docs/zh-TW/skills/continuous-learning-v2/SKILL.md
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
npx skillsauth add affaan-m/everything-claude-code 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.
進階學習系統,透過原子「本能」(帶信心評分的小型學習行為)將你的 Claude Code 工作階段轉化為可重用知識。
| 功能 | v1 | v2 | |------|----|----| | 觀察 | Stop hook(工作階段結束) | PreToolUse/PostToolUse(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 |
本能是一個小型學習行為:
---
id: prefer-functional-style
trigger: "when writing new functions"
confidence: 0.7
domain: "code-style"
source: "session-observation"
---
# 偏好函式風格
## 動作
適當時使用函式模式而非類別。
## 證據
- 觀察到 5 次函式模式偏好
- 使用者在 2025-01-15 將基於類別的方法修正為函式
屬性:
工作階段活動
│
│ Hooks 捕獲提示 + 工具使用(100% 可靠)
▼
┌─────────────────────────────────────────┐
│ observations.jsonl │
│ (提示、工具呼叫、結果) │
└─────────────────────────────────────────┘
│
│ Observer agent 讀取(背景、Haiku)
▼
┌─────────────────────────────────────────┐
│ 模式偵測 │
│ • 使用者修正 → 本能 │
│ • 錯誤解決 → 本能 │
│ • 重複工作流程 → 本能 │
└─────────────────────────────────────────┘
│
│ 建立/更新
▼
┌─────────────────────────────────────────┐
│ instincts/personal/ │
│ • prefer-functional.md (0.7) │
│ • always-test-first.md (0.9) │
│ • use-zod-validation.md (0.6) │
└─────────────────────────────────────────┘
│
│ /evolve 聚類
▼
┌─────────────────────────────────────────┐
│ evolved/ │
│ • commands/new-feature.md │
│ • skills/testing-workflow.md │
│ • agents/refactor-specialist.md │
└─────────────────────────────────────────┘
如果作為外掛安裝(建議):
不需要在 ~/.claude/settings.json 中額外加入 hook。Claude Code v2.1+ 會自動載入外掛的 hooks/hooks.json,其中已經註冊了 observe.sh。
如果你之前把 observe.sh 複製到 ~/.claude/settings.json,請移除重複的 PreToolUse / PostToolUse 區塊。重複註冊會造成重複執行,並觸發 ${CLAUDE_PLUGIN_ROOT} 解析錯誤;這個變數只會在外掛自己的 hooks/hooks.json 中展開。
如果手動安裝到 ~/.claude/skills,新增到你的 ~/.claude/settings.json:
{
"hooks": {
"PreToolUse": [{
"matcher": "*",
"hooks": [{
"type": "command",
"command": "~/.claude/skills/continuous-learning-v2/hooks/observe.sh"
}]
}],
"PostToolUse": [{
"matcher": "*",
"hooks": [{
"type": "command",
"command": "~/.claude/skills/continuous-learning-v2/hooks/observe.sh"
}]
}]
}
}
mkdir -p ~/.claude/homunculus/{instincts/{personal,inherited},evolved/{agents,skills,commands}}
touch ~/.claude/homunculus/observations.jsonl
觀察者可以在背景執行並分析觀察:
# 啟動背景觀察者
~/.claude/skills/continuous-learning-v2/agents/start-observer.sh
| 指令 | 描述 |
|------|------|
| /instinct-status | 顯示所有學習本能及其信心 |
| /evolve | 將相關本能聚類為技能/指令 |
| /instinct-export | 匯出本能以分享 |
| /instinct-import <file> | 從他人匯入本能 |
編輯 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 # 你的個人資料、技術水平
├── observations.jsonl # 當前工作階段觀察
├── observations.archive/ # 已處理觀察
├── instincts/
│ ├── personal/ # 自動學習本能
│ └── inherited/ # 從他人匯入
└── evolved/
├── agents/ # 產生的專業 agents
├── skills/ # 產生的技能
└── commands/ # 產生的指令
當你使用 Skill Creator GitHub App 時,它現在產生兩者:
從倉庫分析的本能有 source: "repo-analysis" 並包含來源倉庫 URL。
信心隨時間演化:
| 分數 | 意義 | 行為 | |------|------|------| | 0.3 | 試探性 | 建議但不強制 | | 0.5 | 中等 | 相關時應用 | | 0.7 | 強烈 | 自動批准應用 | | 0.9 | 近乎確定 | 核心行為 |
信心增加當:
信心減少當:
"v1 依賴技能進行觀察。技能是機率性的——它們根據 Claude 的判斷觸發約 50-80% 的時間。"
Hooks 100% 的時間確定性地觸發。這意味著:
v2 完全相容 v1:
~/.claude/skills/learned/ 技能仍可運作基於本能的學習:一次一個觀察,教導 Claude 你的模式。
data-ai
Design task-local harnesses, eval gates, and reusable skill extraction for Claude dynamic workflow mode and other adaptive agent harnesses.
development
React component testing with React Testing Library, Vitest/Jest, MSW for network mocking, accessibility assertions with axe, and the decision boundary between component tests and Playwright/Cypress end-to-end runs. Use when writing or fixing tests for React components, hooks, or pages.
tools
React and Next.js performance optimization patterns adapted from Vercel Engineering's React Best Practices (https://github.com/vercel-labs/agent-skills). Organizes 70+ rules across 8 priority categories — waterfalls, bundle size, server-side, client fetching, re-render, rendering, JS micro-perf, advanced. Use when writing, reviewing, or refactoring React/Next.js code for performance.
tools
React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.