core-sdk

Build and run Kailash workflows with nodes, connections, and runtime execution.

Updated Oct 10, 2025
One-click install
npx skills add https://github.com/FFOO6866/lead2cash --skill core-sdk-ffoo6866
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: core-sdk
Source: https://github.com/FFOO6866/lead2cash/tree/main/.claude/skills/01-core-sdk
Command: npx skills add https://github.com/FFOO6866/lead2cash --skill core-sdk-ffoo6866

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you understand and correctly use the Kailash Core SDK so you can design workflow automation without getting stuck on node configuration, connections, runtime selection, async patterns, or lifecycle rules.

Core Features & Use Cases

  • Workflow fundamentals: Learn the canonical 4-parameter node configuration and the 4-parameter connection syntax for reliable data flow.
  • Runtime execution patterns: Choose the right runtime (LocalRuntime vs AsyncLocalRuntime) and execute with the required workflow.build() contract.
  • Advanced orchestration: Apply production-grade patterns for cycles, conditional execution, error handling, progress/diagnostics, scheduling, and MCP integration.
  • Production readiness: Cover enterprise capabilities like monitoring, validation, debugging, observability, and runtime architecture concepts.

Quick Start

Create a workflow with WorkflowBuilder, wire nodes using 4-parameter connections, build it, then run it with a LocalRuntime context manager using runtime.execute(workflow.build()).

Frequently Asked Questions about core-sdk

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

FAQPage Schema
How do I build a workflow with node connections and execute it properly?

Use WorkflowBuilder to configure nodes with the canonical 4-parameter syntax, wire data ports using 4-parameter connections, then execute via runtime.execute(workflow.build()) within a LocalRuntime context manager for deterministic workflow execution.

When should I use AsyncLocalRuntime instead of LocalRuntime for workflow execution?

Choose AsyncLocalRuntime over LocalRuntime when your workflow execution requires async-capable orchestration, such as handling concurrent node processing, cycles, or conditional routing patterns that demand non-blocking runtime execution behavior.

What is the correct way to connect data ports between nodes in a workflow graph?

The correct way to connect data ports is using the canonical 4-parameter connection syntax, which ensures reliable data flow between nodes by explicitly defining source node, source port, target node, and target port in the workflow graph.

Does the core SDK support MCP integration and conditional routing in production workflows?

Yes, the core SDK supports advanced production patterns including MCP integration, conditional routing, cycles, error handling, and runtime diagnostics, enabling complex async orchestration across CLI, scripts, and Docker or Nexus deployments.

Can I deploy Kailash workflows to Docker and Nexus environments?

Yes, Kailash workflows can be deployed across Docker and Nexus environments, with the core SDK providing production-ready capabilities like monitoring, validation, debugging, and observability to support enterprise runtime architecture requirements.

Why does my workflow execution fail without calling workflow.build()?

Workflow execution requires workflow.build() because it is the canonical contract that compiles node graphs and connection definitions into a runnable object the runtime can process, ensuring deterministic or async-capable execution without configuration errors.