Skip to content

Commit 8e8432e

Browse files
authored
Merge branch 'main' into main
2 parents d42de63 + 2f4c9ca commit 8e8432e

321 files changed

Lines changed: 9083 additions & 1632 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

.augment/code_review_guidelines.yaml

Lines changed: 11 additions & 133 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,7 @@
11
# Augment Code Review Guidelines for BMAD-METHOD
22
# https://docs.augmentcode.com/codereview/overview
3-
# Focus: Workflow validation and quality
3+
# Focus: Skill validation and quality
4+
# Canonical rules: tools/skill-validator.md (single source of truth)
45

56
file_paths_to_ignore:
67
# --- Shared baseline: tool configs ---
@@ -48,123 +49,17 @@ file_paths_to_ignore:
4849

4950
areas:
5051
# ============================================
51-
# WORKFLOW STRUCTURE RULES
52+
# SKILL FILES
5253
# ============================================
53-
workflow_structure:
54-
description: "Workflow folder organization and required components"
54+
skill_files:
55+
description: "All skill content — SKILL.md, workflow.md, step files, data files, and templates within skill directories"
5556
globs:
57+
- "src/**/skills/**"
5658
- "src/**/workflows/**"
59+
- "src/**/tasks/**"
5760
rules:
58-
- id: "workflow_entry_point_required"
59-
description: "Every workflow folder must have workflow.md as entry point"
60-
severity: "high"
61-
62-
- id: "sharded_workflow_steps_folder"
63-
description: "Sharded workflows (using workflow.md) must have steps/ folder with numbered files (step-01-*.md, step-02-*.md)"
64-
severity: "high"
65-
66-
- id: "workflow_step_limit"
67-
description: "Workflows should have 5-10 steps maximum to prevent context loss in LLM execution"
68-
severity: "medium"
69-
70-
# ============================================
71-
# WORKFLOW ENTRY FILE RULES
72-
# ============================================
73-
workflow_definitions:
74-
description: "Workflow entry files (workflow.md)"
75-
globs:
76-
- "src/**/workflows/**/workflow.md"
77-
rules:
78-
- id: "workflow_name_required"
79-
description: "Workflow entry files must define 'name' field in frontmatter or root element"
80-
severity: "high"
81-
82-
- id: "workflow_description_required"
83-
description: "Workflow entry files must include 'description' explaining the workflow's purpose"
84-
severity: "high"
85-
86-
- id: "workflow_installed_path"
87-
description: "Workflows should define installed_path for relative file references within the workflow"
88-
severity: "medium"
89-
90-
- id: "valid_step_references"
91-
description: "Step file references in workflow entry must point to existing files"
92-
severity: "high"
93-
94-
# ============================================
95-
# SHARDED WORKFLOW STEP RULES
96-
# ============================================
97-
workflow_steps:
98-
description: "Individual step files in sharded workflows"
99-
globs:
100-
- "src/**/workflows/**/steps/step-*.md"
101-
rules:
102-
- id: "step_goal_required"
103-
description: "Each step must clearly state its goal (## STEP GOAL, ## YOUR TASK, or step n='X' goal='...')"
104-
severity: "high"
105-
106-
- id: "step_mandatory_rules"
107-
description: "Step files should include MANDATORY EXECUTION RULES section with universal agent behavior rules"
108-
severity: "medium"
109-
110-
- id: "step_context_boundaries"
111-
description: "Step files should define CONTEXT BOUNDARIES explaining available context and limits"
112-
severity: "medium"
113-
114-
- id: "step_success_metrics"
115-
description: "Step files should include SUCCESS METRICS section with ✅ checkmarks for validation criteria"
116-
severity: "medium"
117-
118-
- id: "step_failure_modes"
119-
description: "Step files should include FAILURE MODES section with ❌ marks for anti-patterns to avoid"
120-
severity: "medium"
121-
122-
- id: "step_next_step_reference"
123-
description: "Step files should reference the next step file path for sequential execution"
124-
severity: "medium"
125-
126-
- id: "step_no_forward_loading"
127-
description: "Steps must NOT load future step files until current step completes - just-in-time loading only"
128-
severity: "high"
129-
130-
- id: "valid_file_references"
131-
description: "File path references using {variable}/filename.md must point to existing files"
132-
severity: "high"
133-
134-
- id: "step_naming"
135-
description: "Step files must be named step-NN-description.md (e.g., step-01-init.md, step-02-context.md)"
136-
severity: "medium"
137-
138-
- id: "halt_before_menu"
139-
description: "Steps presenting user menus ([C] Continue, [a] Advanced, etc.) must HALT and wait for response"
140-
severity: "high"
141-
142-
# ============================================
143-
# WORKFLOW CONTENT QUALITY
144-
# ============================================
145-
workflow_content:
146-
description: "Content quality and consistency rules for all workflow files"
147-
globs:
148-
- "src/**/workflows/**/*.md"
149-
rules:
150-
- id: "communication_language_variable"
151-
description: "Workflows should use {communication_language} variable for agent output language consistency"
152-
severity: "low"
153-
154-
- id: "path_placeholders_required"
155-
description: "Use path placeholders (e.g. {project-root}, {installed_path}, {output_folder}) instead of hardcoded paths"
156-
severity: "medium"
157-
158-
- id: "no_time_estimates"
159-
description: "Workflows should NOT include time estimates - AI development speed varies significantly"
160-
severity: "low"
161-
162-
- id: "facilitator_not_generator"
163-
description: "Workflow agents should act as facilitators (guide user input) not content generators (create without input)"
164-
severity: "medium"
165-
166-
- id: "no_skip_optimization"
167-
description: "Workflows must execute steps sequentially - no skipping or 'optimizing' step order"
61+
- id: "skill_validation"
62+
description: "Apply the full rule catalog defined in tools/skill-validator.md. That file is the single source of truth for all skill validation rules covering SKILL.md metadata, workflow.md constraints, step file structure, path references, variable resolution, sequential execution, and skill invocation syntax."
16863
severity: "high"
16964

17065
# ============================================
@@ -183,27 +78,10 @@ areas:
18378
description: "Agent files must define persona with role, identity, communication_style, and principles"
18479
severity: "high"
18580

186-
- id: "agent_menu_valid_workflows"
187-
description: "Menu triggers must reference valid workflow paths that exist"
81+
- id: "agent_menu_valid_skills"
82+
description: "Menu triggers must reference valid skill names that exist"
18883
severity: "high"
18984

190-
# ============================================
191-
# TEMPLATES
192-
# ============================================
193-
templates:
194-
description: "Template files for workflow outputs"
195-
globs:
196-
- "src/**/template*.md"
197-
- "src/**/templates/**/*.md"
198-
rules:
199-
- id: "placeholder_syntax"
200-
description: "Use {variable_name} or {{variable_name}} syntax consistently for placeholders"
201-
severity: "medium"
202-
203-
- id: "template_sections_marked"
204-
description: "Template sections that need generation should be clearly marked (e.g., <!-- GENERATE: section_name -->)"
205-
severity: "low"
206-
20785
# ============================================
20886
# DOCUMENTATION
20987
# ============================================

.github/workflows/quality.yaml

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
name: Quality & Validation
22

3-
# Runs comprehensive quality checks on all PRs:
3+
# Runs comprehensive quality checks on all PRs and pushes to main:
44
# - Prettier (formatting)
55
# - ESLint (linting)
66
# - markdownlint (markdown quality)
@@ -10,6 +10,8 @@ name: Quality & Validation
1010
# Keep this workflow aligned with `npm run quality` in `package.json`.
1111

1212
"on":
13+
push:
14+
branches: [main]
1315
pull_request:
1416
branches: ["**"]
1517
workflow_dispatch:

.gitignore

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -17,6 +17,8 @@ npm-debug.log*
1717
# Build output
1818
build/*.txt
1919

20+
design-artifacts/
21+
2022
# Environment variables
2123
.env
2224

CHANGELOG.md

Lines changed: 31 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,36 @@
11
# Changelog
22

3+
## v6.2.0 - 2026-03-15
4+
5+
### 🎁 Highlights
6+
7+
* Fix manifest generation so BMad Builder installs correctly when a module has no agents (#1998)
8+
* Prototype preview of bmad-product-brief-preview skill — try `/bmad-product-brief-preview` and share feedback! (#1959)
9+
* All skills now use native skill directory format for improved modularity and maintainability (#1931, #1945, #1946, #1949, #1950, #1984, #1985, #1988, #1994)
10+
11+
### 🎁 Features
12+
13+
* Rewrite code-review skill with sharded step-file architecture and auto-detect review intent from invocation args (#2007, #2013)
14+
* Add inference-based skill validator with comprehensive rules for naming, variables, paths, and invocation syntax (#1981)
15+
* Add REF-03 skill invocation language rule and PATH-05 skill encapsulation rule to validator (#2004)
16+
17+
### 🐛 Bug Fixes
18+
19+
* Validation pass 2 — fix path, variable, and sequence issues across 32 files (#2008)
20+
* Replace broken party-mode workflow refs with skill syntax (#2000)
21+
* Improve bmad-help description for accurate trigger matching (#2012)
22+
* Point zh-cn doc links to Chinese pages instead of English (#2010)
23+
* Validation cleanup for bmad-quick-flow (#1997), 6 skills batch (#1996), bmad-sprint-planning (#1995), bmad-retrospective (#1993), bmad-dev-story (#1992), bmad-create-story (#1991), bmad-code-review (#1990), bmad-create-epics-and-stories (#1989), bmad-create-architecture (#1987), bmad-check-implementation-readiness (#1986), bmad-create-ux-design (#1983), bmad-create-product-brief (#1982)
24+
25+
### 🔧 Maintenance
26+
27+
* Normalize skill invocation syntax to `Invoke the skill` pattern repo-wide (#2004)
28+
29+
### 📚 Documentation
30+
31+
* Add Chinese translation for core-tools reference (#2002)
32+
* Update version hint, TEA module link, and HTTP→HTTPS links in Chinese README (#1922, #1921)
33+
334
## [6.1.0] - 2026-03-12
435

536
### Highlights

README_CN.md

Lines changed: 9 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -20,15 +20,15 @@
2020
- **派对模式** — 将多个智能体角色带入一个会话进行协作和讨论
2121
- **完整生命周期** — 从想法开始(头脑风暴)到部署发布
2222

23-
[**docs.bmad-method.org** 了解更多](http://docs.bmad-method.org)
23+
[**docs.bmad-method.org** 了解更多](https://docs.bmad-method.org/zh-cn/)
2424

2525
---
2626

2727
## 🚀 BMad 的下一步是什么?
2828

2929
**V6 已到来,我们才刚刚开始!** BMad 方法正在快速发展,包括跨平台智能体团队和子智能体集成、技能架构、BMad Builder v1、开发循环自动化等优化,以及更多正在开发中的功能。
3030

31-
**[📍 查看完整路线图 →](http://docs.bmad-method.org/roadmap/)**
31+
**[📍 查看完整路线图 →](https://docs.bmad-method.org/zh-cn/roadmap/)**
3232

3333
---
3434

@@ -40,7 +40,7 @@
4040
npx bmad-method install
4141
```
4242

43-
> 如果你获得的是过时的测试版,请使用:`npx bmad-method@6.0.1 install`
43+
> 想要最新的预发布版本?使用 `npx bmad-method@next install`。相比默认安装,可能会有更多变更。
4444
4545
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)。
4646

@@ -50,7 +50,7 @@ npx bmad-method install
5050
npx bmad-method install --directory /path/to/project --modules bmm --tools claude-code --yes
5151
```
5252

53-
[查看所有安装选项](http://docs.bmad-method.org/how-to/non-interactive-installation/)
53+
[查看非交互式安装选项](https://docs.bmad-method.org/zh-cn/how-to/non-interactive-installation/)
5454

5555
> **不确定该做什么?** 运行 `bmad-help` — 它会准确告诉你下一步做什么以及什么是可选的。你也可以问诸如 `bmad-help 我刚刚完成了架构设计,接下来该做什么?` 之类的问题。
5656
@@ -62,18 +62,18 @@ 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
6262
| ----------------------------------------------------------------------------------------------------------------- | ------------------------------------------------- |
6363
| **[BMad Method (BMM)](https://github.com/bmad-code-org/BMAD-METHOD)** | 包含 34+ 工作流的核心框架 |
6464
| **[BMad Builder (BMB)](https://github.com/bmad-code-org/bmad-builder)** | 创建自定义 BMad 智能体和工作流 |
65-
| **[Test Architect (TEA)](https://github.com/bmad-code-org/tea)** | 基于风险的测试策略和自动化 |
65+
| **[Test Architect (TEA)](https://github.com/bmad-code-org/bmad-method-test-architecture-enterprise)** | 基于风险的测试策略和自动化 |
6666
| **[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) |
6767
| **[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 |
6868

6969
## 文档
7070

71-
[BMad 方法文档站点](http://docs.bmad-method.org) — 教程、指南、概念和参考
71+
[BMad 方法文档站点](https://docs.bmad-method.org/zh-cn/) — 教程、指南、概念和参考
7272

7373
**快速链接:**
74-
- [入门教程](http://docs.bmad-method.org/tutorials/getting-started/)
75-
- [从先前版本升级](http://docs.bmad-method.org/how-to/upgrade-to-v6/)
76-
- [测试架构师文档](https://bmad-code-org.github.io/bmad-method-test-architecture-enterprise/)
74+
- [入门教程](https://docs.bmad-method.org/zh-cn/tutorials/getting-started/)
75+
- [从先前版本升级](https://docs.bmad-method.org/zh-cn/how-to/upgrade-to-v6/)
76+
- [测试架构师文档(英文)](https://bmad-code-org.github.io/bmad-method-test-architecture-enterprise/)
7777

7878

7979
## 社区

docs/how-to/get-answers-about-bmad.md

Lines changed: 0 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -42,8 +42,6 @@ BMad-Help responds with:
4242
- What the first required task is
4343
- What the rest of the process looks like
4444

45-
---
46-
4745
## When to Use This Guide
4846

4947
Use this section when:

docs/how-to/project-context.md

Lines changed: 6 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ sidebar:
55
order: 7
66
---
77

8-
Use the `project-context.md` file to ensure AI agents follow your project's technical preferences and implementation rules throughout all workflows.
8+
Use the `project-context.md` file to ensure AI agents follow your project's technical preferences and implementation rules throughout all workflows. To make sure this is always available, you can also add the line `Important project context and conventions are located in [path to project context]/project-context.md` to your tools context or always rules file (such as `AGENTS.md`)
99

1010
:::note[Prerequisites]
1111
- BMad Method installed
@@ -114,20 +114,11 @@ A `project-context.md` file that:
114114

115115
## Tips
116116

117-
:::tip[Focus on the Unobvious]
118-
Document patterns agents might miss such as "Use JSDoc style comments on every public class, function and variable", not universal practices like "use meaningful variable names" which LLMs know at this point.
119-
:::
120-
121-
:::tip[Keep It Lean]
122-
This file is loaded by every implementation workflow. Long files waste context. Do not include content that only applies to narrow scope or specific stories or features.
123-
:::
124-
125-
:::tip[Update as Needed]
126-
Edit manually when patterns change, or re-generate after significant architecture changes.
127-
:::
128-
129-
:::tip[Works for All Project Types]
130-
Just as useful for Quick Flow as for full BMad Method projects.
117+
:::tip[Best Practices]
118+
- **Focus on the unobvious** — Document patterns agents might miss (e.g., "Use JSDoc on every public class"), not universal practices like "use meaningful variable names."
119+
- **Keep it lean** — This file is loaded by every implementation workflow. Long files waste context. Exclude content that only applies to narrow scope or specific stories.
120+
- **Update as needed** — Edit manually when patterns change, or re-generate after significant architecture changes.
121+
- Works for Quick Flow and full BMad Method projects alike.
131122
:::
132123

133124
## Next Steps

docs/reference/commands.md

Lines changed: 6 additions & 17 deletions
Original file line numberDiff line numberDiff line change
@@ -105,32 +105,21 @@ See [Workflow Map](./workflow-map.md) for the complete workflow reference organi
105105

106106
Tasks and tools are standalone operations that do not require an agent or workflow context.
107107

108-
#### BMad-Help: Your Intelligent Guide
108+
**BMad-Help: Your Intelligent Guide**
109109

110-
**`bmad-help`** is your primary interface for discovering what to do next. It's not just a lookup tool — it's an intelligent assistant that:
111-
112-
- **Inspects your project** to see what's already been done
113-
- **Understands natural language queries** — ask questions in plain English
114-
- **Varies by installed modules** — shows options based on what you have
115-
- **Auto-invokes after workflows** — every workflow ends with clear next steps
116-
- **Recommends the first required task** — no guessing where to start
117-
118-
**Examples:**
110+
`bmad-help` is your primary interface for discovering what to do next. It inspects your project, understands natural language queries, and recommends the next required or optional step based on your installed modules.
119111

112+
:::note[Example]
120113
```
121114
bmad-help
122115
bmad-help I have a SaaS idea and know all the features. Where do I start?
123116
bmad-help What are my options for UX design?
124-
bmad-help I'm stuck on the PRD workflow
125117
```
118+
:::
126119

127-
#### Other Tasks and Tools
120+
**Other Core Tasks and Tools**
128121

129-
| Example skill | Purpose |
130-
| --- | --- |
131-
| `bmad-shard-doc` | Split a large markdown file into smaller sections |
132-
| `bmad-index-docs` | Index project documentation |
133-
| `bmad-editorial-review-prose` | Review document prose quality |
122+
The core module includes 11 built-in tools — reviews, compression, brainstorming, document management, and more. See [Core Tools](./core-tools.md) for the complete reference.
134123

135124
## Naming Convention
136125

0 commit comments

Comments
 (0)