菜单
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
PostgreSQL database patterns for query optimization, schema design, indexing, and security. Based on Supabase best practices.
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
Go testing patterns including table-driven tests, subtests, benchmarks, fuzzing, and test coverage. Follows TDD methodology with idiomatic Go practices.
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
Pattern for progressively refining context retrieval to solve the subagent context problem
| name | continuous-learning |
| description | Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use. |
自動評估 Claude Code 工作階段結束時的內容，提取可重用模式並儲存為學習技能。
此技能作為 Stop hook 在每個工作階段結束時執行：
~/.claude/skills/learned/編輯 config.json 以自訂：
{
"min_session_length": 10,
"extraction_threshold": "medium",
"auto_approve": false,
"learned_skills_path": "~/.claude/skills/learned/",
"patterns_to_detect": [
"error_resolution",
"user_corrections",
"workarounds",
"debugging_techniques",
"project_specific"
],
"ignore_patterns": [
"simple_typos",
"one_time_fixes",
"external_api_issues"
]
}
| 模式 | 描述 |
|---|---|
error_resolution | 特定錯誤如何被解決 |
user_corrections | 來自使用者修正的模式 |
workarounds | 框架/函式庫怪異問題的解決方案 |
debugging_techniques | 有效的除錯方法 |
project_specific | 專案特定慣例 |
新增到你的 ~/.claude/settings.json：
{
"hooks": {
"Stop": [{
"matcher": "*",
"hooks": [{
"type": "command",
"command": "~/.claude/skills/continuous-learning/evaluate-session.sh"
}]
}]
}
}
/learn 指令 - 工作階段中手動提取模式Homunculus v2 採用更複雜的方法：
| 功能 | 我們的方法 | Homunculus v2 |
|---|---|---|
| 觀察 | Stop hook（工作階段結束） | PreToolUse/PostToolUse hooks（100% 可靠） |
| 分析 | 主要上下文 | 背景 agent（Haiku） |
| 粒度 | 完整技能 | 原子「本能」 |
| 信心 | 無 | 0.3-0.9 加權 |
| 演化 | 直接到技能 | 本能 → 聚類 → 技能/指令/agent |
| 分享 | 無 | 匯出/匯入本能 |
來自 homunculus 的關鍵見解：
"v1 依賴技能進行觀察。技能是機率性的——它們觸發約 50-80% 的時間。v2 使用 hooks 進行觀察（100% 可靠），並以本能作為學習行為的原子單位。"
參見：/Users/affoon/Documents/tasks/12-continuous-learning-v2.md 完整規格。