Communitygithub.com

curiositech/windags-skills

自動攔截並優化提示詞,使用 prompt-learning MCP 伺服器。透過嵌入索引歷史記錄從效能中學習。採用 APE、OPRO、DSPy 模式。啟動條件:「優化提示詞」、「改善此提示」、「提示工程」,或任何複雜任務請求。需要 prompt-learning MCP 伺服器。不適用於簡單問題(直接回答)、直接指令(直接執行)或對話式回覆(無需優化)。

windags-skills 是什麼?

此技能作為一個有狀態的提示詞優化器,能夠在複雜任務中自動攔截使用者請求,並根據任務複雜度、Token 預算和歷史表現選擇最佳優化策略。它支援多種優化技術:APE(自動提示工程)適用於指令重寫、OPRO(基於提示的優化)適用於參數調整與約束,以及 DSPy 編譯用於多模組流水線。為了避免優化陷阱(如過度優化、模板執著或歷史過擬合),它內建了品質閘門和停止條件。此技能適用於 Claude Code、Cursor 和 Codex 等平台,特別擅長處理需要多步驟推理、技術分析或系統模板建立的任務。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/curiositech/windags-skills/tree/HEAD/skills/automatic-stateful-prompt-improver

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

自動狀態提示詞改善器

決策點

提示詞評估:
├── 簡單問題/指令(什麼、何時、如何)
│   └── 跳過優化 → 直接回答
├── 複雜任務(多步驟、推理、技術性)
│   ├── Token 預算 < 1000
│   │   └── APE:3-5 次迭代
│   ├── Token 預算 1000-5000
│   │   └── OPRO:5-10 次迭代
│   └── Token 預算 > 5000
│       └── DSPy 編譯:10-20 次迭代
└── 可重複使用的模板/系統提示詞
    └── 完整優化搭配歷史檢索

優化技術選擇:
├── 需要指令重寫
│   └── 使用 APE(自動提示工程)
├── 參數調整與約束
│   └── 使用 OPRO(基於提示的優化)
├── 複雜流水線含多個模組
│   └── 使用 DSPy 編譯模式
└── 未知/探索性領域
    └── 混合 APE→OPRO→DSPy 串聯

迭代控制:
├── 連續 3 輪改善 < 1% → 停止
├── 品質分數 > 0.95 → 停止
├── 達到最大迭代次數 → 停止
├── 使用者確認滿意 → 停止
└── 繼續 → 下一迭代

回饋整合:
├── 任務成功(使用者確認/指標良好)
│   └── 記錄正面回饋 + 嵌入以便檢索
├── 任務失敗/品質不佳
│   └── 記錄負面回饋 + 分析失敗模式
└── 結果不明確
    └── 在記錄前要求使用者提供明確回饋

失敗模式

過度優化螺旋

  • 症狀:提示詞膨脹至 500+ Token,包含許多巢狀約束
  • 診斷:追逐遞減回報,而非在「夠好」時停止
  • 修正:應用 80/20 法則——若每次迭代改善低於 5%,則停止

模板執著

  • 症狀:花費迭代在格式/結構上,而非任務清晰度
  • 診斷:混淆了呈現與效能
  • 修正:衡量實際任務成功,而非模板符合度

歷史過擬合

  • 症狀:優化後的提示詞對過去範例有效,但對新輸入失敗
  • 診斷:訓練資料集太狹隘(來自檢索)
  • 修正:在優化中加入多樣化範例,並對保留案例進行測試

能力誤判

  • 症狀:對模型原生處理的任務添加過多輔助結構
  • 診斷:未經測試即假設模型限制
  • 修正:在大量提示前先測試基準能力

衡量盲目性

  • 症狀:多次迭代卻無明確的成功指標
  • 診斷:在不知「更好」的定義下進行優化
  • 修正:在第一步就定義可衡量的成功標準

工作範例

範例 1:程式碼優化請求

原始內容:「讓這段程式碼更好」

def process_data(data):
    results = []
    for item in data:
        if item > 0:
            results.append(item * 2)
    return results

決策點導航:

  1. 評估:複雜任務(需要程式碼分析)→ 觸發優化
  2. 技術選擇:程式碼審查 + 改善 → APE 搭配 5 次迭代
  3. 檢索的背景資訊:歷史中類似的程式碼優化提示詞
  4. 優化後的提示詞:「分析此 Python 函式的效能、可讀性和 Pythonic 模式。識別具體改善:演算法複雜度、記憶體使用、邊界情況和風格。提供重構後的程式碼並附上解釋。」

新手常忽略的:模糊的「更好」未指定標準 專家會注意的:需要明確的維度(效能、風格、邊界情況)

結果:清晰分析列表推導式的機會、邊界情況處理、型別提示

範例 2:推理任務模板

原始內容:「幫我想清楚這個決定」

決策點導航:

  1. 評估:可重複使用的模板 + 推理任務 → 完整優化
  2. 歷史檢索:找到決策框架提示詞(相似度 0.87)
  3. 技術選擇:DSPy 編譯(結構化推理流水線)
  4. 迭代策略:10 輪,衡量決策品質

優化後的模板:

決策分析框架:
1. 情境:清楚陳述決策及其限制
2. 利害關係人:列出受影響方及其利益
3. 選項:產生 3-5 個不同的替代方案
4. 標準:定義成功指標與權重
5. 取捨:根據標準分析每個選項
6. 建議:選擇最佳選項並附上信心水準

應用的品質閘門:模板完整性、可重複使用性分數、使用者滿意度

範例 3:模糊的技術請求

原始內容:「設定監控」

決策點導航:

  1. 評估:規格不足 + 技術性 → 觸發優化
  2. 釐清策略:OPRO 搭配約束引出
  3. 領域背景:檢索監控設定模式

優化後的提示詞: 「設計監控設定,指定:(1) 基礎設施範圍(伺服器、容器、應用程式),(2) 關鍵指標(效能、可用性、業務),(3) 警示閾值與升級, (4) 技術棧限制,(5) 預算/複雜度限制。提供實作藍圖並標明優先順序。」

前後取捨:

  • 優化前:無止盡的一來一回釐清
  • 優化後:一次交換即可完成結構化需求收集
  • 成本:初始提示詞較長
  • 效益:一次回合完成完整規格

品質閘門

呼叫 optimize_prompt 前的執行前檢查清單:

  • 任務複雜度分數 > 3(需要多步驟/推理)
  • 已定義或可推導出明確的成功標準
  • Token 預算已估算,技術已選擇
  • 已識別領域背景以便檢索
  • 根據複雜度設定了迭代限制

最佳化後驗證:

  • 優化後的提示詞具體且可操作
  • 成功指標可衡量
  • 限制連貫性驗證(無矛盾)
  • Token 效率:改善正當化了增加的長度
  • 歷史背景已適當整合
  • 重大變更已獲得使用者確認

品質評分標準(0-100):

  • 清晰度:新手使用者能理解需求嗎?(25 分)
  • 具體性:具體 vs. 抽象指令?(25 分)
  • 完整性:涵蓋邊界情況與限制嗎?(25 分)
  • 效率:在不冗贅的情況下達成目標嗎?(25 分)

不適用範圍

請勿將此技能用於:

  • 簡單事實性問題 → 直接使用知識回答
  • 不涉及推理的檔案操作 → 使用檔案管理技能
  • 直接指令執行 → 立即執行
  • 對話式回覆 → 自然回應
  • 已經優化過的提示詞 → 先檢查歷史以避免重複優化
  • 使用者明確表示「不要優化」 → 尊重使用者偏好

請委派給:

  • 數學問題 → 使用以計算為主的技能
  • 創意寫作 → 使用創意寫作技能(除非需要創建模板)
  • 資料分析 → 使用資料分析技能(除非需要複雜推理)
  • 除錯 → 使用除錯技能(除非需要系統性改善)

需要判斷的灰色地帶:

  • 中等複雜度任務(分數 2-4) → 先測試基準效能
  • 領域專業請求 → 僅在具有可重複使用模板潛力時優化
  • 後續問題 → 僅在顯著擴大範圍時優化

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