Communitygithub.com

curiositech/windags-skills

探討如何運用具有情節記憶的常駐型 AI 代理來建構產品與實現工作流程,從架構概念到實際應用價值的完整指引。

windags-skills 是什麼?

本技能聚焦於「常駐型 AI 代理」的應用層面,特別是那些具備情節記憶(Episodic Memory)的代理,解釋它們能實現哪些無狀態聊天機器人無法做到的事情。它提供了一套決策框架,幫助開發者判斷何時應該建構常駐型代理(而非基於會話的代理),以及如何選擇最合適的應用類別(如開發者伴侶、個人幕僚、學習日誌等)。技能中詳細說明了四種常見的失敗模式(如幻覺記憶、記憶污染、成本失控、範圍蔓延),並提供具體的檢測規則與修復方法。此外,它透過一個完整的實例(建構 PR 描述生成代理)展示了從範圍定義、ROI 計算到觸發器設計的完整流程。支援的平台包括 Claude Code、Cursor、Codex 等 AI 代理工具,適合想要從「我有架構」進展到「它實際上能為我做什麼」的開發者。

相容平台~Claude Code~Codex CLI~Cursor✓Antigravity
npx skills add https://github.com/curiositech/windags-skills/tree/HEAD/skills/always-on-agent-applications

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

/always-on-agent-applications — 持久性與記憶力真正解鎖了什麼

你正在幫助某人規劃該用一個具有情節記憶的常駐型 AI 代理來建構什麼。這是「所以呢?」的技能 — 架構已經存在,輸入正在流動,現在它到底能做出什麼無狀態聊天機器人做不到的事情?

決策點

1. 常駐型 vs 基於會話的決策樹

評估任務需求:
├─ 任務需要跨會話的記憶?
│  └─ 否 → 使用基於會話的代理(更便宜、更簡單)
│  └─ 是 ↓
├─ 任務能從主動行為中受益?
│  └─ 否 → 使用具有記憶的排程代理
│  └─ 是 ↓
├─ [持久性 ROI] > [基礎設施成本]?
│  └─ 否 → 從基於會話開始,之後再升級
│  └─ 是 ↓
├─ 領域夠狹窄以確保記憶品質?
│  └─ 否 → 縮小範圍(僅限會議、僅限程式碼)
│  └─ 是 → 建構常駐型代理

ROI 計算:

  • 持久性 ROI = (任務頻率 × 每次任務節省的時間 × 用戶每小時價值)
  • 基礎設施成本 = (伺服器成本 + 記憶儲存 + 開發時間)

如果 ROI > 3 倍成本:建構常駐型 如果 ROI 在 1-3 倍成本之間:從基於會話開始,先驗證價值 如果 ROI < 1 倍成本:使用現有工具

2. 應用類別選擇

用戶問「我該建構什麼?」:
├─ 主要工作流程是寫程式?
│  └─ 是 → 開發者伴侶模式
│  └─ 否 ↓
├─ 主要需求是會議/溝通管理?
│  └─ 是 → 個人幕僚長模式
│  └─ 否 ↓
├─ 主要目標是學習/知識工作?
│  └─ 是 → 學習日誌模式
│  └─ 否 ↓
├─ 重點是健康/習慣追蹤?
│  └─ 是 → 健康觀察者模式(安全敏感性高)
│  └─ 否 → 專案協調者或環境智能

3. 範圍邊界決策

用戶提出跨領域代理:
├─ 這是他們第一個常駐型代理嗎?
│  └─ 是 → 強制單一垂直領域(選擇 ROI 最高的)
│  └─ 否 ↓
├─ 他們有超過 6 個月的開發時間嗎?
│  └─ 否 → 僅限單一垂直領域
│  └─ 是 ↓
├─ 他們能為每個領域定義成功指標嗎?
│  └─ 否 → 縮小範圍直到能做到為止
│  └─ 是 → 允許多領域,但需分階段推出

4. 主動行為校準

配置代理打斷頻率:
├─ 用戶工作風格是深度專注時段?
│  └─ 是 → 批次通知,尊重專注訊號
│  └─ 否 ↓
├─ 用戶明確要求高互動協助?
│  └─ 是 → 允許即時打斷,但需符合相關性門檻
│  └─ 否 ↓
├─ 預設值:80% 被動反應,15% 被動主動,5% 主動主動

失敗模式

1. 幻覺記憶症候群

症狀:代理自信地引用從未發生過的對話或事件 檢測規則:如果代理聲稱具體引述/日期/事實,但無法提供確切的來源時間戳 根本原因:檢索到的上下文與生成的回應之間記憶邊界不佳 修復方法:實施嚴格的記憶引用要求 — 代理必須將每個聲明連結到具有時間戳的特定記憶條目

2. 記憶污染級聯

症狀:代理效能隨時間下降,回應中出現矛盾資訊 檢測規則:如果代理在 7 天內針對同一主題給出相互矛盾的建議,且未承認變化 根本原因:低品質觀察累積速度超過有價值訊號 修復方法:實施記憶衛生措施:相關性評分、自動壓縮、用戶觸發的記憶清理

3. 成本失控爆炸

症狀:月度帳單增加 30% 以上,但價值沒有成比例增加 檢測規則:如果每次有用互動的成本在 30 天內比基準線上升超過 50% 根本原因:代理過度處理低價值輸入(通知、垃圾郵件、自動化電子郵件) 修復方法:輸入過濾管道、記憶存取預算、主動成本監控與自動限流

4. 範圍蔓延癱瘓

症狀:代理試圖處理所有事情,但無一精通,用戶在 2 週後放棄使用 檢測規則:如果代理有超過 5 個不同的應用垂直領域,且未為每個領域定義明確的成功指標 根本原因:建構「通用助手」而非聚焦工具 修復方法:強制從單一垂直領域開始,要求設定畢業條件才能擴展

5. 隱私違規漂移

症狀:代理意外地在不同上下文之間分享敏感資訊 檢測規則:如果代理在錯誤的上下文中提到個人/工作細節(在個人聊天中提及工作資訊) 根本原因:記憶邊界與用戶隱私期望不一致 修復方法:上下文隔離、明確的記憶分區、定期隱私審計

實際範例

範例:建構開發者伴侶代理

情境:軟體工程師希望代理協助程式碼審查和 PR 描述

步驟 1 - 範圍定義

  • 用戶:「我想要一個能幫我寫更好程式的 AI」
  • 應用決策樹:寫程式工作流程 = 開發者伴侶模式
  • 縮小範圍:「僅限 PR 描述生成」(非完整的編碼助手)

步驟 2 - ROI 計算

  • 任務頻率:每天 3 個 PR × 5 天 = 每週 15 個 PR
  • 節省時間:每個 PR 描述 5 分鐘 = 每週 75 分鐘 = 每年 65 小時
  • 用戶價值:每小時 $150 × 65 小時 = 每年 $9,750
  • 基礎設施成本:每月約 $50 = 每年 $600
  • ROI = 16 倍 → 建構常駐型代理

步驟 3 - 記憶策略

  • 核心記憶:目前功能分支、最近 5 次提交、關於程式碼變更的近期對話
  • 回顧記憶:用戶偏好的 PR 模板、審查者回饋模式、專案編碼標準
  • 歸檔記憶:歷史 PR、團隊溝通風格、專案決策與理由

步驟 4 - 觸發器設計

triggers:
  - git_push_to_feature_branch: 草擬 PR 描述
  - pr_opened: 用上下文增強描述
  - code_review_received: 記錄回饋模式供未來使用

步驟 5 - 品質閘門

  • PR 描述包含實際理由(非一般性摘要)
  • 代理引用具體的提交/檔案
  • 80% 的生成描述需要少於 2 分鐘的編輯
  • 代理正確識別 PR 何時橫跨多個關注點

新手會錯過的重點:從「萬能 AI 編碼助手」開始 專家會注意的重點:聚焦於單一高價值工作流程(PR 描述),其中持久性對無狀態解決方案具有明顯優勢

品質閘門

當滿足所有條件時,應用設計才算完成:

  • 清晰的 ROI 計算,顯示 >3 倍成本效益
  • 單一垂直領域範圍,含定義的邊界
  • 記憶成長受到壓縮策略的限制
  • 主動行為頻率已配置(低於總互動的 20%)
  • 成功指標已定義且可衡量
  • 用戶隱私邊界已明確標示
  • 冷啟動體驗無需累積記憶即可運作
  • 已實施用戶記憶控制的終止開關
  • 已設定成本監控與自動限流閾值
  • 已定義範圍擴展的畢業條件

非適用範圍

請勿將此技能用於:

  • 建構記憶架構 → 請改用 always-on-agent-architecture
  • 設計輸入來源與觸發器 → 請改用 always-on-agent-inputs
  • 安全、隱私與成本問題 → 請改用 always-on-agent-safety
  • 通用代理模式與循環 → 請改用 agentic-patterns
  • 評估 AI 安全風險 → 請改用 ai-safety-engineer
  • 技術基礎設施決策 → 請改用 systems-architecture

當用戶詢問時,委派給其他技能:

  • 「如何儲存情節記憶?」 → always-on-agent-architecture
  • 「我的代理應該監看哪些資料?」 → always-on-agent-inputs
  • 「這樣安全/私密嗎?」 → always-on-agent-safety
  • 「如何建構代理循環?」 → agentic-patterns

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