Communitygithub.com

專家任務分析與能力設計

應用認知任務分析法,解析專家工作中依賴感知線索、分支判斷與持續監控迴圈的作業。用於將專家能力分解為代理架構、模擬設計或驗證訪談。不適用於單純的步驟式SOP捕獲或沒有隱性線索層的簡單流程。

專家任務分析與能力設計 是什麼?

此技能旨在幫助開發者或AI代理系統使用者,將人類專家的深層認知能力轉化為可實現的代理架構、模擬環境或訓練系統。它聚焦於專家表現中「難以言傳」的部分,也就是那些感知觸發點(例如聲音變化、線索張力)、持續監控迴圈以及基於情境的判斷分支,而非僅僅是表面流程。技能強調「科學層」與「藝術層」的分離,前者是可敘述的程序,後者是專家實際依賴的感知線索。支援的平臺包括任何需要建構專家行為模型的情境,例如 Claude Code、Cursor、Codex 等代理系統的任務設計。其運作方式基於認知任務分析(CTA)方法,如臨界決策法(CDM)和臨界線索清單,並要求透過多專家驗證來彌補單一專家模型的盲點。簡而言之,這個技能是橋接人類專家直覺與AI代理結構化行為的關鍵工具。

相容平台✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/curiositech/windags-skills/tree/HEAD/skills/a-task-analysis-of-pier-side-ship-handli

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

專家任務分析與能力設計 是做什麼的?

當任務模型看似程序完整,但仍缺少區分專家表現與檢查清單的感知觸發點、監控迴圈與工具使用習慣時,請使用此技能。

使用時機

  • 你需要將專家表現轉化為代理架構、模擬器或訓練環境。
  • 書面SOP說明了步驟,但未說明專家如何知道該選擇哪個分支。
  • 系統在正常情況下運作,但在依賴情境判斷的邊緣案例上失敗。
  • 你正在訪談領域專家,需要一種提取隱性知識的方法,而不僅僅是敘述程序。
  • 一個有向無環圖或編排樹需要持續的監控迴圈,而不僅僅是單次順序節點。

不適用範圍

此技能不適合以下情況的主要工具:

  • 簡單、確定性的工作流程,其中明確的流程已能完整涵蓋整個任務。
  • 不依賴感知模式識別的低風險自動化。
  • 事後的文件化練習,無需針對真實專家表現進行驗證。
  • 模擬中視覺真實性比決策的線索準確度更重要。

核心心智模型

科學層 vs. 藝術層

專家表現具有一個專家通常能說明的陳述層,以及一個通常只在專家被逼問分支點時才會顯現的感知層。GOMS 捕捉前者。臨界線索清單和臨界決策法訪談則是恢復後者的方法。

線索是承載結構的

喚醒模式、線索張力、聲音變化或微妙的相對位置關係並非裝飾性細節。它們是專家選擇的實際輸入。如果系統無法「看見」線索,就無法複製專家的決策函數。

附帶選擇規則的層級結構

專家工作是一個帶有局部分支條件的嵌套目標層級結構,而非一串平鋪的步驟。重要的結構不僅是「做什麼」,還有「什麼條件」選擇方法A而非方法B。

持續監控迴圈

許多專家任務依賴於持續評估目標,這些目標與順序動作同時運行。僅對一次性節點進行建模的工作流程會遺失預判能力,並將專業知識轉變為反應。

驗證鴻溝

單一專家的任務模型必然不完整,因為常規工具與設定行為會從意識中消失。驗證並非選擇性的修飾步驟;它是使缺失的任務結構顯見的方法。

決策點

請參閱建模流程圖:diagrams/01_flowchart_decision-points.md

flowchart TD
  A[需要專家能力模型] --> B[分解目標與方法]
  B --> C{分支點是否可以程序性說明?}
  C -->|是| D[記錄明確的選擇規則]
  C -->|否| E[探索感知線索]
  D --> F{需要持續監控?}
  E --> F
  F -->|是| G[建立監控迴圈與冗餘感知模型]
  F -->|否| H[保留順序子目標]
  G --> I[透過更多專家或軌跡進行驗證]
  H --> I

1. 決定適當的分解粒度

  • 在第一次出現有意義的方法選擇時停止分解。
  • 如果分支條件仍然隱藏,則深入分解並探索選擇該分支的線索。
  • 如果沒有剩餘的分支點,你現在正在記錄執行細節,而非任務架構。

2. 決定使用何種知識提取方法

  • 對於明確的程序和工具順序,使用結構化分解。
  • 當專家說「我就是知道」或「看情況」時,使用臨界決策法探針。
  • 當第一個模型異常乾淨或缺乏工具使用時,使用多專家驗證。

3. 決定模擬什麼

  • 模擬實際觸發分支決策的線索。
  • 在專家依賴多個管道時,加入冗餘感知。
  • 省略不影響線索識別或選擇品質的美觀細節。

失敗模式

1. 扁平檢查清單捕獲

症狀: 任務模型讀起來順暢,但一旦環境偏離便失敗。 檢測規則: 分支條件缺失或隱藏在敘述中,而非明確的選擇規則。 恢復方式: 將檢查清單轉換為帶有線索連結分支點的目標層級結構。

2. 無線索模擬

症狀: 受訓者或代理在模擬器中成功,但在實際部署中失敗。 檢測規則: 模擬重現了程序,但未重現專家用來選擇程序的訊號。 恢復方式: 建立臨界線索清單,並圍繞線索準確度重新設計環境。

3. 單一管道脆弱性

症狀: 一個嘈雜或缺失的輸入導致整個決策過程崩潰。 檢測規則: 關鍵判斷完全依賴於單一來源。 恢復方式: 加入冗餘管道與明確的交叉檢查行為。

4. 單一專家盲點

症狀: 基本工具或情境設定動作從未出現在第一個模型中。 檢測規則: 驗證專家立即提及遺漏的設備、常規或監控行為。 恢復方式: 將分歧視為缺失結構的證據,而非雜訊。

5. 純順序架構

症狀: 系統能對事件做出反應,但無法維持持續評估。 檢測規則: 所有節點都是一次性任務,沒有代表持續監控目標的節點。 恢復方式: 加入明確的監控迴圈,包含預測-觀察-比較-調整的行為。

操作範例

範例1:將專家判斷轉化為代理樹

一位航運領域專家提供了靠港的程序敘述。初稿被乾淨地分解為步驟,但當水流、拖船可用性和纜繩行為同時變化時仍然失敗。此技能在相關分支點加入了選擇規則,記錄了驅動這些選擇的線索清單,並引入了持續監控迴圈,而非僅有順序節點。

範例2:模擬保真度分流

一個訓練模擬器完美渲染了水面、船隻和碼頭幾何形狀,但受訓者仍然會越過停止點。認知任務分析(CTA)揭示了專家依賴相對於固定岸上參考物的相對運動以及纜繩張力線索,而模擬器從未強調這些。此技能將設計工作導向這些線索,而非更多視覺修飾。

品質關卡

  • 任務模型區分了明確程序與感知線索知識。
  • 分支點包含了選擇每個方法的線索或條件。
  • 持續監控目標與一次性順序目標分開建模。
  • 在專家依賴的關鍵決策處,有冗餘資訊管道。
  • 至少一次驗證過程使用額外的專家或軌跡來挑戰模型。

參考檔案

檔案載入時機
references/goms-task-decomposition-for-agent-systems.md建立目標層級結構或決定分解深度時
references/critical-cue-inventories-for-agent-perception.md恢復決策點的感知觸發器時
references/knowledge-elicitation-methodology-for-agent-capability-building.md執行CTA或臨界決策法訪談時
references/validation-gap-what-experts-dont-know-they-know.md對初稿任務模型進行壓力測試時
references/redundant-sensing-in-multi-channel-environments.md設計穩健的多通道感知時
references/the-art-science-gap-transfer-to-simulation.md決定哪些模擬細節會實質影響技能轉移時
references/situation-awareness-and-the-conning-officers-mental-model.md建立監控迴圈與偏差檢測模型時

反模式

  • 將「隱性知識」視為結束探究的標籤,而非需要更深入挖掘的信號。
  • 只捕獲程序,然後將結果稱為專家模型。
  • 為美學真實性而非線索準確度設計模擬。
  • 在自動化隱藏了最重要結構的領域中,假設單一專家模型就足夠完整。

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