LTiollier

Xu Maestro — AI skill for Claude Code

AI community

XuMaestro is a powerful and flexible workflow orchestrator for AI agents (Gemini & Claude).

How to install Xu Maestro

This entry records only its repository, not the path inside it, so there is no exact command to give. Open LTiollier/xu-maestro and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Xu Maestro does

XuMaestro is a powerful and flexible workflow orchestrator for AI agents (Gemini & Claude). it allows you to define complex sequences of automated tasks, manage loops over files, include sub-workflows, and track execution in real-time through a modern interface.

Alternatives in AI

Omniget — Udemy & Hotmart course downloader, YouTube downloader (yt-dlp GUI, 1,800+ sites) + desktop app for AI agents 13.9k ★
Cursor Tools — by eastlondoner - Creates a versatile AI command interface supporting multiple providers and models with flexi 4.7k ★
Define — Definition phase - Clarify and scope problems with multi-AI consensus 2.8k ★

README

XuMaestro 🎭

**XuMaestro** is a powerful and flexible workflow orchestrator for AI agents (Gemini & Claude). it allows you to define complex sequences of automated tasks, manage loops over files, include sub-workflows, and track execution in real-time through a modern interface.

🌟 Features

YAML Configuration: Define your workflows simply in YAML files.
AI-Powered Workflow Generation: Instantly create complex YAML workflows from a simple text description using AI.
Multi-Engine Support: Native support for both gemini-cli and claude-code.
Real-Time Execution: Follow progress, logs, and agent exchanges via a SSE (Server-Sent Events) stream.
Loop System (loop): Automatically iterate over lists of files using glob patterns.
Workflow Composition: Reuse existing workflows as steps using the sub-workflow engine.
Interactivity: Agents can pause execution to ask questions to the user.
Resilience & Checkpoints: Error management, automatic retries (mandatory mode), and resumption from the last successful checkpoint.
Context Isolation: Each step enriches the shared context while maintaining clean isolation during loop iterations.
Parallel Execution: Run independent agents simultaneously using the parallel: block to reduce total run time.
Git Checkpoints (Auto-Commit): Automatically commit changes after each successful agent execution with AI-generated commit messages.