Workflow fluency for AI coding agents. 1 core skill · 25 commands · 7 domain references · memory layer · audit trail — works across Cursor, Claude Code, Gemini CLI, Copilot, and 6 more.
How to install maestro?
sharpdeveye/maestro
$git clone https://github.com/sharpdeveye/maestroInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install maestro by running `git clone https://github.com/sharpdeveye/maestro`, then use it for the current task and follow its documentation at https://github.com/sharpdeveye/maestro.
README.md
| 1 | <div align="center"> |
| 2 | |
| 3 | <picture> |
| 4 | <source media="(prefers-color-scheme: dark)" srcset="assets/banner.svg"> |
| 5 | <source media="(prefers-color-scheme: light)" srcset="assets/banner.svg"> |
| 6 | <img src="assets/banner.svg" alt="Maestro — Workflow fluency for AI coding agents" width="100%"> |
| 7 | </picture> |
| 8 | |
| 9 | <br> |
| 10 | |
| 11 | [](LICENSE) |
| 12 | [](https://github.com/sharpdeveye/maestro/releases) |
| 13 | [](https://www.npmjs.com/package/maestro-workflow-mcp) |
| 14 | [](https://marketplace.visualstudio.com/items?itemName=sharpdeveye.maestro-workflow) |
| 15 | [](https://modelcontextprotocol.io) |
| 16 | [](#the-skill-agent-workflow) |
| 17 | [](#25-commands) |
| 18 | [](#supported-tools) |
| 19 | |
| 20 | 1 core skill · 25 commands · 7 domain references · memory layer · audit trail |
| 21 | |
| 22 | [Quick Start](#quick-start) · [Commands](#25-commands) · [What's New in v2](#whats-new-in-v2) · [Supported Tools](#supported-tools) · [Contributing](#contributing) |
| 23 | |
| 24 | </div> |
| 25 | |
| 26 | --- |
| 27 | |
| 28 | ## What is Maestro? |
| 29 | |
| 30 | AI agents are only as good as the workflows they operate in. Without guidance, you get the same predictable mistakes: unstructured prompts, context window overflows, tool sprawl, no error handling, and multi-agent systems for single-agent problems. |
| 31 | |
| 32 | Maestro fights that pattern with: |
| 33 | |
| 34 | - A comprehensive **agent-workflow** skill with 7 domain-specific reference files ([view source](source/skills/agent-workflow)) |
| 35 | - **25 commands** to diagnose, evaluate, refine, streamline, fortify, capture, reflect, and more |
| 36 | - **Persistent memory** — decisions, audit trail, and session history survive across sessions |
| 37 | - Curated **anti-patterns** that explicitly tell the AI what NOT to do |
| 38 | - A **context gathering protocol** (`.maestro.md` or `.maestro/context.md`) that ensures every command has project-specific awareness |
| 39 | - **Every command recommends a next step** — no dead ends |
| 40 | |
| 41 | --- |
| 42 | |
| 43 | ## Quick Start |
| 44 | |
| 45 | ```bash |
| 46 | npx skills add sharpdeveye/maestro |
| 47 | ``` |
| 48 | |
| 49 | Then use any command in your AI coding agent: |
| 50 | |
| 51 | ```text |
| 52 | /diagnose # Find workflow issues |
| 53 | /streamline # Remove unnecessary complexity |
| 54 | /fortify # Add error handling |
| 55 | /refine # Final quality pass |
| 56 | ``` |
| 57 | |
| 58 | Most commands accept an optional argument to focus on a specific area: |
| 59 | |
| 60 | ```text |
| 61 | /diagnose prompts |
| 62 | /fortify payment-workflow |
| 63 | /specialize legal |
| 64 | ``` |
| 65 | |
| 66 | ### Combine Commands |
| 67 | |
| 68 | ```text |
| 69 | /diagnose /calibrate /refine # Full workflow: audit → standardize → polish |
| 70 | /evaluate /fortify /accelerate # Review → harden → optimize |
| 71 | ``` |
| 72 | |
| 73 | --- |
| 74 | |
| 75 | ## The Skill: agent-workflow |
| 76 | |
| 77 | A comprehensive workflow design skill with 7 domain references ([view skill](source/skills/agent-workflow/SKILL.md)): |
| 78 | |
| 79 | | Reference | Domain | |
| 80 | |-----------|--------| |
| 81 | | [prompt-engineering](source/skills/agent-workflow/reference/prompt-engineering.md) | Prompt structure, few-shot, CoT, output schemas | |
| 82 | | [context-management](source/skills/agent-workflow/reference/context-management.md) | Window optimization, memory, state management | |
| 83 | | [tool-orchestration](source/skills/agent-workflow/reference/tool-orchestration.md) | Tool design, chaining, error handling, sandboxing | |
| 84 | | [agent-architecture](source/skills/agent-workflow/reference/agent-archit |
Related
6 picksType
- langchain-mcp-adaptersMake Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.Jul 2026
- mcporterTypeScript runtime and CLI for connecting to configured Model Context Protocol servers.Jul 2026
- mcp-proxyA MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.Jul 2026
- mcp-atlassianThe Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification.Jul 2026
- open-webuiOpen WebUIJul 2026
- rulesyncUnified AI rules management CLI tool that generates configuration files for various AI development toolsJul 2026
