evolve
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseSelf-Evolving Agent v5.11.0
Self-Evolving Agent v5.11.0
[版本檢查] → 北極星錨定 → [Worktree 隔離] → PSB 環境檢查 → 目標分析(🔗 brainstorming)→ 自動領域識別 → 評估能力 → 習得技能 → PDCA 執行(🔗 TDD + verification)→ 診斷(🔗 systematic-debugging)→ 多策略重試 → Repo 記憶 → 定期健檢 → [Worktree 完成] → 直到成功
[Version Check] → North Star Alignment → [Worktree Isolation] → PSB Environment Check → Goal Analysis (🔗 brainstorming) → Automatic Domain Identification → Capability Assessment → Skill Acquisition → PDCA Execution (🔗 TDD + verification) → Diagnosis (🔗 systematic-debugging) → Multi-Strategy Retries → Repo Memory → Regular Health Check → [Worktree Completion] → Until Success
快速導覽
Quick Overview
本 skill 採用原子化架構,將知識拆分為獨立模組:
| 模組 | 用途 | 路徑 |
|---|---|---|
| 00-getting-started | 入門與環境設定 | → |
| 01-core | 核心流程(PSB + PDCA) | → |
| 02-checkpoints | 強制檢查點(護欄) | → |
| 03-memory | 記憶系統操作 | → |
| 04-emergence | 涌現機制 | → |
| 05-integration | 外部工具整合(含 superpowers) | → |
| 06-scaling | 大規模專案優化 | → |
| 99-evolution | 自我進化機制 | → |
This skill adopts an atomic architecture, splitting knowledge into independent modules:
| Module | Purpose | Path |
|---|---|---|
| 00-getting-started | Getting Started & Environment Setup | → |
| 01-core | Core Workflow (PSB + PDCA) | → |
| 02-checkpoints | Mandatory Checkpoints (Guardrails) | → |
| 03-memory | Memory System Operations | → |
| 04-emergence | Emergence Mechanism | → |
| 05-integration | External Tool Integration (including superpowers) | → |
| 06-scaling | Large-Scale Project Optimization | → |
| 99-evolution | Self-Evolution Mechanism | → |
使用方式
Usage
bash
/evolve [目標描述]bash
/evolve [Goal Description]範例
Examples
/evolve 建立一個能自動生成遊戲道具圖片的 ComfyUI 工作流程
/evolve 優化這段程式碼的效能,目標是降低 50% 執行時間
/evolve 為這個專案建立完整的測試覆蓋率達到 80%
undefined/evolve Create a ComfyUI workflow that automatically generates game item images
/evolve Optimize the performance of this code, targeting a 50% reduction in execution time
/evolve Establish full test coverage for this project to reach 80%
undefinedFlags
Flags
bash
--explore # 探索模式 - 允許自主選擇方向
--emergence # 涌現模式 - 啟用跨領域連結探索
--autonomous # 自主模式 - 完全自主,追求系統性創新
--max-iterations N # 最大迭代次數(預設 10)
--from-spec NAME # 從 spec-workflow 的 tasks.md 執行bash
--explore # Exploration Mode - Allow autonomous direction selection
--emergence # Emergence Mode - Enable cross-domain connection exploration
--autonomous # Autonomous Mode - Fully independent, pursuing systematic innovation
--max-iterations N # Maximum number of iterations (default 10)
--from-spec NAME # Execute from spec-workflow's tasks.md核心哲學
Core Philosophy
人類與 AI 協作的本質:透過抽象化介面溝通
| 傳統軟體 | AI 協作 | 作用 |
|---|---|---|
| API | MCP | 能力邊界(能做什麼) |
| SDK/Library | Tools | 具體實作(怎麼做) |
| 文檔+實踐 | Skill | 領域知識(何時用什麼) |
| Config | CLAUDE.md | 上下文約束(專案規範) |
深層洞察:
- Skill 不只是知識,是「封裝好的判斷力」
- 告訴 AI 在什麼情況下,用什麼方式,達成什麼目標
- 減少決策點 > 讓 AI 自己選擇
The essence of human-AI collaboration: Communicate through abstract interfaces
| Traditional Software | AI Collaboration | Purpose |
|---|---|---|
| API | MCP | Capability Boundaries (what can be done) |
| SDK/Library | Tools | Specific Implementation (how to do it) |
| Docs + Practices | Skill | Domain Knowledge (when to use what) |
| Config | CLAUDE.md | Context Constraints (project specifications) |
Deep Insights:
- Skill is not just knowledge, but "packaged judgment"
- Tell the AI when to use which method to achieve what goal
- Reduce decision points > let the AI choose on its own
設計原則
Design Principles
| 原則 | 說明 |
|---|---|
| 有主見的設計 | 合理預設值 > 讓 AI 選擇,必填參數 ≤ 2 個 |
| 深且窄 | 專注 10% 高價值任務,不追求功能廣度 |
| 預期失敗 | 95% Agent 在生產環境失敗是常態,設計優雅降級 |
| 增強回饋 | 執行中提醒目標和進度,失敗時說明影響範圍 |
| Principle | Description |
|---|---|
| Opinionated Design | Reasonable defaults > letting AI choose, required parameters ≤ 2 |
| Deep & Narrow | Focus on 10% high-value tasks, do not pursue functional breadth |
| Expect Failure | 95% of Agents fail in production environments as normal, design graceful degradation |
| Enhanced Feedback | Remind of goals and progress during execution, explain impact scope when failing |
執行流程概覽
Execution Process Overview
Self-Evolving Loop v5.2
- 🔄 版本檢查(自動)— 檢查更新、詢問用戶、自動更新
- 🌟 CP0: 北極星錨定 — 願景、完成標準、不做清單、動機
- 🔒 CP0.5: Worktree 隔離(條件觸發)— Level 2 / autonomous / 並行任務
- PSB System — Plan → Setup → Build(環境準備)
- 目標分析 — 深度訪談 + 架構等級判斷(Level 2 強制)
- 能力評估 → Skill 習得
- PDCA Cycle — Plan → Do → Check → Act(含多策略選擇)
- CP3: 方向校正(對照北極星)
- Git-based Memory — 記錄學習經驗
- 🏥 CP6: 專案健檢(每 5 次迭代)— Scope、方向、終止檢查
- 🏁 CP6.5: Worktree 完成(條件觸發)— 合併/清理
↻ 重複直到:目標達成 或 達到最大迭代次數
主要功能:Superpowers 整合 | LEANN 語義搜尋 | Worktree 隔離 | 北極星系統 | 深度訪談詳見:CHANGELOG | 05-integration | 02-checkpoints
Self-Evolving Loop v5.2
- 🔄 Version Check (Automatic) — Check for updates, ask user, auto-update
- 🌟 CP0: North Star Alignment — Vision, completion criteria, no-do list, motivation
- 🔒 CP0.5: Worktree Isolation (Conditional Trigger) — Level 2 / autonomous / parallel tasks
- PSB System — Plan → Setup → Build (environment preparation)
- Goal Analysis — In-depth interview + architecture level judgment (mandatory for Level 2)
- Capability Assessment → Skill Acquisition
- PDCA Cycle — Plan → Do → Check → Act (including multi-strategy selection)
- CP3: Direction Correction (align with North Star)
- Git-based Memory — Record learning experiences
- 🏥 CP6: Project Health Check (every 5 iterations) — Scope, direction, termination check
- 🏁 CP6.5: Worktree Completion (Conditional Trigger) — Merge/cleanup
↻ Repeat until: Goal achieved or maximum iterations reached
Key Features: Superpowers Integration | LEANN Semantic Search | Worktree Isolation | North Star System | In-Depth InterviewSee details: CHANGELOG | 05-integration | 02-checkpoints
架構考量三層設計
Three-Tier Architecture Consideration
| Layer | 階段 | 動作 |
|---|---|---|
| 1 | Goal Analysis | 判斷架構等級 (0/1/2) |
| 2 | PDCA Plan | 依等級做架構設計 |
| 3 | CP1.5 Phase 2 | 驗證實作符合設計 |
→ 設計 → 實作 → 驗證 閉環
| Layer | Phase | Action |
|---|---|---|
| 1 | Goal Analysis | Determine architecture level (0/1/2) |
| 2 | PDCA Plan | Conduct architecture design based on level |
| 3 | CP1.5 Phase 2 | Verify implementation complies with design |
→ Design → Implementation → Verification Loop
強制檢查點(護欄)
Mandatory Checkpoints (Guardrails)
這些檢查點不可跳過,詳見 02-checkpoints
| 檢查點 | 時機 | 動作 |
|---|---|---|
| CP0 🌟 | 專案/任務開始前 | 北極星錨定(建立或讀取) |
| CP0.5 🔒 | CP0 後(條件觸發) | Worktree 隔離環境準備 |
| CP1 | 任務開始前 | 搜尋 .claude/memory/ 查找相關經驗 |
| CP1.5 | 寫程式碼前 | 一致性檢查(兩階段) |
| CP2 | 程式碼變更後 | 編譯 + 測試驗證 |
| CP3 | Milestone 完成後 | 確認目標、方向校正、下一步 |
| CP3.5 | Memory 文件創建後 | 立即同步 index.md |
| CP4 | 迭代完成後 | 涌現機會檢查(選擇性) |
| CP5 | PDCA Check 失敗時 | 失敗後驗屍,生成結構化 Lesson |
| CP6 🏥 | 每 5 次迭代後 | 專案健檢(Scope、方向、終止檢查) |
| CP6.5 🏁 | 任務完成時(條件觸發) | Worktree 合併/清理 |
These checkpoints cannot be skipped, see details in 02-checkpoints
| Checkpoint | Timing | Action |
|---|---|---|
| CP0 🌟 | Before project/task starts | North Star Alignment (create or read) |
| CP0.5 🔒 | After CP0 (conditional trigger) | Worktree isolation environment preparation |
| CP1 | Before task starts | Search .claude/memory/ for relevant experiences |
| CP1.5 | Before writing code | Consistency check (two phases) |
| CP2 | After code changes | Compilation + test verification |
| CP3 | After milestone completion | Confirm goal, direction correction, next steps |
| CP3.5 | After memory document creation | Immediately sync index.md |
| CP4 | After iteration completion | Emergence opportunity check (optional) |
| CP5 | When PDCA Check fails | Post-mortem analysis, generate structured Lesson |
| CP6 🏥 | Every 5 iterations | Project health check (Scope, direction, termination check) |
| CP6.5 🏁 | When task completes (conditional trigger) | Worktree merge/cleanup |
Checkpoint 並行化
Checkpoint Parallelization
效率優化:以下 CP 可並行執行:
- CP1 + CP1.5 Phase 1:Memory 搜尋與基礎一致性檢查互不依賴,使用 同時啟動
run_in_background: true - CP4 + 下一迭代 Plan:涌現檢查在背景運行,不阻塞後續 PDCA
不可並行:CP0/CP0.5 必須先完成;CP1.5 Phase 2 依賴 CP1 結果;CP2 → CP3 為序列關係。
詳見 02-checkpoints/README.md
Efficiency Optimization: The following CPs can be executed in parallel:
- CP1 + CP1.5 Phase 1: Memory search and basic consistency check are independent, start simultaneously with
run_in_background: true - CP4 + Next Iteration Plan: Emergence check runs in the background without blocking subsequent PDCA
Non-parallelizable: CP0/CP0.5 must be completed first; CP1.5 Phase 2 depends on CP1 results; CP2 → CP3 is sequential.
See details in 02-checkpoints/README.md
CP1.5 兩階段設計
CP1.5 Two-Phase Design
Phase 1: 基礎檢查(必執行)
- 搜尋現有實作,避免重複造輪子
- 檢查專案慣例(命名、風格)
- 檢查 Schema/API 一致性
Phase 2: 架構檢查(自動偵測觸發)
- 依賴方向、錯誤處理一致性、橫切關注點、設計模式一致性
觸發條件:新增目錄/模組、變更涉及 3+ 目錄、新增外部依賴、觸及 core/infra/domain/shared/、新增公開 API
Phase 1: Basic Check (Mandatory)
- Search existing implementations to avoid reinventing the wheel
- Check project conventions (naming, style)
- Check Schema/API consistency
Phase 2: Architecture Check (Automatically Triggered)
- Dependency direction, error handling consistency, cross-cutting concerns, design pattern consistency
Trigger Conditions: New directory/module added, changes involve 3+ directories, new external dependencies added, touching core/infra/domain/shared/, new public API added
停止條件
Termination Conditions
| 狀態 | 條件 |
|---|---|
| ✅ 成功 | 所有子目標完成 + 驗收標準通過 |
| ❌ 失敗 | 達到最大迭代次數 或 連續 3 次相同錯誤 |
| ⏸️ 暫停 | 需要用戶決策 或 風險操作需確認 |
| Status | Condition |
|---|---|
| ✅ Success | All sub-goals completed + acceptance criteria passed |
| ❌ Failure | Reached maximum iterations or 3 consecutive identical errors |
| ⏸️ Pause | User decision required or risky operation needs confirmation |
完成信號
Completion Signals
✅ GOAL ACHIEVED: [目標描述]⏸️ NEED HUMAN: [原因]❌ CANNOT COMPLETE: [原因]
✅ GOAL ACHIEVED: [Goal Description]⏸️ NEED HUMAN: [Reason]❌ CANNOT COMPLETE: [Reason]