Don't Vibe Code, Do Skele-Code: Interactive No-Code Notebooks for Subject Matter Experts to Build Lower-Cost Agentic Workflows

arXiv cs.AI / 3/20/2026

💬 OpinionDeveloper Stack & InfrastructureTools & Practical UsageModels & Research

共有:

Key Points

Skele-Code provides a natural-language and graph-based interface enabling less-technical users to build AI agent workflows.
It supports incremental, interactive notebook-style development, with each step converted to code and requiring a set of functions and behavior to enable incremental building of workflows.
Agents are invoked only for code generation and error recovery, not for orchestration or task execution.
The approach is agent-supported but code-first, and uses context-engineering to reduce token costs relative to multi-agent workflow execution.
Workflows are modular, extensible, and shareable, and can be used as skills by agents or as steps in other workflows.

Abstract

Skele-Code is a natural-language and graph-based interface for building workflows with AI agents, designed especially for less or non-technical users. It supports incremental, interactive notebook-style development, and each step is converted to code with a required set of functions and behavior to enable incremental building of workflows. Agents are invoked only for code generation and error recovery, not orchestration or task execution. This agent-supported, but code-first approach to workflows, along with the context-engineering used in Skele-Code, can help reduce token costs compared to the multi-agent system approach to executing workflows. Skele-Code produces modular, easily extensible, and shareable workflows. The generated workflows can also be used as skills by agents, or as steps in other workflows.