Source profileQuality 68/100

affaan-m/ECC/docs/zh-TW/skills/continuous-learning/SKILL.md

continuous-learning

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.

Source repository stars
234,327
Declared platforms
1
Static risk flags
0
Last source update
2026-07-27
Source checked
2026-07-28

Decision brief

What it does—and where it fits

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。

Best for

    Not for

    • Tasks that require unconfirmed production actions or broad system permissions.
    • Environments where the pinned source and install steps cannot be inspected.

    Compatibility matrix

    Platform support, with evidence labels

    PlatformStatusEvidenceWhat to check
    CodexNot declaredNo explicit evidencePortability before use
    Claude CodeDeclaredSource recordInstall path and trigger
    CursorNot declaredNo explicit evidencePortability before use
    Gemini CLINot declaredNo explicit evidencePortability before use
    Open the compatibility checker

    Installation

    Inspect first. Install second.

    The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.

    Source-detected install commandSource
    npx skills add https://github.com/affaan-m/ECC --skill "docs/zh-TW/skills/continuous-learning"
    Safe inspection promptEditorial

    Inspect the Agent Skill "continuous-learning" from https://github.com/affaan-m/ECC/blob/4e973d3eaf92d97f8d2e2d8abb39d8bdc8711b38/docs/zh-TW/skills/continuous-learning/SKILL.md at commit 4e973d3eaf92d97f8d2e2d8abb39d8bdc8711b38. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.

    Workflow

    What the source asks the agent to do

    1. 01

      運作方式

      此技能作為 Stop hook 在每個工作階段結束時執行:

      工作階段評估:檢查工作階段是否有足夠訊息(預設:10+ 則)模式偵測:從工作階段識別可提取的模式技能提取:將有用模式儲存到 /.claude/skills/learned/
    2. 02

      設定

      Review the “設定” section in the pinned source before continuing.

      Review and apply the “設定” source section.
    3. 03

      模式類型

      Review the “模式類型” section in the pinned source before continuing.

      Review and apply the “模式類型” source section.

    Permission review

    Static risk signals and limitations

    No configured static risk pattern was detected

    This is not proof of safety. Runtime behavior, indirect dependencies, and hidden external systems are outside the static scan.

    Evidence record

    Why each signal appears

    EvidenceSourceComputedTestedEditorial
    SignalValueEvidence typeMeaning
    Quality score68/100ComputedDocumentation, specificity, maintenance, and trust rules
    Repository stars234,327SourceRepository attention, not individual Skill quality
    Compatibility1 platformsSourceDeclared in the catalog source record
    Usage guidecatalog recordEditorialGenerated or reviewed according to the visible evidence level

    Pinned source

    Provenance and original SKILL.md

    Repository
    affaan-m/ECC
    Skill path
    docs/zh-TW/skills/continuous-learning/SKILL.md
    Commit
    4e973d3eaf92d97f8d2e2d8abb39d8bdc8711b38
    License
    MIT
    Collected
    2026-07-28
    Default branch
    main
    View the original SKILL.md

    持續學習技能

    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。

    運作方式

    此技能作為 Stop hook 在每個工作階段結束時執行:

    1. 工作階段評估:檢查工作階段是否有足夠訊息(預設:10+ 則)
    2. 模式偵測:從工作階段識別可提取的模式
    3. 技能提取:將有用模式儲存到 ~/.claude/skills/learned/

    設定

    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"
      ]
    }
    

    模式類型

    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

    Hook 設定

    新增到你的 ~/.claude/settings.json

    {
      "hooks": {
        "Stop": [{
          "matcher": "*",
          "hooks": [{
            "type": "command",
            "command": "~/.claude/skills/continuous-learning/evaluate-session.sh"
          }]
        }]
      }
    }
    

    為什麼用 Stop Hook?

    • 輕量:工作階段結束時只執行一次
    • 非阻塞:不會為每則訊息增加延遲
    • 完整上下文:可存取完整工作階段記錄

    相關

    • Longform Guide - 持續學習章節
    • /learn 指令 - 工作階段中手動提取模式

    比較筆記(研究:2025 年 1 月)

    vs Homunculus

    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0.3-0.9 加權
    演化直接到技能本能 → 聚類 → 技能/指令/agent
    分享匯出/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。"

    潛在 v2 增強

    1. 基於本能的學習 - 較小的原子行為,帶信心評分
    2. 背景觀察者 - Haiku agent 並行分析
    3. 信心衰減 - 如果被矛盾則本能失去信心
    4. 領域標記 - code-style、testing、git、debugging 等
    5. 演化路徑 - 將相關本能聚類為技能/指令

    參見:docs/continuous-learning-v2-spec.md 完整規格。

    Alternatives

    Compare before choosing