Communitygithub.com

curiositech/windags-skills

通过级联近似、自我改进和异构评估解决棘手问题的战略模式,源自DeepMind的AlphaGo系统。

windags-skills 是什么?

该技能借鉴DeepMind AlphaGo的核心架构理念,提供一套用于解决计算资源有限下的复杂决策问题的系统化方法。它指导开发者根据问题空间的大小、准确性与延迟需求以及评估器错误模式,选择合适的评估策略,例如单评估器、级联近似或自适应分配。技能详细阐述了五种关键失败模式(如架构膨胀、同步耦合、代理指标固化)及其检测与修复方法,并提供了如代码审查场景的实战示例。该技能支持Claude Code等平台,通过质量门和边界定义确保正确应用,帮助开发者构建高效、鲁棒的AI代理系统。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/curiositech/windags-skills/tree/HEAD/skills/alphago-deep-rl

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

AlphaGo 架构技能

决策点

何时使用单个评估器 vs. 级联评估器

问题特征:
├── 搜索空间可处理 (b^d < 10^9)
│   └── 使用单个最佳评估器 → 标准优化
└── 搜索空间不可处理 (b^d > 10^12)
    ├── 有统一的评估预算
    │   └── 使用级联近似:
    │       1. 快速剪枝(策略网络)→ 收窄波束
    │       2. 中等评估(价值网络)→ 估计质量
    │       3. 廉价探索(模拟)→ 广度覆盖
    └── 非统一评估预算
        └── 自适应分配:
            ├── 关键位置 → 昂贵评估
            └── 常规位置 → 廉价启发式

准确度与延迟需求决策树

系统要求:
├── 延迟关键型(<1ms 响应)
│   ├── 准确度容忍度高(>10% 错误可接受)
│   │   └── 仅快速模拟(2µs/评估)
│   └── 准确度容忍度低(<5% 错误)
│       └── 缓存的策略网络 + 启发式回退
├── 延迟中等(1-100ms 响应)
│   ├── 需要高准确度
│   │   └── 价值网络(3ms)+ 策略网络引导
│   └── 平衡准确度/速度
│       └── 混合评估:λ=0.5 价值 + 模拟
└── 延迟容忍型(>100ms)
    └── 完整级联:策略 → 价值 → 模拟,配合 MCTS

错误模式多样性评估

选择多个评估器时:
├── 所有评估器具有相似的失败模式
│   └── 使用单个最佳评估器(无多样性收益)
├── 评估器有互补错误
│   ├── 快速/噪声 + 慢速/准确配对
│   │   └── 混合 λ=0.3-0.7(偏向准确)
│   ├── 保守 + 探索配对
│   │   └── 混合 λ=0.5(等权重)
│   └── 学习 + 手工配对
│       └── 基于置信度分数的动态混合
└── 未知错误相关性
    └── 实证测试:在保留集上衡量性能

失败模式

架构膨胀(检测:>5 个近似层)

症状:添加更多近似层但收益递减 根本原因:每层增加开销而无成比例准确度提升 修复:分析计算成本与准确度提升;移除投资回报率低的层 检测规则:如果增加第 N 层准确度提升 <5% 但延迟增加 >20%,则出现架构膨胀

同步耦合(检测:快速组件空闲等待)

症状:CPU 利用率下降,同时等待 GPU 评估 根本原因:快速搜索与慢速神经网络评估之间的紧耦合 修复:实现带陈旧值容忍的异步队列 检测规则:如果快速组件(搜索、模拟)空闲时间 >50%,则出现同步耦合

代理指标固化(检测:指标改善但性能下降)

症状:走子预测准确度提高但胜率下降 根本原因:优化模拟人类行为而非客观成功 修复:从监督学习切换到带真实目标的强化学习 检测规则:如果代理指标和结果指标连续 10 次评估趋势相反,则出现代理指标固化

单一评估器谬误(检测:拒绝“更差”的单个组件)

症状:因为价值网络具有更高的个体准确度而丢弃模拟 根本原因:假设最佳个体组件构成最佳系统组件 修复:经验性地测试混合性能;多样性通常胜过个体质量 检测规则:如果依据个体性能选择组件而不测试组合,则出现单一评估器谬误

统一预算分配(检测:对所有决策使用相同计算量)

症状:在明显走子和关键位置上花费相同的评估时间 根本原因:未将计算预算适应于决策重要性 修复:基于位置不确定性和结果敏感性实现自适应分配 检测规则:如果各位置的评估时间方差小于平均值的 20%,则出现统一分配

实战示例

为代码审查实现级联近似

场景:设计 AI 系统审查有 50-500 行变更的拉取请求,需要 <10s 响应时间,必须捕获 95% 的错误。

第一步:分析计算约束

  • 静态分析:每个文件 10ms
  • ML 错误检测器:每个文件 2s
  • 深度语义分析:每个文件 30s
  • 可用预算:总计 10s

第二步:应用级联决策树 根据“搜索空间不可处理”路径,因为穷举分析超出预算:

  1. 快速剪枝层(静态分析):排除没有复杂性变更的文件
  2. 中等评估层(ML 检测器):对剩余文件评分,评估错误可能性
  3. 昂贵分析层(语义):仅对最高分文件进行深度分析

第三步:预算分配策略

  • 保留 2s 用于对所有剩余文件进行 ML 评估
  • 基于 ML 评分分配剩余 8s 给语义分析
  • 评分 >0.8 的文件:每个 4s(最多 2 个文件)
  • 评分 0.5-0.8 的文件:每个 2s
  • 评分 <0.5 的文件:仅使用 ML 结果

第四步:混合评估实现 不使用“最佳”评估器(语义分析),而是混合 ML 和语义分数:

  • ML 检测器:快速,擅长模式匹配,但遗漏新型错误
  • 语义分析:慢速,捕获复杂逻辑错误,误报率高
  • 混合 λ=0.6:最终分数 = 0.6 * 语义 + 0.4 * ml

新手方法:对所有内容运行语义分析 → 前几个文件后超时 专家洞察:级联允许将昂贵计算仅用于最重要的地方,同时确保每个文件获得某种评估

质量门

[ ] N 个评估器已测试:实现并基准测试了至少 3 个具有不同速度/准确度配置的评估器 [ ] 错误相关性已测量:计算成对相关矩阵,显示评估器在测试集上的相关性 <0.7 [ ] 混合与单个已评估:实证比较显示混合性能优于最佳个体组件 >5% [ ] 延迟要求已满足:完整级联下,第 95 百分位响应时间低于指定阈值 [ ] 准确度要求已满足:保留集上的错误率满足指定阈值(例如,<5% 假阴性率) [ ] 预算分配已分析:计算成本分解显示预算根据决策重要性进行分配 [ ] 失败模式已测试:在对抗条件下(分布偏移、资源约束、边缘情况)测试系统 [ ] 异步协调已验证:即使慢速组件饱和,快速组件的利用率仍保持 >80% [ ] 可扩展性已验证:负载增加到标称容量的 10 倍时,性能优雅降级 [ ] 监控已配置:指标跟踪代理与结果的校准、组件利用率和级联有效性

非适用边界

不要将此技能用于:

  • 具有可处理搜索空间的简单优化问题 → 改用标准优化
  • 单模型训练或调优 → 改用深度学习训练
  • 需要 <1ms 延迟的实时系统 → 改用低延迟系统
  • 一个评估器明显优于其他且其他评估器无价值的问题 → 改用单模型部署
  • 没有搜索树结构的顺序决策过程 → 改用强化学习基础

当需要以下技能时,委托给其他技能:

  • 需要实现特定神经网络架构 → 深度学习架构
  • 设计分布式系统基础设施 → 分布式系统设计
  • 优化单个组件性能 → 性能优化
  • 处理训练数据收集和标注 → 数据工程
  • 实现特定搜索算法 → 搜索算法

此技能重点针对:在计算约束下协调多个不完美评估器的架构模式,而非单个组件的实现细节。

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