Design directed acyclic graphs of agent nodes for multi-agent workflows.
npx skills add https://github.com/curiositech/port-daddy --skill windags-architect
Please help me install this Agent Skill. Skill: windags-architect Source: https://github.com/curiositech/port-daddy/tree/main/skills/windags-architect Command: npx skills add https://github.com/curiositech/port-daddy --skill windags-architect
WinDAGs Architect provides a comprehensive framework to design, execute, mutate, and visualize directed acyclic graphs (DAGs) of skillful AI agents so teams can coordinate multi-agent workflows reliably, safely, and cost-effectively. It addresses ambiguity in planning by supporting vague-node expansion, progressive revelation, mutation strategies, circuit breakers, and cross-wave context management to prevent deadlocks and cascade failures. The skill codifies execution-mode selection, model routing, failure mitigation, and quality-evaluation gates so complex, multi-domain problems can be decomposed and executed as repeatable, auditable workflows.
Ask windags-architect to design a dynamic DAG for "Build a portfolio website", recommend execution mode, assign node commitment levels, and produce a wave-by-wave execution plan.
High-intent search queries and answers about installing and using this skill.
Multi-agent DAG orchestration coordinates AI agents as a directed acyclic graph to execute complex workflows reliably. You need it when decomposing multi-domain problems into repeatable pipelines requiring cross-wave context management, circuit breakers, and mutation strategies.
You design multi-agent workflows by selecting execution modes (local, web, embedded), assigning node commitment levels (committed, tentative, exploratory), and choosing DAG architecture patterns like sequential, fan-out, or iterative refinement to produce a wave-by-wave execution plan.
Yes, Temporal enables durable execution of agent pipelines and ReactFlow with ELKjs provides live DAG visualization. The framework supplies integration patterns for both alongside mixed-provider LLM abstraction for routing across different model providers.
Prevent multi-agent cascade failures by configuring circuit breakers, applying automatic replace/add/split mutations, setting mutation depth limits, and using escalation ladders for human intervention to resolve deadlocks across DAG execution waves.
Model routing for mixed-provider LLM workflows uses tier-based, cascading, adaptive, and RouteLLM patterns to direct tasks to appropriate providers. It includes cost-tracking guidance to balance performance and expenses across agent nodes.
You do not need predefined nodes because the framework supports vague-node expansion and progressive revelation. It resolves architectural ambiguity by dynamically expanding vague nodes during DAG execution, allowing iterative refinement of multi-agent workflows.
MohamedAbdallah-14Validate prerequisites, select interaction mode, and delegate to the execute workflow.
majiayu000Estimate tokens, prune messages, and auto-compact LLM context histories.
curiositechConstruct DAG visualizations with ReactFlow v12, ELKjs layout, and Zustand state.
Geralt1983Execute multi-agent pipelines through sequential prompt chaining and predefined workflows.
