docs/zh-TW/skills/continuous-learning/SKILL.md
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
npx skillsauth add affaan-m/everything-claude-code continuous-learningInstall 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.
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:docs/continuous-learning-v2-spec.md 完整規格。
tools
Garbage collection for your Claude Code configuration. Periodically scans ~/.claude (skills, memory, hooks, permissions, MCP servers, caches) for redundant, stale, orphaned, or low-value items, then walks the user through a confirm-each-deletion cleanup. Use when the user says "clean up my config", "config GC", "too many skills", "audit my setup", "my .claude is bloated", or asks for a periodic config review.
data-ai
当用户希望通过并行工作、并发 agents、批量工具调用、隔离 worktree 或多条独立验证通道来大幅加速任务、同时不损失正确性时使用。
documentation
在回答之前先读取仓库的实时状态,引导用户了解 ECC 当前的 agents、skills、命令、hooks、规则、安装配置档案以及项目接入流程。
testing
Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.