Maestro is an open-source AI workflow skill that provides 25 commands, a persistent memory layer, and curated anti-patterns for building reliable, production-grade AI agent workflows. It covers 7 domains: prompt engineering, context management, tool orchestration, agent architecture, feedback loops, knowledge systems, and guardrails & safety.

What is Maestro Skills?

Maestro Skills (at maestroskills.dev) is the name for the complete Maestro ecosystem — the workflow skill, the MCP server, and the documentation. It's a Claude Code Skill that teaches your AI agent how to behave across complex, multi-step tasks by installing a meta-workflow layer with 25 commands, 7 reference domains, persistent memory, and curated anti-patterns.

How do I install Maestro?

Install Maestro in seconds by running: npx skills add sharpdeveye/maestro. This installs the skill along with all 25 commands into your AI development environment. Then run /teach-maestro to scan your project and generate a .maestro.md context file.

What commands does Maestro include?

Maestro includes 25 commands across 4 categories: Analysis (diagnose, evaluate, reflect), Fix & Improve (refine, streamline, calibrate, fortify, zero-defect), Enhance (amplify, compose, enrich, accelerate, chain, guard, iterate, temper, turbocharge), and Utility (extract-pattern, adapt-workflow, onboard-agent, specialize, teach-maestro, capture, recap).

What is the /zero-defect command?

The /zero-defect command is a model-agnostic precision protocol that enforces 8 execution rules, pre-commit verification gates, and anti-pattern correction tables. It ensures maximum discipline in AI outputs with zero assumptions and verified results.

Does Maestro support MCP (Model Context Protocol)?

Yes, Maestro fully supports the Model Context Protocol (MCP) via the maestro-workflow-mcp npm package. All 25 commands are available as MCP-compatible prompts. The server supports dual transport — local via stdio and remote via HTTP — and exposes 25 prompts, 10 tools, and 8 resources.

How does Maestro integrate with Claude Code?

Maestro follows the standard Claude Code Skills format. Install it with npx skills add sharpdeveye/maestro. Claude auto-discovers the skill at startup and loads SKILL.md metadata (~100 tokens). When you trigger a workflow command, Claude loads the full instructions on demand. For MCP integration, add the maestro-workflow-mcp server to your MCP client config.

What anti-patterns does Maestro prevent?

Maestro prevents 6 documented anti-patterns: Context Dumping (feeding entire codebases into prompts), Retry & Pray (retrying without changing anything), Agent Overkill (over-engineering with multi-agent systems), Tool Sprawl (vague tool descriptions), Ship & Pray (deploying with no evaluation), and No Cost Controls (no token budgets or rate limits).

Is Maestro free and open-source?

Yes, Maestro is completely free and open-source under the MIT license. The source code is available at https://github.com/sharpdeveye/maestro and the MCP server is published as maestro-workflow-mcp on npm.

What is the MCP Server for Maestro?

The MCP server (maestro-workflow-mcp on npm) exposes all 25 Maestro commands as MCP-compatible prompts, plus 10 tools (list_commands, run_command, read_context, init, wave_start, wave_advance, wave_status, write_decision, read_decisions, read_audit) and 8 resources (core skill + 7 domain references). It supports dual transport — local via stdio and remote via HTTP — enabling integration with Claude Code, Cursor, VS Code, Gemini CLI, Antigravity, and any MCP-compatible client.

Workflow Fluency for AI Agents

Name: Maestro
Availability: InStock
Author: SharpDevEye

Maestro is an open-source AI workflow skill with 25 commands, persistent memory, and curated anti-patterns for building reliable, production-grade AI agent workflows. Achieve workflow fluency across prompt engineering, context management, tool orchestration, and agent architecture.

How It Works

Install Maestro in seconds and start using workflow commands immediately. Maestro provides workflow fluency by teaching AI agents systematic planning, execution, and verification across complex, multi-step tasks.

npx skills add sharpdeveye/maestro

25 Commands Across 4 Categories

Analysis: diagnose, evaluate, reflect
Fix & Improve: refine, streamline, calibrate, fortify, zero-defect
Enhance: amplify, compose, enrich, accelerate, chain, guard, iterate, temper, turbocharge
Utility: extract-pattern, adapt-workflow, onboard-agent, specialize, teach-maestro, capture, recap

MCP Server

The maestro-workflow-mcp npm package exposes all 25 workflow commands as MCP-compatible prompts with dual transport (stdio + HTTP) and 10 tools. Learn more about MCP integration.

Anti-Patterns

Maestro documents 6 common AI workflow anti-patterns including Context Dumping, Retry & Pray, Agent Overkill, Tool Sprawl, Ship & Pray, and No Cost Controls. Read the full anti-pattern guide.

Works Everywhere

Maestro is compatible with Claude Code, Cursor, VS Code, Gemini CLI, Antigravity, Kiro, Trae, OpenCode, Pi, and any MCP-compatible client.

Frequently Asked Questions

What is Maestro?: An open-source AI workflow skill that provides workflow fluency with 25 commands and persistent memory for building production-grade AI agent workflows.
How do I install it?: Run npx skills add sharpdeveye/maestro in your terminal. Then run /teach-maestro to initialize.
Is it free?: Yes — MIT licensed, fully open-source on GitHub.
Does it support MCP?: Yes — the maestro-workflow-mcp package provides full Model Context Protocol support.

GitHub · npm · llms.txt · Sitemap · Robots