Communitygithub.com

curiositech/windags-skills

來自 DeepMind AlphaGo 系統的戰略模式,用於透過級聯近似、自我改進和異質評估來解決棘手的問題。

windags-skills 是什麼?

這項技能借鑑 DeepMind AlphaGo 系統中的核心策略,提供一套處理計算成本高昂、搜尋空間巨大問題的架構模式。其核心是級聯近似法:結合多個不同速度與準確度的評估器(如快速策略網路、中速價值網路、慢速隨機模擬),在有限的計算資源下,透過類似決策樹的規則,決定何時使用單一最佳評估器,何時應組合多個評估器以達到最佳結果。技能詳細說明了五種常見的失敗模式,包括架構膨脹、同步耦合、代理指標固定、單一評估器謬誤及均勻預算分配,並提供具體的檢測規則與修復方法,協助開發者避免陷阱。最後,透過一個程式碼審查系統的實際案例,逐步展示如何應用級聯策略來滿足複雜的延遲與準確度要求,並附上品質閘門清單以確保實施的正確性。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/curiositech/windags-skills/tree/HEAD/skills/alphago-deep-rl

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

AlphaGo 架構技能

決策點

何時使用單一 vs. 級聯評估器

問題特徵:
├── 搜尋空間可處理 (b^d < 10^9)
│   └── 使用單一最佳評估器 → 標準最佳化
└── 搜尋空間不可處理 (b^d > 10^12)
    ├── 有統一的評估預算
    │   └── 使用級聯近似:
    │       1. 快速剪枝 (策略網路) → 縮小搜尋寬度
    │       2. 中等評估 (價值網路) → 估計品質
    │       3. 廉價探索 (隨機模擬) → 覆蓋廣度
    └── 非統一的評估預算
        └── 自適應分配:
            ├── 關鍵位置 → 昂貴評估
            └── 例行位置 → 廉價啟發式

準確度 vs. 延遲需求決策樹

系統需求:
├── 延遲敏感 (<1ms 回應)
│   ├── 高容錯度 (可接受 >10% 錯誤率)
│   │   └── 僅快速隨機模擬 (2µs/評估)
│   └── 低容錯度 (需 <5% 錯誤率)
│       └── 快取策略網路 + 啟發式備用方案
├── 延遲適中 (1-100ms 回應)
│   ├── 需要高準確度
│   │   └── 價值網路 (3ms) + 策略網路引導
│   └── 平衡準確度/速度
│       └── 混合評估:λ=0.5 價值 + 隨機模擬
└── 延遲容忍 (>100ms)
    └── 完整級聯:策略 → 價值 → 隨機模擬 + MCTS

錯誤模式多樣性評估

選擇多個評估器時:
├── 所有評估器具有相似的失敗模式
│   └── 使用單一最佳評估器 (無多樣性效益)
├── 評估器具有互補性錯誤
│   ├── 快速/雜訊 + 慢速/準確配對
│   │   └── 在 λ=0.3-0.7 混合 (偏向準確)
│   ├── 保守 + 探索配對
│   │   └── 在 λ=0.5 混合 (等權重)
│   └── 學習 + 手工配對
│       └── 基於信心分數動態混合
└── 未知錯誤相關性
    └── 經驗測試:在保留集上測量效能

失敗模式

架構膨脹 (檢測:>5 個近似層)

症狀:添加更多近似層但看到收益遞減 根本原因:每層增加開銷但沒有成比例的準確度提升 修復方法:分析運算成本 vs. 準確度提升;移除 ROI 低的層 檢測規則:如果添加第 N 層使準確度提升 <5% 但延遲增加 >20%,則存在架構膨脹

同步耦合 (檢測:快速元件閒置等待)

症狀:等待 GPU 評估時 CPU 使用率下降 根本原因:快速搜尋與緩慢神經網路評估之間的緊密耦合 修復方法:實現非同步佇列,並容忍過時的價值 檢測規則:如果快速元件(搜尋、隨機模擬)的空閒時間 >50%,則存在同步耦合

代理指標固定 (檢測:指標改善但效能下降)

症狀:移動預測準確度提高但勝率下降 根本原因:優化人類模仿而非客觀成功 修復方法:從監督學習轉向強化學習,使用真實目標 檢測規則:如果代理指標和結果指標趨勢相反,且持續超過 10 次評估,則存在代理指標固定

單一評估器謬誤 (檢測:拒絕「較差」的個別元件)

症狀:因為價值網路有較高的個別準確度而丟棄隨機模擬 根本原因:假設最佳個別元件就能組成最佳系統元件 修復方法:經驗性地測試混合效能;多樣性通常勝過個別品質 檢測規則:如果你僅根據個別效能選擇元件而沒有測試組合,則存在單一評估器謬誤

均勻預算分配 (檢測:所有決策使用相同運算量)

症狀:在明顯的移動與關鍵位置上花費相同的評估時間 根本原因:未根據決策重要性調整運算預算 修復方法:基於位置不確定性和結果敏感度實現自適應分配 檢測規則:如果各位置的評估時間變異數 <平均值的 20%,則存在均勻分配

實際範例

為程式碼審查實施級聯近似

情境:設計一個 AI 系統來審查包含 50-500 行改動的拉取請求,需要 <10s 回應時間,必須捕捉 95% 的錯誤。

步驟 1:分析運算限制

  • 靜態分析:每個檔案 10ms
  • ML 錯誤檢測器:每個檔案 2s
  • 深度語意分析:每個檔案 30s
  • 可用預算:總共 10s

步驟 2:應用級聯決策樹 由於詳盡分析超出預算,遵循「搜尋空間不可處理」路徑:

  1. 快速剪枝層(靜態分析):剔除沒有複雜度變化的檔案
  2. 中等評估層(ML 檢測器):對剩餘檔案評分以預測錯誤可能性
  3. 昂貴分析層(語意分析):僅對分數最高的檔案進行深度分析

步驟 3:預算分配策略

  • 為所有剩餘檔案的 ML 評估保留 2s
  • 根據 ML 分數將剩餘 8s 分配給語意分析
  • 分數 >0.8 的檔案:每個分配 4s(最多 2 個檔案)
  • 分數 0.5-0.8 的檔案:每個分配 2s
  • 分數 <0.5 的檔案:僅使用 ML 分數

步驟 4:混合評估實施 與其使用「最佳」評估器(語意分析),不如混合 ML 和語意分數:

  • ML 檢測器:快速,擅長模式匹配,但會漏掉新穎的錯誤
  • 語意分析:緩慢,能捕捉複雜的邏輯錯誤,但誤報率高
  • 在 λ=0.6 混合:最終分數 = 0.6 * 語意 + 0.4 * ML

新手方法:對所有內容執行語意分析 → 在前幾個檔案後超時 專家見解:級聯允許僅在最需要的地方花費昂貴的計算資源,同時確保每個檔案都得到一些評估

品質閘門

[ ] 已測試 N 個評估器:已實施並基準測試最少 3 個具有不同速度/準確度輪廓的評估器 [ ] 已測量錯誤相關性:計算的成對相關矩陣顯示評估器在測試集上的相關性 <0.7 [ ] 已評估混合 vs. 單一:經驗比較顯示混合法比最佳個別元件效能提升 >5% [ ] 已滿足延遲需求:在完整級聯下,95 百分位回應時間低於指定閾值 [ ] 已滿足準確度需求:保留集上的錯誤率低於指定閾值(例如 <5% 偽陰性率) [ ] 已分析預算分配:運算成本分析顯示預算根據決策重要性分配 [ ] 已測試失敗模式:在對抗性條件下測試系統(分佈轉移、資源限制、邊緣情況) [ ] 已驗證非同步協調:即使在慢速元件飽和時,快速元件的使用率仍保持 >80% [ ] 已驗證可擴展性:將負載增加到名義容量 10 倍時,效能可優雅地降級 [ ] 監控儀表化:指標追蹤代理 vs. 結果對齊、元件使用率和級聯效能

不適用範圍

請勿將此技能用於:

  • 具有可處理搜尋空間的簡單最佳化問題 → 改用 standard-optimization
  • 單一模型訓練或調優 → 改用 deep-learning-training
  • 需要 <1ms 延遲的即時系統 → 改用 low-latency-systems
  • 一個評估器明顯優於其他且其他無附加價值的問題 → 改用 single-model-deployment
  • 沒有搜尋樹結構的順序決策過程 → 改用 reinforcement-learning-fundamentals

當需要以下情況時,委託給其他技能:

  • 需要實作特定的神經網路架構 → deep-learning-architectures
  • 設計分散式系統基礎設施 → distributed-systems-design
  • 最佳化個別元件效能 → performance-optimization
  • 處理訓練資料收集與標記 → data-engineering
  • 實作特定的搜尋演算法 → search-algorithms

此技能專注於:在計算限制下協調多個不完美評估器的架構模式,而不是個別元件的實作細節。

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

curiositech/windags-skills

Expert in 2000s-era music visualization (Milkdrop, AVS, Geiss) and modern WebGL implementations. Specializes in Butterchurn integration, Web Audio API AnalyserNode FFT data, GLSL shaders for audio-reactive visuals, and psychedelic generative art. Activate on "Milkdrop", "music visualization", "WebGL visualizer", "Butterchurn", "audio reactive", "FFT visualization", "spectrum analyzer". NOT for simple bar charts/waveforms (use basic canvas), video editing, or non-audio visuals.

curiositech/windags-skills

Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal landscape.

curiositech/windags-skills

Expert in 3D computer vision labeling tools, workflows, and AI-assisted annotation for LiDAR, point clouds, and sensor fusion. Covers SAM4D/Point-SAM, human-in-the-loop architectures, and vertical-specific training strategies. Activate on '3D labeling', 'point cloud annotation', 'LiDAR labeling', 'SAM 3D', 'SAM4D', 'sensor fusion annotation', '3D bounding box', 'semantic segmentation point cloud'. NOT for 2D image labeling (use clip-aware-embeddings), general ML training (use ml-engineer), video annotation without 3D (use computer-vision-pipeline), or VLM prompt engineering (use prompt-engineer).

curiositech/windags-skills

Implement WCAG 2.2 AA/AAA compliance with automated testing, keyboard navigation, screen reader support, and focus management. Activate on: accessibility audit, WCAG compliance, keyboard navigation, screen reader, aria attributes, axe-core, focus trap. NOT for: design-level accessibility review (use design-accessibility-auditor), color contrast only (use css-in-js-architect).

curiositech/windags-skills

Time-blind friendly planning, executive function support, and daily structure for ADHD brains. Specializes in realistic time estimation, dopamine-aware task design, and building systems that actually work for neurodivergent minds.

curiositech/windags-skills

Designs digital experiences for ADHD brains using neuroscience research and UX principles. Expert in reducing cognitive load, time blindness solutions, dopamine-driven engagement, and compassionate design patterns. Activate on 'ADHD design', 'cognitive load', 'accessibility', 'neurodivergent UX', 'time blindness', 'dopamine-driven', 'executive function'. NOT for general accessibility (WCAG only), neurotypical UX design, or simple UI styling without ADHD context.

curiositech/windags-skills

>- Apply crisis decision-making research to agent routing, uncertainty triage, and coordination failure analysis in time-pressured systems. Use when diagnosing handoff failures, analytical paralysis, or expert judgment under incomplete information. NOT for routine coding, simple CRUD design, or static single-agent tasks with complete information.

curiositech/windags-skills

Extend and modify the admin dashboard, developer portal, and operations console. Use when adding new admin tabs, metrics, monitoring features, or internal tools. Activates for dashboard development, analytics, user management, and internal tooling.

curiositech/windags-skills

Conversation patterns and interaction protocols for multi-agent systems. Covers request/response, pub/sub, blackboard, delegation chains, debate, critique, consensus, fan-out/fan-in, supervisor-worker, and peer negotiation. Deep analysis of AutoGen conversation patterns, CrewAI delegation, LangGraph state passing, and FIPA-ACL performatives. Teaches how to design what agents say to each other and in what order. Activate on: "agent conversation", "agent protocol", "multi-agent debate", "agent delegation", "supervisor worker pattern", "agent voting", "consensus protocol", "fan-out fan-in", "agent negotiation", "blackboard pattern", "agent dialogue", "conversation topology", "agent handoff". NOT for: wire format or serialization (use agent-interchange-formats), orchestration infrastructure (use agentic-infrastructure-2026), single agent behavior (use agentic-patterns).

curiositech/windags-skills

Meta-agent for creating new custom agents, skills, and MCP integrations. Expert in agent design, MCP development, skill architecture, and rapid prototyping. Activate on 'create agent', 'new skill', 'MCP server', 'custom tool', 'agent design'. NOT for using existing agents (invoke them directly), general coding (use language-specific skills), or infrastructure setup (use deployment-engineer).

curiositech/windags-skills

AI-powered calendar management and agent-based scheduling coordination. Covers calendar APIs (Google Calendar, CalDAV/iCal), AI scheduling assistants (Reclaim, Clockwise, Motion, Cal.com), building custom calendar agents with MCP, multi-calendar merging, timezone management, focus block protection, meeting fatigue detection, and agent-to-agent meeting negotiation protocols. Activate on: "calendar agent", "AI scheduling", "calendar coordination", "meeting scheduling", "calendar API", "focus time protection", "calendar optimization", "Google Calendar MCP", "Reclaim", "Clockwise", "Motion", "Cal.com", "smart scheduling", "calendar-aware agent", "timezone scheduling", "agent negotiation meetings". NOT for: manual calendar UI component design (use form-validation-architect), project management scheduling or Gantt charts (use project-management-guru-adhd), general time-tracking or pomodoro apps (use adhd-daily-planner for time-awareness), building the agent itself from scratch (use agent-creator).

curiositech/windags-skills

Build and adopt production AI agent infrastructure in 2026. Covers framework selection (LangGraph, CrewAI, AutoGen, MCP), orchestration patterns, evaluation, observability, memory systems, and tool use. Also covers the SOCIAL dimension: how to sell agent infrastructure internally, change management, measuring ROI, building trust in autonomous systems, and scaling adoption across teams. Activate on: "agent infrastructure", "agent framework comparison", "which agent framework", "sell AI tools internally", "agent adoption", "agent observability", "agent evaluation", "MCP architecture", "agentic mesh", "enterprise AI agents", "AI change management", "agent ROI". NOT for: building specific agents (use ai-engineer), designing agent behavior patterns (use agentic-patterns), prompt tuning (use prompt-engineer).

curiositech/windags-skills

Fundamental patterns for effective agentic behavior. Teaches decomposition, tool orchestration, error recovery, context management, quality self-assessment, and knowing when to stop. Model-agnostic principles that make any agent more effective regardless of domain. Activate on: "how should I structure this agent", "agentic workflow", "agent patterns", "multi-step task", "tool orchestration", "/agentic-patterns", "decompose this", "agent best practices", "chain of actions", "when should the agent stop", "agent loop design". NOT for: creating agent infrastructure (use agent-creator), building DAGs (use windags-architect), specific tool implementation.

curiositech/windags-skills

Automated discovery and matching of agent skills for dynamic task routing and capability assessment

curiositech/windags-skills

Cryptographic security for agentic systems — zero-trust agent networking, signed message envelopes (JWS/JWE), capability-based security (ocaps), Merkle tree audit trails, WASM sandboxing, and formal verification. Covers CLI dev tool security, mTLS between agents, permission boundaries (least privilege for AI agents), and supply chain security for skills/plugins. Activate on: "agent security", "zero trust agents", "secure agent communication", "capability-based security", "ocap", "signed messages between agents", "agent audit trail", "sandbox agent execution", "agent permissions", "mTLS agents", "cryptographic verification", "agent supply chain", "OWASP agentic", "prove agent did X", "tamper-proof agent logs". NOT for: application-level SAST scanning (use security-auditor), network firewall rules (use infrastructure), SOC2/HIPAA compliance (organizational), or prompt injection defense (use prompt-engineer).

curiositech/windags-skills

Data structures and serialization formats for agent-to-agent communication. Covers message envelopes, structured output schemas, capability declarations, task handoff payloads, error/retry signaling, and context windows as data structures. Deep comparison of A2A protocol, MCP, OpenAI function calling, and LangChain message types. Teaches when to use rigid schemas vs free-form with validation, typed vs untyped, streaming vs batch. Activate on: "agent message format", "agent communication schema", "agent-to-agent protocol", "A2A protocol", "MCP message format", "structured output for agents", "agent interop", "interchange format", "agent serialization", "task handoff format", "capability declaration". NOT for: what agents say to each other (use agent-conversation-protocols), orchestration topology (use multi-agent-coordination), building agent infrastructure (use agentic-infrastructure-2026).

curiositech/windags-skills

Logic-based agent programming language implementing BDI architecture for practical autonomous agent development

curiositech/windags-skills

>- Design AgentSpeak(L)-style BDI agents with context-guarded plans, selection functions, and intention stacks. Use for interruptible autonomy, agent policy, and multi-agent orchestration in dynamic environments. NOT for simple rule engines, static planners, or centralized workflows.

curiositech/windags-skills

Foundational concurrent computation model where actors communicate exclusively through asynchronous message passing

curiositech/windags-skills

license: Apache-2.0 NOT for unrelated tasks outside this domain.

相關技能