instinct-export     # 导出本能以便共享
/instinct-import     # 导入他人的本能

Commands

命令列表

Command	Description
`/instinct-status`	Show all learned instincts with confidence
`/evolve`	Cluster related instincts into skills/commands
`/instinct-export`	Export instincts for sharing
`/instinct-import <file>`	Import instincts from others

命令	描述
`/instinct-status`	显示所有已学习的本能及其置信度
`/evolve`	将相关本能聚类为技能/命令
`/instinct-export`	导出本能用于共享
`/instinct-import <file>`	从文件导入他人的本能

Configuration

配置说明

Edit

config.json

json

{
  "version": "2.0",
  "observation": {
    "enabled": true,
    "store_path": "~/.claude/homunculus/observations.jsonl",
    "max_file_size_mb": 10,
    "archive_after_days": 7
  },
  "instincts": {
    "personal_path": "~/.claude/homunculus/instincts/personal/",
    "inherited_path": "~/.claude/homunculus/instincts/inherited/",
    "min_confidence": 0.3,
    "auto_approve_threshold": 0.7,
    "confidence_decay_rate": 0.05
  },
  "observer": {
    "enabled": true,
    "model": "haiku",
    "run_interval_minutes": 5,
    "patterns_to_detect": [
      "user_corrections",
      "error_resolutions",
      "repeated_workflows",
      "tool_preferences"
    ]
  },
  "evolution": {
    "cluster_threshold": 3,
    "evolved_path": "~/.claude/homunculus/evolved/"
  }
}

编辑

config.json

文件：

json

{
  "version": "2.0",
  "observation": {
    "enabled": true,
    "store_path": "~/.claude/homunculus/observations.jsonl",
    "max_file_size_mb": 10,
    "archive_after_days": 7
  },
  "instincts": {
    "personal_path": "~/.claude/homunculus/instincts/personal/",
    "inherited_path": "~/.claude/homunculus/instincts/inherited/",
    "min_confidence": 0.3,
    "auto_approve_threshold": 0.7,
    "confidence_decay_rate": 0.05
  },
  "observer": {
    "enabled": true,
    "model": "haiku",
    "run_interval_minutes": 5,
    "patterns_to_detect": [
      "user_corrections",
      "error_resolutions",
      "repeated_workflows",
      "tool_preferences"
    ]
  },
  "evolution": {
    "cluster_threshold": 3,
    "evolved_path": "~/.claude/homunculus/evolved/"
  }
}

File Structure

文件结构

~/.claude/homunculus/
├── identity.json           # Your profile, technical level
├── observations.jsonl      # Current session observations
├── observations.archive/   # Processed observations
├── instincts/
│   ├── personal/           # Auto-learned instincts
│   └── inherited/          # Imported from others
└── evolved/
    ├── agents/             # Generated specialist agents
    ├── skills/             # Generated skills
    └── commands/           # Generated commands

~/.claude/homunculus/
├── identity.json           # 你的个人资料、技术水平
├── observations.jsonl      # 当前会话观测记录
├── observations.archive/   # 已处理的观测记录归档
├── instincts/
│   ├── personal/           # 自动学习到的本能
│   └── inherited/          # 从他人处导入的本能
└── evolved/
    ├── agents/             # 生成的专业Agent
    ├── skills/             # 生成的技能
    └── commands/           # 生成的命令

Integration with Skill Creator

与Skill Creator集成

When you use the Skill Creator GitHub App, it now generates both:

Traditional SKILL.md files (for backward compatibility)
Instinct collections (for v2 learning system)

Instincts from repo analysis have

source: "repo-analysis"

and include the source repository URL.

当你使用Skill Creator GitHub应用时，它现在会同时生成：

传统的SKILL.md文件（用于向后兼容）
本能集合（用于v2学习系统）

来自代码库分析的本能会标记

source: "repo-analysis"

，并包含源代码库的URL。

Confidence Scoring

置信度评分机制

Confidence evolves over time:

Score	Meaning	Behavior
0.3	Tentative	Suggested but not enforced
0.5	Moderate	Applied when relevant
0.7	Strong	Auto-approved for application
0.9	Near-certain	Core behavior

Confidence increases when:

Pattern is repeatedly observed
User doesn't correct the suggested behavior
Similar instincts from other sources agree

Confidence decreases when:

User explicitly corrects the behavior
Pattern isn't observed for extended periods
Contradicting evidence appears

置信度会随时间演化：

评分	含义	行为
0.3	暂定	仅作为建议，不强制执行
0.5	中等	相关场景下自动应用
0.7	较高	自动批准并应用
0.9	近乎确定	作为核心行为应用

置信度提升场景：

模式被重复观测到
用户未修正建议的行为
来自其他来源的相似本能达成一致

置信度下降场景：

用户明确修正了该行为
长时间未观测到该模式
出现矛盾的证据

Why Hooks vs Skills for Observation?

为什么选择钩子而非技能进行观测？

"v1 relied on skills to observe. Skills are probabilistic—they fire ~50-80% of the time based on Claude's judgment."

Hooks fire 100% of the time, deterministically. This means:

Every tool call is observed
No patterns are missed
Learning is comprehensive

"v1版本依赖技能进行观测。技能是概率性的——基于Claude的判断，触发率约为50-80%。"

钩子会100%确定性触发，这意味着：

每一次工具调用都会被观测到
不会遗漏任何模式
学习过程全面覆盖

Backward Compatibility

向后兼容性

v2 is fully compatible with v1:

Existing
```
~/.claude/skills/learned/
```
skills still work
Stop hook still runs (but now also feeds into v2)
Gradual migration path: run both in parallel

v2版本完全兼容v1版本：

现有的
```
~/.claude/skills/learned/
```
目录下的技能仍可正常使用
停止钩子仍会运行（但现在也会为v2版本提供数据）
提供渐进式迁移路径：可以同时运行两个版本

Privacy

隐私说明

Observations stay local on your machine
Only instincts (patterns) can be exported
No actual code or conversation content is shared
You control what gets exported

观测记录全程保存在本地设备上
仅能导出本能（模式），不会包含实际代码或对话内容
你完全控制哪些内容可以被导出

continuous-learning-v2

Original

Translation

Continuous Learning v2 - Instinct-Based Architecture

持续学习v2 - 基于本能的架构

What's New in v2

v2版本新特性

The Instinct Model

本能模型

Prefer Functional Style

Prefer Functional Style

Action

Action

Evidence

Evidence

How It Works

工作流程

Quick Start

快速开始

1. Enable Observation Hooks

1. 启用观测钩子

2. Initialize Directory Structure

2. 初始化目录结构

3. Use the Instinct Commands

3. 使用本能相关命令

Commands

命令列表

Configuration

配置说明

File Structure

文件结构

Integration with Skill Creator

与Skill Creator集成

Confidence Scoring

置信度评分机制

Why Hooks vs Skills for Observation?

为什么选择钩子而非技能进行观测？

Backward Compatibility

向后兼容性

Privacy

隐私说明

Related

相关资源