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。
47
50%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Passed
No findings from the security scan
Fix and improve this skill with Tessl
tessl review fix ./docs/zh-CN/skills/continuous-learning-v2/SKILL.md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。
dfbf946
Also appears in
on Aug 14, 2026
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.