skills.rest
batuhanysv
batuhanysvCOMMUNITY
Explore all skills by this author →
GitHub

workflow-engine

Define machine-readable DAGs for orchestrating multi-agent workflows with routing and approvals.

Updated Mar 16, 2026
Search Tags:#automation#workflow#agent#orchestration#governance#conductor#DAG
One-click install
npx skills add https://github.com/batuhanysv/sdx-agentic-infraops --skill workflow-engine-batuhanysv
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: workflow-engine
Source: https://github.com/batuhanysv/sdx-agentic-infraops/tree/main/.github/skills/workflow-engine
Command: npx skills add https://github.com/batuhanysv/sdx-agentic-infraops --skill workflow-engine-batuhanysv

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and templates (resource) components.

What problem does it solve?

This Skill provides a declarative, machine-readable workflow graph that the Conductor uses to route tasks, manage approvals, and handle parallel execution, eliminating hardcoded step logic.

Core Features & Use Cases

  • Declarative Workflow DAG: Defines nodes (steps, gates, fan-outs) and edges (dependencies, conditions) for complex agent pipelines.
  • Conditional Routing: Supports dynamic routing based on decision outcomes (e.g., Bicep vs. Terraform).
  • Human Approval Gates: Integrates checkpoints for user review and decision-making.
  • Parallel Execution: Manages fan-out patterns for concurrent sub-step processing.
  • Use Case: The Conductor uses this Skill to determine the next logical step after a user approves the architecture, routing to either the Bicep or Terraform planning agent based on the decisions.iac_tool field.

Quick Start

Use the workflow-engine skill to validate the current step in the session state against the workflow graph.

Frequently Asked Questions about workflow-engine

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I orchestrate multi-agent workflows with conditional routing?▼

A declarative Directed Acyclic Graph (DAG) orchestrates multi-agent workflows by defining nodes for steps and edges for dependencies, enabling dynamic conditional routing based on decision outcomes without hardcoding step logic.

Can I add human approval gates to an automated agent pipeline?▼

Yes, automated agent pipelines support human approval gates by defining checkpoint nodes within the workflow DAG, allowing users to review and make decisions before the Conductor routes to the next logical step.

How does parallel execution work in a multi-agent DAG?▼

Parallel execution in a multi-agent DAG operates through fan-out patterns, allowing the Conductor to manage concurrent sub-step processing across multiple nodes simultaneously for dynamic workflow execution and state management.

What is a machine-readable DAG for AI agent orchestration?▼

A machine-readable DAG for AI agent orchestration is a declarative workflow graph defining step routing, conditional logic, and approval gates, eliminating hardcoded step logic and enabling dynamic execution by the Conductor.

Do I need a Conductor to execute a declarative workflow graph?▼

Yes, a Conductor is required to execute a declarative workflow graph, utilizing the defined DAG model with node types and edge conditions for dynamic workflow execution, state management, and subagent fan-out.

Related Skills

Explore More Software Engineering Skills→
cas-bigdatalabcas-bigdatalab
541

source_stop

Configure the initial data source for a DAG workflow with a file path.

Official
Basic
pazdedavpazdedav

workflow-engine

Define DAG workflow graphs with JSON schema for agent orchestration.

Community
Advanced
Avihai-HAvihai-H

workflow-engine

Define and execute declarative Azure infrastructure deployment workflows with managed dependencies.

Community
Advanced
curiositechcuriositech
2

dag-planner

Plan and optimize DAG execution graphs for multi-step tasks.

Official
Advanced