skills.rest
pazdedav
pazdedavCOMMUNITY
Explore all skills by this author →
Website𝕏@pazdedavGitHub

workflow-engine

Define DAG workflow graphs with JSON schema for agent orchestration.

Updated Mar 9, 2026
Search Tags:#automation#workflow#agent#orchestration#iac#conductor#dag
One-click install
npx skills add https://github.com/pazdedav/my-infraops-project --skill workflow-engine-pazdedav
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: workflow-engine
Source: https://github.com/pazdedav/my-infraops-project/tree/main/.github/skills/workflow-engine
Command: npx skills add https://github.com/pazdedav/my-infraops-project --skill workflow-engine-pazdedav

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides a declarative, machine-readable workflow graph that the Conductor uses to route steps, manage dependencies, and handle conditional logic, eliminating the need for hardcoded step logic.

Core Features & Use Cases

  • Workflow Orchestration: Defines a Directed Acyclic Graph (DAG) for multi-step agent processes.
  • Conditional Routing: Manages complex branching based on previous step outcomes or specific decision fields (e.g., IaC tool choice).
  • Gate Management: Integrates human approval checkpoints within the workflow.
  • Parallel Execution: Supports fan-out patterns for executing independent sub-steps concurrently.
  • Use Case: Ensure that after an architecture is approved, the system correctly routes to either the Bicep or Terraform planning step based on the decisions.iac_tool field, and then proceeds to code generation and deployment for the selected path.

Quick Start

Use the workflow-engine skill to determine the next step in the current workflow based on the state file.

Frequently Asked Questions about workflow-engine

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

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

Agent workflow orchestration uses a declarative JSON schema to define a Directed Acyclic Graph (DAG), managing nodes, edges, and conditional routing based on specific decision fields to eliminate hardcoded step logic.

Can I use a DAG to manage parallel execution and human approval gates?▼

Yes, the workflow DAG supports fan-out patterns for parallel execution of independent sub-steps and integrates human approval checkpoints through dedicated gate management within the workflow graph.

How does conditional logic route steps based on previous agent outcomes?▼

Conditional logic evaluates previous step outcomes or specific decision fields, such as routing to Bicep or Terraform planning based on the decisions.iac_tool field, ensuring correct downstream code generation.

What is the best way to define a machine-readable workflow graph for agents?▼

Defining a machine-readable workflow graph requires a JSON schema specifying nodes, edges, conditions, and gates, which a conductor uses to manage step routing and state for multi-step agent pipelines.

Do I need hardcoded step logic to manage dependencies in agent pipelines?▼

No, you do not need hardcoded step logic; the workflow engine provides a declarative, machine-readable workflow graph that the conductor uses to route steps and manage dependencies automatically.

How do I determine the next step in a multi-step agent workflow?▼

To determine the next step in a multi-step agent workflow, the conductor protocol reads the current state file and routes execution based on the defined DAG, conditions, and gate statuses.

Related Skills

Explore More Software Engineering Skills→
jwilgerjwilger

orchestration-protocol

Define multi-agent orchestration patterns with delegation, workflow gates, and domain vetoes.

Community
Advanced
cescraflicescrafli

claude-devfleet

Manages parallel Code Agents missions with Git worktrees and dashboards.

Community
Intermediate
shuyu-labsshuyu-labs
288

distributed-task-orchestrator

Decompose complex requests into atomic tasks and orchestrate parallel sub-agents.

Official
Advanced
davidorexdavidorex
25

pi-workflows

Orchestrate YAML-defined agent workflows with DAG-based execution and typed data flow.

Community
Advanced