· Joseph · AI & Machine Learning  · 4 min read

[Day 2] BMAD-Method and OpenCode installation

今天來個單純一點的,安裝BMAD-Method跟OpenCode。BMAD-Method在專案根目錄安裝就好,他只是把流程跟team, role的設定黨寫入資料夾而已。而OpenCode則是像Gemini, Claude code那樣的 The AI coding agent built for the terminal ,但因為我IDE是neovim,用他是為了方便在neovim裡使用。

參考影片:https://www.youtube.com/watch?v=70cN9swORE8

TOC

今天來個單純一點的,安裝BMAD-MethodOpenCode。BMAD-Method在專案根目錄安裝就好,他只是把流程跟team, role的設定黨寫入資料夾而已。而OpenCode則是像Gemini, Claude code那樣的 The AI coding agent built for the terminal ,但因為我IDE是neovim,用他是為了方便在neovim裡使用。

參考影片:https://www.youtube.com/watch?v=70cN9swORE8

TOC

BMAD-Method

首先我們先建立一個專案資料夾 project-1,然後在資料夾下操作安裝。

$ mkdir ~/project/bmad-method/project-1
$ cd ~/project/bmad-method/project-1

接著跑下關鍵指令,讓安裝精靈一步一步帶你決策

npx bmad-method install

bmad-method-step-1 很快迎來我的第一個問題:我們要安裝什麼擴充包 expansion packs?

所有的pack可以參考:

  1. https://github.com/bmad-code-org/BMAD-METHOD/tree/main/expansion-packs
  2. https://github.com/bmad-code-org/BMAD-METHOD/blob/main/docs/expansion-packs

我這邊單純的就選 .bmad-core.bmad-infrastructure-devops

第2, 3個問題直覺一些,就是問要不要把文件切小,我這邊選Y

? Will the PRD (Product Requirements Document) be sharded into multiple files? (Y/n) Y

? Will the architecture documentation be sharded into multiple files? (Y/n) Y

然後就看習慣的IDE,去選擇下一個IDE Configuration的選項,我這邊先暫時選 Gemini CLIOpenCode bmad-method-step-3

接下來是問你team的組成,我這邊先來個自己選,然後再決定要哪些teams bmad-method-step-4

跑完以後就可以看到我們專案底下安裝了很多很多的markdown files了

$ tree -L 1 -a
.
├── .bmad-core
│   ├── agent-teams
│   ├── agents
│   ├── checklists
│   ├── core-config.yaml
│   ├── data
│   ├── enhanced-ide-development-workflow.md
│   ├── install-manifest.yaml
│   ├── tasks
│   ├── templates
│   ├── user-guide.md
│   ├── utils
│   ├── workflows
│   └── working-in-the-brownfield.md
├── .bmad-infrastructure-devops
│   ├── agents
│   ├── checklists
│   ├── config.yaml
│   ├── data
│   ├── install-manifest.yaml
│   ├── README.md
│   ├── tasks
│   ├── templates
│   └── utils
├── .gemini
│   └── commands
├── AGENTS.md
├── opencode.jsonc
└── web-bundles
    ├── expansion-packs
    └── teams

但不要忘了他重要的警語

📖 IMPORTANT: Please read the user guide at docs/user-guide.md (also installed at .bmad-core/user-guide.md)

This guide contains essential information about the BMad workflow and how to use the agents effectively.

OpenCode

接下來是 OpenCode,我這邊也用npm安裝

$ npm install -g opencode-ai

然後跑完後直接執行 opencode auth login 先選擇你的授權登入方式,我選擇的是Google 並貼上API key就好

opencode-login

最後執行 opencode 就可以打開啦。 opencode

這也很簡單,到這邊就結束了。 我們來看看Gemini跟opencode的執行結果

opencode 輸入 @,就可以看到bmad-method的夥伴們了

opencode-agents

Gemini 輸入 / 找到/BMad:agents開頭的夥伴

gemini-agents

這樣就有multi-agents啦!

今天到這邊就結束囉,幾個指令稍微安裝設定一下,為了接下來幾天鋪路。 喜歡我文章的再幫忙推廣一下喔!

Back to Blog

Related Posts

View All Posts »
[Day 3] BMAD-Method project-1 calculator

[Day 3] BMAD-Method project-1 calculator

第一個project來個簡單的計算機,我打算用Reactjs做一個純前端的計算機出來,他會需要容器化技術docker。先用這個簡單的專案來做暖身。 TOC

[Day 1] BMAD-Method intro

[Day 1] BMAD-Method intro

這是自發性的連續寫30篇教學文章,不是很想把文章發在ithelp,來這邊挑戰一下自己寫30天BMAD-Method相關的技術文章,預計會用BMAD-Method做各種不擅長的專案。期間可能會視情況購置需要的AI agent plans,可能是Claude Code, OpenAI, 或Gemini都說不定,看token燃燒速度而定。 第一篇先來介紹介紹BMAD-Method這個 AI Agent Framework吧。 TOC

Use Grafana MCP with Gemini and n8n

Use Grafana MCP with Gemini and n8n

The Model Context Protocol (MCP) is extremely useful. An AI assistant helps you decide when and how to use connected tools, so you only need to configure them. After integrating MCP logging management systems into several of my projects, it has saved me a significant amount of time. In this article, I'm going to integrate Grafana with the Gemini CLI and n8n. I will chat with the Gemini CLI and n8n and have them invoke the Grafana MCP server. structure TOC

Use Figma MCP server with Gemini CLI

Use Figma MCP server with Gemini CLI

In this article, I won't introduce what MCP is. Instead, I will explain how to set up the Figma MCP server and use Gemini as an MCP client to work with Figma. I will also show you how to run a prompt to get a Figma design with Gemini. TOC