bmad-method 6.2.1-next.30 → 6.2.1-next.32
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README_CN.md
CHANGED
|
@@ -5,20 +5,20 @@
|
|
|
5
5
|
[](https://nodejs.org)
|
|
6
6
|
[](https://discord.gg/gk8jAdXWmj)
|
|
7
7
|
|
|
8
|
-
|
|
8
|
+
**筑梦架构（Build More Architect Dreams）** —— 简称 “BMAD 方法”，面向 BMad 模块生态的 AI 驱动敏捷开发方法。它会随项目复杂度调整工作深度，从日常 bug 修复到企业级系统建设都能适配。
|
|
9
9
|
|
|
10
|
-
**100% 免费且开源。**
|
|
10
|
+
**100% 免费且开源。** 没有付费墙，没有封闭内容，也没有封闭 Discord。我们希望每个人都能平等获得高质量的人机协作开发方法。
|
|
11
11
|
|
|
12
12
|
## 为什么选择 BMad 方法？
|
|
13
13
|
|
|
14
|
-
传统 AI
|
|
14
|
+
传统 AI 工具常常替你思考，结果往往止于“能用”。BMad 通过专业智能体和引导式工作流，让 AI 成为协作者：流程有结构，决策有依据，产出更稳定。
|
|
15
15
|
|
|
16
|
-
- **AI
|
|
17
|
-
-
|
|
18
|
-
- **结构化工作流**
|
|
19
|
-
-
|
|
20
|
-
- **派对模式**
|
|
21
|
-
- **完整生命周期**
|
|
16
|
+
- **AI 智能引导** —— 随时调用 `bmad-help` 获取下一步建议
|
|
17
|
+
- **规模与领域自适应** —— 按项目复杂度自动调整规划深度
|
|
18
|
+
- **结构化工作流** —— 覆盖分析、规划、架构、实施全流程
|
|
19
|
+
- **专业角色智能体** —— 提供 PM、架构师、开发者、UX、Scrum Master 等 12+ 角色
|
|
20
|
+
- **派对模式** —— 多个智能体可在同一会话协作讨论
|
|
21
|
+
- **完整生命周期** —— 从头脑风暴一路到交付上线
|
|
22
22
|
|
|
23
23
|
[在 **docs.bmad-method.org** 了解更多](https://docs.bmad-method.org/zh-cn/)
|
|
24
24
|
|
|
@@ -26,7 +26,7 @@
|
|
|
26
26
|
|
|
27
27
|
## 🚀 BMad 的下一步是什么？
|
|
28
28
|
|
|
29
|
-
**V6
|
|
29
|
+
**V6 已经上线，而这只是开始。** BMad 仍在快速演进：跨平台智能体团队与子智能体集成、Skills 架构、BMad Builder v1、Dev Loop 自动化等能力都在持续推进。
|
|
30
30
|
|
|
31
31
|
**[📍 查看完整路线图 →](https://docs.bmad-method.org/zh-cn/roadmap/)**
|
|
32
32
|
|
|
@@ -40,7 +40,7 @@
|
|
|
40
40
|
npx bmad-method install
|
|
41
41
|
```
|
|
42
42
|
|
|
43
|
-
>
|
|
43
|
+
> 想体验最新预发布版本？可使用 `npx bmad-method@next install`。它比默认版本更新更快，也可能更容易发生变化。
|
|
44
44
|
|
|
45
45
|
按照安装程序提示操作，然后在项目文件夹中打开你的 AI IDE（Claude Code、Cursor 等）。
|
|
46
46
|
|
|
@@ -52,19 +52,19 @@ npx bmad-method install --directory /path/to/project --modules bmm --tools claud
|
|
|
52
52
|
|
|
53
53
|
[查看非交互式安装选项](https://docs.bmad-method.org/zh-cn/how-to/non-interactive-installation/)
|
|
54
54
|
|
|
55
|
-
>
|
|
55
|
+
> **不确定下一步？** 直接问 `bmad-help`。它会告诉你“必做什么、可选什么”，例如：`bmad-help 我刚完成架构设计，接下来做什么？`
|
|
56
56
|
|
|
57
57
|
## 模块
|
|
58
58
|
|
|
59
|
-
BMad
|
|
59
|
+
BMad 可通过官方模块扩展到不同专业场景。你可以在安装时选择，也可以后续随时补装。
|
|
60
60
|
|
|
61
|
-
|
|
|
62
|
-
| ----------------------------------------------------------------------------------------------------------------- |
|
|
63
|
-
| **[BMad Method (BMM)](https://github.com/bmad-code-org/BMAD-METHOD)** |
|
|
64
|
-
| **[BMad Builder (BMB)](https://github.com/bmad-code-org/bmad-builder)** | 创建自定义 BMad
|
|
65
|
-
| **[Test Architect (TEA)](https://github.com/bmad-code-org/bmad-method-test-architecture-enterprise)** |
|
|
66
|
-
| **[Game Dev Studio (BMGD)](https://github.com/bmad-code-org/bmad-module-game-dev-studio)** | 游戏开发工作流（Unity
|
|
67
|
-
| **[Creative Intelligence Suite (CIS)](https://github.com/bmad-code-org/bmad-module-creative-intelligence-suite)** | 创新、头脑风暴、设计思维
|
|
61
|
+
| 模块 | 用途 |
|
|
62
|
+
| ----------------------------------------------------------------------------------------------------------------- | ---------------------------- |
|
|
63
|
+
| **[BMad Method (BMM)](https://github.com/bmad-code-org/BMAD-METHOD)** | 核心框架，内含 34+ 工作流 |
|
|
64
|
+
| **[BMad Builder (BMB)](https://github.com/bmad-code-org/bmad-builder)** | 创建自定义 BMad 智能体与工作流 |
|
|
65
|
+
| **[Test Architect (TEA)](https://github.com/bmad-code-org/bmad-method-test-architecture-enterprise)** | 基于风险的测试策略与自动化 |
|
|
66
|
+
| **[Game Dev Studio (BMGD)](https://github.com/bmad-code-org/bmad-module-game-dev-studio)** | 游戏开发工作流（Unity/Unreal/Godot） |
|
|
67
|
+
| **[Creative Intelligence Suite (CIS)](https://github.com/bmad-code-org/bmad-module-creative-intelligence-suite)** | 创新、头脑风暴、设计思维 |
|
|
68
68
|
|
|
69
69
|
## 文档
|
|
70
70
|
|
|
@@ -72,10 +72,9 @@ BMad 方法通过官方模块扩展到专业领域。可在安装期间或之后
|
|
|
72
72
|
|
|
73
73
|
**快速链接：**
|
|
74
74
|
- [入门教程](https://docs.bmad-method.org/zh-cn/tutorials/getting-started/)
|
|
75
|
-
- [
|
|
75
|
+
- [从旧版本升级](https://docs.bmad-method.org/zh-cn/how-to/upgrade-to-v6/)
|
|
76
76
|
- [测试架构师文档（英文）](https://bmad-code-org.github.io/bmad-method-test-architecture-enterprise/)
|
|
77
77
|
|
|
78
|
-
|
|
79
78
|
## 社区
|
|
80
79
|
|
|
81
80
|
- [Discord](https://discord.gg/gk8jAdXWmj) — 获取帮助、分享想法、协作
|
|
@@ -85,9 +84,9 @@ BMad 方法通过官方模块扩展到专业领域。可在安装期间或之后
|
|
|
85
84
|
|
|
86
85
|
## 支持 BMad
|
|
87
86
|
|
|
88
|
-
BMad
|
|
87
|
+
BMad 对所有人免费，而且会一直免费。如果你愿意支持项目发展：
|
|
89
88
|
|
|
90
|
-
- ⭐
|
|
89
|
+
- ⭐ 给仓库点个 Star
|
|
91
90
|
- ☕ [请我喝咖啡](https://buymeacoffee.com/bmad) — 为开发提供动力
|
|
92
91
|
- 🏢 企业赞助 — 在 Discord 上私信
|
|
93
92
|
- 🎤 演讲与媒体 — 可参加会议、播客、采访（在 Discord 上联系 BM）
|
|
@@ -107,15 +106,3 @@ MIT 许可证 — 详见 [LICENSE](LICENSE)。
|
|
|
107
106
|
[](https://github.com/bmad-code-org/BMAD-METHOD/graphs/contributors)
|
|
108
107
|
|
|
109
108
|
请参阅 [CONTRIBUTORS.md](CONTRIBUTORS.md) 了解贡献者信息。
|
|
110
|
-
|
|
111
|
-
---
|
|
112
|
-
## 术语说明
|
|
113
|
-
|
|
114
|
-
- **agent**：智能体。在人工智能与编程文档中，指具备自主决策或执行能力的单元。
|
|
115
|
-
- **workflow**：工作流。指一系列有序的任务或步骤，用于完成特定目标。
|
|
116
|
-
- **CI/CD**：持续集成/持续部署。一种自动化软件开发实践，用于频繁集成代码更改并自动部署。
|
|
117
|
-
- **IDE**：集成开发环境。提供代码编辑、调试、构建等功能的软件开发工具。
|
|
118
|
-
- **PM**：产品经理。负责产品规划、需求管理和团队协调的角色。
|
|
119
|
-
- **UX**：用户体验。指用户在使用产品或服务过程中的整体感受和交互体验。
|
|
120
|
-
- **Scrum Master**：Scrum 主管。敏捷开发 Scrum 框架中的角色，负责促进团队遵循 Scrum 流程。
|
|
121
|
-
- **PRD**：产品需求文档。详细描述产品功能、需求和规格的文档。
|
package/package.json
CHANGED
|
@@ -15,13 +15,27 @@ spec_file: '' # set at runtime for plan-code-review before leaving this step
|
|
|
15
15
|
- The user chose this workflow on purpose. Later steps (e.g. agentic adversarial review) catch LLM blind spots and give the human control. Do not skip them.
|
|
16
16
|
- **EARLY EXIT** means: stop this step immediately — do not read or execute anything further here. Read and fully follow the target file instead. Return here ONLY if a later step explicitly says to loop back.
|
|
17
17
|
|
|
18
|
-
##
|
|
18
|
+
## Intent check (do this first)
|
|
19
19
|
|
|
20
|
-
|
|
21
|
-
|
|
22
|
-
|
|
23
|
-
|
|
24
|
-
-
|
|
20
|
+
Before listing artifacts or prompting the user, check whether you already know the intent. Check in this order — skip the remaining checks as soon as the intent is clear:
|
|
21
|
+
|
|
22
|
+
1. Explicit argument
|
|
23
|
+
Did the user pass a specific file path, spec name, or clear instruction this message?
|
|
24
|
+
- If it points to a file that matches the tech-spec template (has `status` frontmatter with a recognized value: ready-for-dev, in-progress, or in-review) → set `spec_file` and **EARLY EXIT** to the appropriate step (step-03 for ready/in-progress, step-04 for review).
|
|
25
|
+
- Anything else (intent files, external docs, plans, descriptions) → ingest it as starting intent and proceed to INSTRUCTIONS. Do not attempt to infer a workflow state from it.
|
|
26
|
+
|
|
27
|
+
2. Recent conversation
|
|
28
|
+
Do the last few human messages clearly show what the user intends to work on?
|
|
29
|
+
Use the same routing as above.
|
|
30
|
+
|
|
31
|
+
3. Otherwise — scan artifacts and ask
|
|
32
|
+
- `{wipFile}` exists? → Offer resume or archive.
|
|
33
|
+
- Active specs (`ready-for-dev`, `in-progress`, `in-review`) in `{implementation_artifacts}`? → List them and HALT. Ask user which to resume (or `[N]` for new).
|
|
34
|
+
- If `ready-for-dev` or `in-progress` selected: Set `spec_file`. **EARLY EXIT** → `./step-03-implement.md`
|
|
35
|
+
- If `in-review` selected: Set `spec_file`. **EARLY EXIT** → `./step-04-review.md`
|
|
36
|
+
- Unformatted spec or intent file lacking `status` frontmatter? → Suggest treating its contents as the starting intent. Do NOT attempt to infer a state and resume it.
|
|
37
|
+
|
|
38
|
+
Never ask extra questions if you already understand what the user intends.
|
|
25
39
|
|
|
26
40
|
## INSTRUCTIONS
|
|
27
41
|
|
|
@@ -28,6 +28,10 @@ Hand `{spec_file}` to a sub-agent/task and let it implement. If no sub-agents ar
|
|
|
28
28
|
|
|
29
29
|
**Path formatting rule:** Any markdown links written into `{spec_file}` must use paths relative to `{spec_file}`'s directory so they are clickable in VS Code. Any file paths displayed in terminal/conversation output must use CWD-relative format with `:line` notation (e.g., `src/path/file.ts:42`) for terminal clickability. No leading `/` in either case.
|
|
30
30
|
|
|
31
|
+
### Self-Check
|
|
32
|
+
|
|
33
|
+
Before leaving this step, verify every task in the `## Tasks & Acceptance` section of `{spec_file}` is complete. Mark each finished task `[x]`. If any task is not done, finish it before proceeding.
|
|
34
|
+
|
|
31
35
|
## NEXT
|
|
32
36
|
|
|
33
37
|
Read fully and follow `./step-04-review.md`
|