Can I use this for human-in-the-loop workflows?

Yes, it includes templates for incorporating signal-based waiting for manual approvals within the workflow logic.

Which workflow engines is this skill compatible with?

This skill is specifically designed for implementations using Temporal.io and LangGraph for Python or TypeScript.

Does this skill handle large file transfers?

No, it follows best practices by storing large artifacts in external storage and passing only the reference (path/digest) between steps.

How does it ensure activity idempotency?

It calculates a SHA256 digest of inputs and checks for existing output paths before execution to prevent redundant processing.

Temporal & LangGraph Workflow Builder

Name: Temporal & LangGraph Workflow Builder
Author: rozwer

byrozwer

Productivity & Workflow

Implements robust, idempotent workflow steps for Temporal and LangGraph with integrated audit logging and artifact management.

About

This skill provides standardized implementation templates for adding or modifying steps within Temporal and LangGraph workflows. It automates the creation of high-reliability activities by enforcing input normalization, SHA256 digest-based idempotency, and reference-based artifact storage. Designed for complex backend processes, it streamlines the integration of manual approval gates, audit logs, and database tracking for step executions, ensuring that every transition in your state machine is traceable and resumable.

Key Features

Built-in support for manual approval signals and human-in-the-loop gates
Template-driven step creation for Temporal and LangGraph nodes
Integrated audit logging and step execution database tracking
Standardized artifact management using storage references and metadata
Activity idempotency via SHA256 input digest verification
0 GitHub stars

Use Cases

Adding complex, multi-stage processing steps to an existing Temporal workflow
Upgrading legacy backend tasks to include comprehensive audit trails and failure recovery
Implementing resumable AI agent nodes using LangGraph with state persistence

About

Key Features

Built-in support for manual approval signals and human-in-the-loop gates
Template-driven step creation for Temporal and LangGraph nodes
Integrated audit logging and step execution database tracking
Standardized artifact management using storage references and metadata
Activity idempotency via SHA256 input digest verification
0 GitHub stars

Use Cases

Adding complex, multi-stage processing steps to an existing Temporal workflow
Upgrading legacy backend tasks to include comprehensive audit trails and failure recovery
Implementing resumable AI agent nodes using LangGraph with state persistence