Communitygithub.com

curiositech/windags-skills - 持续在线AI代理应用指南

探索如何利用具有情景记忆的持续在线AI代理构建产品和流程。涵盖具体产品创意、工作流、持久化加记忆带来的涌现能力,以及实际部署案例,帮助你将架构转化为实际应用。

windags-skills - 持续在线AI代理应用指南 是什么?

该技能指南旨在帮助开发者和AI代理用户理解并利用持续在线的AI代理(如Claude Code、Cursor、Codex等平台)结合情景记忆所解锁的新能力。它超越了无状态聊天机器人的局限,专注于回答'它能做什么'这一核心问题。技能文档提供了完整的决策框架,包括判断何时需要构建持续在线代理的ROI计算、按工作流(如编码、会议管理、学习、健康追踪)选择应用模式的决策树,以及范围边界和主动行为校准的指南。此外,它还详细分析了五种关键故障模式(如幻觉记忆、成本失控、隐私泄露)及其检测与修复方法,并通过一个'开发者伴侣代理'的完整构建实例,演示了从范围定义、ROI计算到内存策略和触发设计的全过程。最终,技能通过质量门列表和清晰的'非所属范围'边界,确保用户能快速评估并应用这些概念。

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

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

/always-on-agent-applications — 持久化 + 记忆实际解锁的能力

你正在帮助某人弄清楚可以用一个具有情景记忆的持续在线AI代理构建什么。这是一个关于'那又怎样?'的技能——架构已经存在,输入正在流动,现在它到底能做哪些无状态聊天机器人做不到的事情?

决策点

1. 持续在线 vs 会话式决策树

评估任务需求:
├─ 任务需要跨会话记忆?
│  └─ 否 → 使用会话式代理(更便宜、更简单)
│  └─ 是 ↓
├─ 任务受益于主动行为?
│  └─ 否 → 使用带记忆的定时代理
│  └─ 是 ↓
├─ [持久化投资回报率] > [基础设施成本]?
│  └─ 否 → 从会话式开始,后续升级
│  └─ 是 ↓
├─ 领域范围足够窄以保证记忆质量?
│  └─ 否 → 缩小范围(仅限会议、仅限代码)
│  └─ 是 → 构建持续在线代理

投资回报率计算:

  • 持久化投资回报率 = (任务频率 × 每次任务节省的时间 × 用户每小时价值)
  • 基础设施成本 = (服务器成本 + 存储成本 + 开发时间)

如果投资回报率 > 3倍成本:构建持续在线代理 如果投资回报率在1-3倍成本之间:从会话式开始,先证明价值 如果投资回报率 < 1倍成本:使用现有工具

2. 应用类别选择

用户问“我应该构建什么?”:
├─ 主要工作流是编码?
│  └─ 是 → 开发者伴侣模式
│  └─ 否 ↓
├─ 主要需求是会议/沟通开销?
│  └─ 是 → 个人幕僚长模式
│  └─ 否 ↓
├─ 主要目标是学习/知识工作?
│  └─ 是 → 学习日志模式
│  └─ 否 ↓
├─ 重点是健康/习惯追踪?
│  └─ 是 → 健康观察者模式(高安全敏感性)
│  └─ 否 → 项目编排器或环境智能

3. 范围边界决策

用户提出多领域代理:
├─ 这是他们的第一个持久化代理?
│  └─ 是 → 强制单一垂直领域(选择投资回报率最高的)
│  └─ 否 ↓
├─ 他们有超过6个月的开发时间?
│  └─ 否 → 仅限单一垂直领域
│  └─ 是 ↓
├─ 他们能为每个领域定义成功指标?
│  └─ 否 → 缩小范围直到能够定义
│  └─ 是 → 允许多领域但需分阶段发布

4. 主动行为校准

配置代理中断频率:
├─ 用户工作风格是深度专注块?
│  └─ 是 → 批量通知,尊重专注信号
│  └─ 否 ↓
├─ 用户明确要求高接触协助?
│  └─ 是 → 允许实时中断,但设置相关性阈值
│  └─ 否 ↓
├─ 默认为:80%被动响应,15%被动主动,5%主动主动

故障模式

1. 幻觉记忆综合征

症状:代理自信地引用从未发生过的对话或事件 检测规则:如果代理声称特定的引用/日期/事实但无法提供精确的源时间戳 根本原因:检索到的上下文与生成的响应之间记忆边界模糊 修复:实施严格的记忆引用要求——代理必须将每个声明链接到带有时间戳的特定记忆条目

2. 记忆污染级联

症状:代理性能随时间下降,响应中出现矛盾信息 检测规则:如果代理在7天内对同一主题给出矛盾的建议且未承认变化 根本原因:低质量观察积累速度超过有价值信号 修复:实施记忆卫生:相关性评分、自动压缩、用户触发的记忆清理

3. 成本失控爆炸

症状:月度账单增长30%以上但价值未按比例增加 检测规则:如果每次有用交互的成本在30天内比基线上升50%以上 根本原因:代理过度处理低价值输入(通知、垃圾邮件、自动邮件) 修复:输入过滤管道、记忆访问预算、带自动限流的主动成本监控

4. 范围蔓延麻痹

症状:代理试图处理一切,但一无所长,用户在两周后放弃 检测规则:如果代理拥有超过5个不同的应用垂直领域且每个领域没有明确的成功指标 根本原因:构建“通用助手”而非专注工具 修复:强制从单一垂直领域开始,要求通过毕业标准才能扩展

5. 隐私侵犯漂移

症状:代理意外地在不同上下文中共享敏感信息 检测规则:如果代理在错误上下文中提及个人/工作细节(工作信息出现在个人聊天中) 根本原因:记忆边界未与用户隐私期望对齐 修复:上下文隔离、显式记忆分区、定期隐私审计

实际示例

示例:构建开发者伴侣代理

场景:软件工程师希望代理帮助进行代码审查和PR描述

步骤1 - 范围定义

  • 用户:“我想要一个能帮我更好地编码的AI”
  • 应用决策树:编码工作流 = 开发者伴侣模式
  • 缩小范围:“仅限PR描述生成”(不是完整的编码助手)

步骤2 - 投资回报率计算

  • 任务频率:每天3个PR × 5天 = 每周15个PR
  • 节省时间:每个PR描述5分钟 = 每周75分钟 = 每年65小时
  • 用户价值:$150/小时 × 65小时 = $9,750/年
  • 基础设施成本:约$50/月 = $600/年
  • 投资回报率 = 16倍 → 构建持续在线代理

步骤3 - 记忆策略

  • 核心记忆:当前功能分支、最近5次提交、最近关于代码变更的对话
  • 回忆记忆:用户偏好的PR模板、审查者反馈模式、项目编码标准
  • 归档记忆:历史PR、团队沟通风格、项目决策及理由

步骤4 - 触发器设计

triggers:
  - git_push_to_feature_branch: 起草PR描述
  - pr_opened: 用上下文增强描述
  - code_review_received: 记录反馈模式以供将来使用

步骤5 - 质量门

  • PR描述包含实际理由(而非通用摘要)
  • 代理引用提到的具体提交/文件
  • 80%的生成描述需要少于2分钟编辑
  • 代理正确识别PR何时涉及多个关注点

新手会遗漏什么:从“全能AI编码助手”开始 专家会抓住什么:专注于单一高价值工作流(PR描述),其中持久化相对于无状态解决方案具有明显优势

质量门

应用设计完成时需满足所有条件:

  • 清晰的投资回报率计算显示>3倍成本收益
  • 单一垂直范围,带有定义的边界
  • 记忆增长受限于压缩策略
  • 主动行为频率已配置(少于总交互的20%)
  • 成功指标已定义且可衡量
  • 用户隐私边界已明确映射
  • 冷启动体验可在没有累积记忆的情况下工作
  • 已实现用户记忆控制的终止开关
  • 已设置带自动限流阈值的成本监控
  • 已为范围扩展定义毕业标准

非所属范围边界

不要将此技能用于:

  • 构建记忆架构 → 使用 always-on-agent-architecture 代替
  • 设计输入源和触发器 → 使用 always-on-agent-inputs 代替
  • 安全性、隐私和成本问题 → 使用 always-on-agent-safety 代替
  • 通用代理模式和循环 → 使用 agentic-patterns 代替
  • 评估AI安全风险 → 使用 ai-safety-engineer 代替
  • 技术基础设施决策 → 使用 systems-architecture 代替

当用户询问以下内容时,委托给其他技能:

  • “如何存储情景记忆?” → always-on-agent-architecture
  • “我的代理应该监控哪些数据?” → always-on-agent-inputs
  • “这安全/隐私吗?” → always-on-agent-safety
  • “如何构建代理循环?” → 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.

相关技能