core-sdk

Create and execute Kailash SDK workflows using WorkflowBuilder, nodes, connections, and runtimes.

Updated Apr 2, 2026
One-click install
npx skills add https://github.com/Hamza-Haadi/disease-risk-classifier-hamza --skill core-sdk-hamza-haadi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: core-sdk
Source: https://github.com/Hamza-Haadi/disease-risk-classifier-hamza/tree/main/.claude/skills/01-core-sdk
Command: npx skills add https://github.com/Hamza-Haadi/disease-risk-classifier-hamza --skill core-sdk-hamza-haadi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Building workflow automations with the Kailash SDK requires knowing the correct node patterns, connection syntax, runtime selection, and parameter passing rules, and mistakes like wrong runtime choice or deprecated connection syntax cause failures. ## Core Features & Use Cases - Workflow Construction: Build workflows with the 4-parameter node pattern, 4-parameter connections, dot notation for nested data, and fan-out/fan-in topologies. - Runtime Execution: Choose between LocalRuntime for CLI/scripts and AsyncLocalRuntime for Docker/FastAPI, with async patterns and resource safety guidance. - Supporting References: Covers installation, imports, parameter passing, error handling, custom nodes via register_callback, MCP integration, and OpenTelemetry tracing. - Use Case: A developer needs to read a CSV, filter rows with PythonCodeNode, and write JSON output; this Skill provides the exact copy-paste pattern with correct ports and connections. ## Quick Start Ask the AI to create a Kailash workflow that reads a CSV file, processes the data with a PythonCodeNode, and executes it with LocalRuntime.

Frequently Asked Questions about core-sdk

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

FAQPage Schema
How do I create a workflow with the Kailash SDK?▼

Create a WorkflowBuilder, add nodes with workflow.add_node("NodeName", "id", {config}), connect them with 4-parameter add_connection calls, then execute with runtime.execute(workflow.build()). Never call workflow.execute(runtime).

How do I connect nodes in a Kailash workflow?▼

Use the 4-parameter syntax: workflow.add_connection(source_id, source_output, target_id, target_input). Dot notation like "result.metrics.accuracy" extracts nested fields, and one output can fan out to multiple targets.

Should I use LocalRuntime or AsyncLocalRuntime?▼

Use AsyncLocalRuntime for Docker and FastAPI async contexts, and LocalRuntime for CLI scripts and synchronous code. Using LocalRuntime inside Docker causes hangs, so AsyncLocalRuntime is mandatory there.

How do I pass parameters to Kailash workflow nodes?▼

Use one of three methods: static node configuration at build time, dynamic connections from other nodes, or runtime parameters passed to execute(). Node-specific runtime parameters are automatically unwrapped and isolated per node.

Does Kailash SDK support cyclic workflows?▼

Cyclic workflows are a planned feature that is not yet implemented in the SDK. Until release, use alternative patterns such as retry logic or manual loops instead of cycle-based iteration.

Why does my Kailash workflow fail with connection errors?▼

Common causes are using the deprecated 3-parameter connection syntax, mismatched node IDs, or wrong port names such as "output" instead of "data" for CSVReaderNode. Verify node IDs match exactly and check each node's documented ports.