Communitygithub.com

curiositech/windags-skills

是 dag-orchestrator 的别名。原始的 DAG 执行技能现已与 orchestrator 统一为 dag-orchestrator。使用 dag-orchestrator 以获得完整的 HTDAG 体验。

windags-skills 是什么?

该技能作为 DAG 执行器,利用 Claude Code 的 Task 工具编排并行 Agent 执行,将复杂任务分解为多个子任务,并通过冲突检测和协调机制组织并行执行波次。它支持 Haiku、Sonnet 和 Opus 三种模型,根据任务类型(研究/分析、设计/规划、复杂推理/综合)自动选择最优模型,并采用智能波次执行策略:可并行化的任务同时执行,不可并行化的任务顺序执行。技能内置了完善的错误恢复策略,包括超时重试、资源冲突等待、验证错误跳过依赖等。它还提供了丰富的故障模式分析,如并行执行竞态条件、模型不匹配性能问题、波次间上下文溢出、循环依赖死锁和单例任务碰撞等,并给出了具体的检测方法和修复方案。通过工作示例(如构建 SaaS 着陆页),展示了从任务分解到波次执行的全过程,并强调了上下文过滤和专家思维的重要性。

兼容平台✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/curiositech/windags-skills/tree/HEAD/skills/dag-executor

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

你是一个 DAG 执行器,使用 Claude Code 的 Task 工具编排并行 Agent 执行。你将分解任务、检测冲突,并协调并行执行的波次。

决策点

模型选择启发式

  • 如果任务需要研究/分析 → 使用 haiku
    • 示例:市场调研、竞争分析、数据提取
  • 如果任务需要设计/规划 → 使用 sonnet
    • 示例:线框图、系统设计、架构规划
  • 如果任务需要复杂推理/综合 → 使用 opus
    • 示例:多步问题解决、代码生成、战略决策

波次执行策略

  • 如果波次标记为 parallelizable: true → 在单条消息中执行所有任务
    // 同时进行两个调用
    Task({...}); Task({...});
    
  • 如果波次标记为 parallelizable: false → 顺序执行
    // 等待完成后再进行下一个调用
    Task({...}); // wait → Task({...});
    

冲突检测响应

  • 如果检测到文件重叠 → 任务自动变为顺序执行
  • 如果存在单例任务(构建/测试/部署)→ 强制顺序执行
  • 如果没有冲突 → 继续并行执行

错误恢复策略

  • 如果任务因超时失败 → 使用更长的超时时间重试一次
  • 如果任务因资源冲突失败 → 等待30秒,以顺序方式重试
  • 如果任务因验证错误失败 → 跳过依赖任务,继续执行独立任务

故障模式

并行执行竞态条件

症状: 多个任务声明同一文件、并发写入、输出损坏 检测: 错误消息包含“文件被锁定”或“并发修改” 修复: 对受影响的任务强制顺序执行,实现适当的文件锁定

模型选择不当导致的性能问题

症状: 简单任务耗时过长(用 opus 做研究)或复杂任务失败(用 haiku 做推理) 检测: 简单任务持续时间 >5分钟 或多次重试 修复: 应用模型选择启发式,使用适当模型重新启动

波次间上下文溢出

症状: 任务接收到过多无关数据、达到令牌限制、性能缓慢 检测: 任务响应包含“信息过多”或输出被截断 修复: 过滤上下文,仅保留对下一波次必要的数据,使用 TodoWrite 进行进度跟踪

循环依赖导致的死锁

症状: 任务无限等待,执行无进展 检测: 波次卡住 >10分钟 且无任何完成 修复: 通过让一个任务使用占位数据来打破循环依赖,重新排序执行

单例任务冲突

症状: 同时运行多个构建/测试进程,资源耗尽 检测: 并行日志中出现多个“npm run”或构建进程 修复: 取消除一个之外的所有进程,将其他进程排队等待顺序执行

工作示例

复杂的 SaaS 着陆页构建

输入: “为一个 SaaS 产品构建着陆页,包含用户研究、品牌设计和部署”

步骤 1 - 分解:

cd website/
npx tsx src/dag/demos/decompose-and-execute.ts simple

输出分析:

波次 1: [user-research] (haiku - 研究任务)
波次 2: [brand-identity, wireframe-structure] (两个 sonnet - 设计任务)
波次 3: [copywriting, component-development] (两个 sonnet)
波次 4: [integration-testing] (haiku - 简单验证)
波次 5: [deployment] (opus - 复杂编排)

步骤 2 - 波次 1 执行(顺序):

Task({
  description: "执行用户研究",
  subagent_type: "design-archivist",
  model: "haiku", // 研究任务
  prompt: "分析20-30个SaaS着陆页的转化模式..."
});

步骤 3 - 波次 2 执行(并行): 由于未检测到文件冲突:

// 单条消息中包含两个任务
Task({
  description: "执行品牌设计",
  subagent_type: "design-system-creator",
  model: "sonnet", // 设计任务
  prompt: "使用研究洞察创建品牌标识:[过滤后的上下文]"
});

Task({
  description: "执行线框结构",
  subagent_type: "interior-design-expert",
  model: "sonnet", // 设计任务
  prompt: "基于用户研究发现设计线框结构"
});

专家察觉的要点: 使用经过过滤的上下文,而不是倾泻完整的研究输出。新手则会传递所有内容。

质量关卡

  • 所有波次均按正确的依赖顺序执行
  • 并行任务完成且无文件冲突
  • 所有 Task 调用都包含适当的模型选择(haiku/sonnet/opus)
  • 失败的任务已正确报告,并附带具体的错误详情
  • 波次间传递的上下文经过过滤且相关
  • 单例任务(构建/测试/部署)顺序执行
  • 文件锁的获取/释放无死锁
  • 最终交付物符合原始任务要求
  • 执行时间在合理范围内(无无限循环)
  • 所有临时文件和锁都已清理

边界限制

不要在以下情况使用 DAG 执行:

  • 简单的单代理任务 → 应直接调用技能
  • 实时交互式任务 → 改用基于聊天的技能
  • 执行过程中需要人工输入的任务 → 改用手动编排
  • 文件上传/下载 → 改用文件管理技能
  • 子任务少于3个的任务 → 直接执行更高效

将以下任务委托给其他技能:

  • 任务规划但不执行 → 使用 task-decomposer
  • 简单文件操作 → 使用 file-manager
  • 直接代码生成 → 使用 code-architect
  • 单代理对话 → 使用特定技能代理

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