task-master-install

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Task Master Install

Task Master 安装指南

Overview

概述

Task-master is an AI-powered task management system for breaking down complex projects into manageable tasks and subtasks. It supports PRD parsing, complexity analysis, and specification-driven development workflows.

Task-Master是一款AI驱动的任务管理系统，可将复杂项目拆解为易于管理的任务与子任务。它支持PRD解析、复杂度分析以及规范驱动开发工作流。

Installation

安装步骤

Step 1: Check if already installed

步骤1：检查是否已安装

bash

task-master --version

If task-master is already installed and the project has a

.taskmaster/

folder, you are finished.

bash

task-master --version

如果Task-Master已安装，且项目中存在

.taskmaster/

文件夹，则安装完成。

Step 2: If you need to install Task-Master

步骤2：若需安装Task-Master

Global installation (recommended):

bash

npm install -g task-master-ai

Local/npx alternative:

bash

npx task-master-ai init

全局安装（推荐）：

bash

npm install -g task-master-ai

本地/npx替代方案：

bash

npx task-master-ai init

Step 3: If you don't have a

.taskmaster/

folder in your project

步骤3：若项目中无

.taskmaster/

文件夹

bash

task-master init

Common flags:

```
--name <name>
```
- Set project name
```
--description <text>
```
- Set project description
```
--version <version>
```
- Set initial version (e.g., '0.1.0')
```
--rules <profiles>
```
- Specify rule profiles (e.g.,
```
cursor,windsurf
```
)
```
-y, --yes
```
- Skip prompts, use defaults

Example:

bash

task-master init --name "My Project" --description "AI-powered web app" --version "0.1.0" --rules cursor,windsurf --yes

bash

task-master init

常用参数：

```
--name <name>
```
- 设置项目名称
```
--description <text>
```
- 设置项目描述
```
--version <version>
```
- 设置初始版本（例如：'0.1.0'）
```
--rules <profiles>
```
- 指定规则配置文件（例如：
```
cursor,windsurf
```
）
```
-y, --yes
```
- 跳过提示，使用默认配置

示例：

bash

task-master init --name "My Project" --description "AI-powered web app" --version "0.1.0" --rules cursor,windsurf --yes

What Happens During Init

初始化过程说明

Task-master init automatically creates:

```
.taskmaster/
```
directory structure (config, tasks, docs, reports, templates)
Rule files for AI coding assistants (
```
.cursor/rules/
```
, etc.)
Configures AI provider and models to use: Cortex-Code, Claude-Code, Gemini-CLI, Codex-CLI, API, etc.

The bootstrapped rules guide all future task-master workflows - no additional setup needed.

Task-Master初始化会自动创建：

```
.taskmaster/
```
目录结构（包含配置、任务、文档、报告、模板）
AI代码助手的规则文件（
```
.cursor/rules/
```
等）
配置要使用的AI提供商与模型：Cortex-Code、Claude-Code、Gemini-CLI、Codex-CLI、API等

初始化生成的规则将指导所有后续Task-Master工作流 - 无需额外设置。

Installing MCP Server for AI Agents

为AI Agents安装MCP Server

To enable AI agents to interact with task-master through MCP tools:

Option 1: Using Cortex (Recommended)

bash

undefined

要让AI Agents通过MCP工具与Task-Master交互：

选项1：使用Cortex（推荐）

bash

undefined

Using npx (no global install required)

使用npx（无需全局安装）

cortex mcp add --args '-y, task-master-ai, mcp' taskmaster npx snova mcp add --args "run, -i, --rm, -e, DOCUMENT_URL, -e, DOCUMENT_TOKEN, -e, DOCUMENT_ID, -e, RUNTIME_URL, -e, RUNTIME_TOKEN, -e, ALLOW_IMG_OUTPUT, datalayer/jupyter-mcp-server:latest" --env "DOCUMENT_URL=http://host.docker.internal:8888, DOCUMENT_TOKEN=jupyter_mcp_token, DOCUMENT_ID=notebooks/model_training.ipynb, RUNTIME_URL=http://host.docker.internal:8888, RUNTIME_TOKEN=jupyter_mcp_token, ALLOW_IMG_OUTPUT=true" jupyter-mcp-server docker

Or if task-master is installed globally

若已全局安装Task-Master

cortex mcp add taskmaster task-master --args "mcp"


**Option 2: Manual Configuration**

Add to your MCP configuration (e.g., `.cursor/mcp.json` or `claude_desktop_config.json`):

```json
{
  "mcpServers": {
    "taskmaster": {
      "command": "npx",
      "args": ["-y", "task-master-ai", "mcp"]
    }
  }
}

Or if task-master is installed globally:

json

{
  "mcpServers": {
    "taskmaster": {
      "command": "task-master",
      "args": ["mcp"]
    }
  }
}

After configuration, restart your AI agent to connect to the task-master MCP server.

cortex mcp add taskmaster task-master --args "mcp"


**选项2：手动配置**

将以下内容添加到你的MCP配置文件（例如：`.cursor/mcp.json`或`claude_desktop_config.json`）：

```json
{
  "mcpServers": {
    "taskmaster": {
      "command": "npx",
      "args": ["-y", "task-master-ai", "mcp"]
    }
  }
}

若已全局安装Task-Master：

json

{
  "mcpServers": {
    "taskmaster": {
      "command": "task-master",
      "args": ["mcp"]
    }
  }
}

配置完成后，重启你的AI Agent以连接到Task-Master MCP服务器。

Troubleshooting

故障排除

Node.js not found - Install Node.js v16+ using:

Windows (with admin):
```
winget install OpenJS.NodeJS
```
macOS:
```
brew install node
```

Linux:

sudo apt install nodejs npm

(Debian/Ubuntu) or

sudo yum install nodejs

(RHEL/CentOS)

Download installer: nodejs.org

Installation issues - Uninstall and reinstall globally:

bash

npm uninstall -g task-master-ai
npm install -g task-master-ai

Then restart terminal and verify with

task-master --version

Permission errors:

Unix/macOS: Install via nvm using

curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.3/install.sh | bash

, restart terminal, and run

nvm install 24

Windows without admin: Use Node.js installer's "Install for me only" option

未找到Node.js - 安装Node.js v16+，可通过以下方式：

Windows（需管理员权限）：
```
winget install OpenJS.NodeJS
```
macOS：
```
brew install node
```

Linux：

sudo apt install nodejs npm

（Debian/Ubuntu）或

sudo yum install nodejs

（RHEL/CentOS）

下载安装包：nodejs.org

安装问题 - 卸载并重新全局安装：

bash

npm uninstall -g task-master-ai
npm install -g task-master-ai

然后重启终端，使用

task-master --version

验证安装。

权限错误：

Unix/macOS：通过nvm安装，执行

curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.3/install.sh | bash

，重启终端后运行

nvm install 24

Windows无管理员权限：使用Node.js安装程序的“仅为我安装”选项

task-master-install

Original

Translation

Task Master Install

Task Master 安装指南

Overview

概述

Installation

安装步骤

Step 1: Check if already installed

步骤1：检查是否已安装

Step 2: If you need to install Task-Master

步骤2：若需安装Task-Master

Step 3: If you don't have a
`.taskmaster/`
folder in your project

步骤3：若项目中无
`.taskmaster/`
文件夹

What Happens During Init

初始化过程说明

Installing MCP Server for AI Agents

为AI Agents安装MCP Server

Using npx (no global install required)

使用npx（无需全局安装）

Or if task-master is installed globally

若已全局安装Task-Master

Troubleshooting

故障排除

task-master-install

Original

Translation

Task Master Install

Task Master 安装指南

Overview

概述

Installation

安装步骤

Step 1: Check if already installed

步骤1：检查是否已安装

Step 2: If you need to install Task-Master

步骤2：若需安装Task-Master

Step 3: If you don't have a .taskmaster/ folder in your project

步骤3：若项目中无.taskmaster/文件夹

What Happens During Init

初始化过程说明

Installing MCP Server for AI Agents

为AI Agents安装MCP Server

Using npx (no global install required)

使用npx（无需全局安装）

Or if task-master is installed globally

若已全局安装Task-Master

Troubleshooting

故障排除

Step 3: If you don't have a
`.taskmaster/`
folder in your project

步骤3：若项目中无
`.taskmaster/`
文件夹