Maestro
Maestro is a workflow skill for AI coding agents that adds diagnostic, refinement and hardening commands, persistent memory and an audit trail, aimed at the common failure modes of unstructured prompts, context overflow and unnecessary multi-agent complexity.
Maestro is built around one agent-workflow skill with seven domain-specific reference files covering prompt engineering, context management, tool orchestration, agent architecture, feedback loops, knowledge systems, and guardrails and safety. Twenty-five commands let a user diagnose workflow problems, evaluate interaction quality, refine, streamline, fortify with error handling, capture decisions, or reflect, and commands can be chained, such as running diagnose, calibrate and refine in sequence.
Persistent memory keeps decisions, an audit trail and session history across sessions, and curated anti-patterns explicitly tell the model what not to do. A context-gathering protocol file gives every command project-specific awareness, and each command recommends its own next step.
It installs with a skills installer command and works across Cursor, Claude Code, Gemini CLI, GitHub Copilot and several other agent tools.