docs/zh-CN/skills/continuous-learning-v2/SKILL.md
基于本能的学习系统,通过钩子观察会话,创建具有置信度评分的原子本能,并将其进化为技能/命令/代理。
npx skillsauth add xu-xiang/everything-claude-code-zh continuous-learning-v2Install this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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 会话转化为可重用的知识。
部分灵感来源于 humanplane (credit: @humanplane) 的 Homunculus 项目。
| 特性 | v1 | v2 | |---------|----|----| | 观察 | 停止钩子(会话结束) | 工具使用前/后(100% 可靠) | | 分析 | 主上下文 | 后台代理(Haiku) | | 粒度 | 完整技能 | 原子化的“本能” | | 置信度 | 无 | 0.3-0.9 加权 | | 演进 | 直接到技能 | 本能 → 聚类 → 技能/命令/代理 | | 共享 | 无 | 导出/导入本能 |
一个本能是一个小型习得行为:
---
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
属性:
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 │
└─────────────────────────────────────────┘
添加到你的 ~/.claude/settings.json 中。
如果作为插件安装(推荐):
{
"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"
}]
}]
}
}
如果手动安装到 ~/.claude/skills:
{
"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"
}]
}]
}
}
Python CLI 会自动创建这些目录,但你也可以手动创建:
mkdir -p ~/.claude/homunculus/{instincts/{personal,inherited},evolved/{agents,skills,commands}}
touch ~/.claude/homunculus/observations.jsonl
/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
| 命令 | 描述 |
|---------|-------------|
| /instinct-status | 显示所有已习得的本能及其置信度 |
| /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> | 从他人处导入本能 |
编辑 config.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/"
}
}
~/.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
当你使用 技能创建器 GitHub 应用 时,它现在会生成两者:
来自仓库分析的本能带有 source: "repo-analysis" 标记,并包含源仓库 URL。
置信度随时间演变:
| 分数 | 含义 | 行为 | |-------|---------|----------| | 0.3 | 尝试性的 | 建议但不强制执行 | | 0.5 | 中等的 | 相关时应用 | | 0.7 | 强烈的 | 自动批准应用 | | 0.9 | 近乎确定的 | 核心行为 |
置信度增加当:
置信度降低当:
“v1 依赖技能进行观察。技能是概率性的——它们基于 Claude 的判断,大约有 50-80% 的概率触发。”
钩子100% 触发,是确定性的。这意味着:
v2 与 v1 完全兼容:
~/.claude/skills/learned/ 技能仍然有效基于本能的学习:一次一个观察,教会 Claude 你的模式。
documentation
将签证申请文件(图像)翻译成英文,并创建包含原文和译文的双语 PDF。
development
Claude Code 会话的全方位验证系统。
tools
在编写新功能、修复 Bug 或重构代码时使用此技能。强制执行测试驱动开发(TDD),包括单元测试、集成测试和 E2E 测试,且覆盖率需达到 80% 以上。
tools
SwiftUI 架构模式,使用 @Observable 进行状态管理,视图组合、导航、性能优化以及现代 iOS/macOS UI 最佳实践。