Communitygithub.com

curiositech/windags-skills

將危機決策研究應用於代理路由、不確定性分流以及時限壓力系統中的協調失效分析。適用於診斷交接失敗、分析癱瘓或在資訊不完全下做出專家判斷。不適用於常規編碼、簡單的 CRUD 設計或資訊完整的靜態單一代理任務。

windags-skills 是什麼?

這個技能將危機決策研究的關鍵概念——如辨識為主的決策、行為層級路由、認識論不確定性以及回顧性偏差——轉化為一個可操作的框架,用於設計和診斷在時間壓力下運作的AI代理系統。它幫助工程師決定系統何時應快速且自動地反應(技能層級)、何時應遵循模式化規則(規則層級)以及何時應進行深思熟慮的分析(知識層級)。該技能提供了一個用於路由決策點、分流資訊請求以及調整學習管線以適應回顧性敘事扭曲的結構化流程。它沒有針對特定平台(例如Claude Code、Cursor),提供了一個與代理無關的認知架構,適用於任何多代理協調情境。特別是在診斷交接失敗、分析癱瘓或集體協調失效時,該框架能確保系統評估理解並解決根本原因,而非僅根據表面現象或事後合理化來進行最佳化。

相容平台✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/curiositech/windags-skills/tree/HEAD/skills/a-discussion-of-decision-making-applied

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

事件指揮決策智慧

當困難不在於產出選項,而在於判斷當前情境實際上需要多少辨識、分析、資訊收集與協調紀律時,請使用此技能。

使用時機

  • 多代理或人機協作系統在時間壓力增加時,會做出更差的決策。
  • 交接、指揮權轉移或跨團隊協調失敗,即使每個組成部分看起來都各自稱職。
  • 系統因資訊不完整而猶豫不決,且無人知道接下來該學習什麼。
  • 事後檢討或案例研究衍生的訓練集可能受到回溯性合理化的污染。
  • 你需要根據行為層級(自動、規則導向或完全分析)來路由工作。

不適用邊界

此技能並非主要用於:

  • 需求明確且無重大不確定性的常規實作工作。
  • 靜態的單一代理任務,且執行期間環境不會改變。
  • 窮舉最佳化成本低廉且延遲無懲罰的問題。
  • 不涉及專家判斷、協調或在壓力下行動的純粹機率估計任務。

核心心智模型

辨識先於列舉

在時間壓力下,專家通常不會比較一個排序後的選項集合。他們辨識情境類型、浮現第一個可行的回應、進行心智模擬,並且僅在模擬失敗時才擴大搜尋範圍。

行為層級路由

使用 Rasmussen 的層級作為路由紀律:

  • 技能層級:針對穩定且反覆演練的情境,採用自動化或預設好的回應。
  • 規則層級:根據模式觸發的規則應用,並進行適度的調整。
  • 知識層級:針對新穎、模糊或高風險的框架突破,進行明確的推理。

關鍵風險在於不匹配。對技能層級的工作進行知識層級處理會浪費時間。而對知識層級的問題進行技能層級自動化則是災難性錯誤。

認識論不確定性

在危機情境中,不確定性通常是關於未知的事物,而不是固有的隨機性。問題變成了「哪個缺失的事實最可能改變行動」,而不是「如何拖延直到確定性出現」。

回顧性扭曲

案例研究和訪談往往重建的是「應該發生什麼」,而非「實際發生什麼」。觀察到的痕跡比事後整理乾淨的敘述更值得信賴。

個人卓越 vs. 系統可靠性

優秀的局部判斷並不能保證系統層級的成功。邊界失效、通道過載以及權威不匹配可能會壓垮出色的個人決策。

決策點

請參閱 diagrams/01_flowchart_decision-points.md 中的簡潔路由圖。

flowchart TD
  A[決策問題] --> B{時間壓力高或資訊碎片化?}
  B -->|是| C{強模式匹配?}
  B -->|否| D[使用一般規則或分析式處理]
  C -->|是| E[辨識為主的行動加上快速模擬]
  C -->|否| F[知識層級推理加上目標性探查]
  E --> G[行動並設定更新檢查點]
  F --> G

1. 選擇行為寄存器

  • 僅在情境確實熟悉、時間壓力有意義且自動化已經過驗證時,才使用技能層級處理。
  • 當已知的行動計畫適用但仍需情境參數化時,使用規則層級處理。
  • 當框架有爭議、情境新穎,或者錯誤的簡化會帶來高昂代價時,使用知識層級推理。

2. 決定要獲取哪些資訊

  • 找出最可能改變所選行動的那一個缺失事實。
  • 在進行廣泛探索性搜尋之前,先獲取該事實。
  • 如果沒有可預見的探查會改變行動,則以當前最佳估計行動,並建立一個明確的更新檢查點。

3. 決定如何從事件中學習

  • 偏好觀察痕跡、時間戳記、訊息歷史和行為日誌,而不是事後修飾的記憶。
  • 將可疑的乾淨敘述視為關於理想狀態的教材,而非真實認知的實際情況。
  • 將行動原因與系統原因分開,以免事後檢討淪為指責。

失效模式

1. 分析癱瘓

症狀: 選項生成擴大,但行動品質並未提升。 檢測規則: 新的替代方案持續出現,但沒有一個能實質改變近期決策。 復原: 切換至第一個可行選項的辨識為主演練模擬,並為進一步搜尋設定時間盒。

2. 行為層級不匹配

症狀: 系統對穩定的任務過度推理,或者對新穎情況進行自動化處理。 檢測規則: 回應風格與情境的真實新穎性和模糊性不符。 復原: 在更換工具或模型之前,先將任務重新分類為 SB、RB 或 KB。

3. 資訊囤積

症狀: 系統不斷要求更多資料,但行動計畫並未改變。 檢測規則: 所獲取的資訊主要增加了信心,而非改變了決策。 復原: 按照行動影響程度對探查進行排序,並停止收集低槓桿效應的資料。

4. 回顧性過擬合

症狀: 訓練或事後檢討的結論變得比原始事件更乾淨、更理性。 檢測規則: 解釋趨向於優雅的故事,但這些故事缺乏即時痕跡的有力支持。 復原: 降低自我報告證據的權重,並圍繞重建的步驟標註不確定性。

5. 協調盲點診斷

症狀: 每個組成部分在局部審查中都通過,但整個系統仍然失敗。 檢測規則: 解釋停留在個人層級,儘管失敗出現在交接或共享通道。 復原: 在重新訓練個體行動者之前,先審計傳輸點、角色邊界和資訊流。

範例

範例 1:緊急事件路由

一個編排層在即時故障期間收到大量警報。一個天真的系統會列舉所有可能的回應者序列而陷入停滯。使用此技能,你將問題分類為 RB/KB 邊界工作,選擇第一個可信的圍堵行動,模擬接下來的三個步驟,並且僅請求可能逆轉圍堵選擇的那一個缺失訊號。

範例 2:事後檢討訓練資料分流

一份修飾過的意外事件審查聲稱指揮官在行動前冷靜評估了三種替代方案。但即時聊天記錄顯示的是一個模式辨識跳躍,加上一個快速的可行性檢查。該技能將敘述歸類為「作為教條有用,但作為行為痕跡權重低」,並保護訓練集免受回顧性扭曲的影響。

品質關卡

  • 在選擇推理深度之前,明確將任務分類為 SB、RB 或 KB。
  • 按資訊可能改變行動的程度進行排序。
  • 事後檢討應將個人決策品質與協調品質分開。
  • 回顧性敘述應標記為觀察型、自我報告型或混合型。
  • 架構應有明確的交接與指令傳輸審計,而不僅僅是組件層級的評分。

參考檔案

檔案載入時機
references/recognition-primed-decision-making-for-agents.md設計辨識優先的動作選擇或修正選項列舉偏差時
references/three-behavior-levels-for-agent-routing.md根據 SB/RB/KB 層級路由任務,或按認知寄存器分解工作時
references/epistemic-uncertainty-and-information-triage-in-crisis-systems.md在時間壓力下對缺失資訊進行分流時
references/crisis-decision-failures-taxonomy-for-agent-systems.md審查決策病理學和進行事前失效檢查時
references/coordination-failure-modes-in-multi-agent-crisis-systems.md診斷交接失敗和集體崩潰時
references/the-retrospective-distortion-problem-for-agent-learning.md權衡案例研究證據和保護學習管線時
references/novice-to-expert-progression-in-agent-capability.md判斷系統對於某任務類別是否足夠專業時
references/the-theory-practice-gap-in-crisis-decision-research.md評估研究模型是否符合運作現實時

反模式

  • 將每個危機決策視為最佳化問題,而非辨識與模擬問題。
  • 在未先說明資訊如何能改變行動之前,就要求更多資訊。
  • 在忽略塑造了失敗的交接結構的情況下,對個別行動者進行評分。
  • 將事後的敘述當作專家認知的直接記錄來使用。

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

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

Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use PROACTIVELY for LLM features, chatbots, AI agents, or AI-powered applications.

curiositech/windags-skills

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

相關技能