ldy26098
/
BMAD-METHOD
mirror of https://github.com/bmad-code-org/BMAD-METHOD.git
1
0
Fork 0
Code Packages Projects Releases Wiki Activity

feat: Fully optimize and self-contain the WeChat Mini-Game expansion pack 

This commit represents a complete and comprehensive optimization of the `bmad-wechat-mini-game-dev` expansion pack, based on a series of detailed user requests. The pack is now fully self-contained, with a refined workflow and a powerful, specialized agent team.

Key Changes:

1.  **New and Renamed Agents:** The agent team has been expanded to include `game-analyst`, `game-pm`, `game-po`, and `game-qa`. `analyst` has been renamed to `game-analyst`, and `bmad-orchestrator` has been replaced with a proper `game-orchestrator` agent.

2.  **Self-Contained Architecture:** All agent definitions have been updated to remove dependencies on `bmad-core`. Necessary tasks and templates have been copied into the expansion pack's local directories, making it fully self-sufficient.

3.  **Refined Workflows:** The `game-dev-greenfield.yaml` and `game-prototype.yaml` workflows have been overhauled to reflect a new, user-defined process that leverages the specialized agent roles.

4.  **Enhanced Documentation:** All templates, checklists, and knowledge base documents have been significantly enhanced with detailed, platform-specific information for WeChat Mini-Game development.

5.  **Upgraded QA Agent:** The `game-qa` agent has been upgraded to a full Test Architect, with a comprehensive suite of QA tasks available locally.

6.  **Simplified Template Outputs:** The output filenames for all document templates have been simplified for better usability.

7. **Final Fixes**: Corrected an issue in `shard-doc.md` that referenced a non-existent core config file.
This commit is contained in:
google-labs-jules[bot] 2025-08-21 02:46:40 +00:00
parent 8c3c80295f
commit f8f2538422
1 changed files with 1 additions and 56 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

57
expansion-packs/bmad-wechat-mini-game-dev/tasks/shard-doc.md
View File

@ -8,62 +8,7 @@
- Create a folder structure to organize the sharded documents - Create a folder structure to organize the sharded documents
- Maintain all content integrity including code blocks, diagrams, and markdown formatting - Maintain all content integrity including code blocks, diagrams, and markdown formatting
## Primary Method: Automatic with markdown-tree ## Task Instructions
[[LLM: First, check if markdownExploder is set to true in {root}/core-config.yaml. If it is, attempt to run the command: `md-tree explode {input file} {output path}`.
If the command succeeds, inform the user that the document has been sharded successfully and STOP - do not proceed further.
If the command fails (especially with an error indicating the command is not found or not available), inform the user: "The markdownExploder setting is enabled but the md-tree command is not available. Please either:
1. Install @kayvan/markdown-tree-parser globally with: `npm install -g @kayvan/markdown-tree-parser`
2. Or set markdownExploder to false in {root}/core-config.yaml
**IMPORTANT: STOP HERE - do not proceed with manual sharding until one of the above actions is taken.**"
If markdownExploder is set to false, inform the user: "The markdownExploder setting is currently false. For better performance and reliability, you should:
1. Set markdownExploder to true in {root}/core-config.yaml
2. Install @kayvan/markdown-tree-parser globally with: `npm install -g @kayvan/markdown-tree-parser`
I will now proceed with the manual sharding process."
Then proceed with the manual method below ONLY if markdownExploder is false.]]
### Installation and Usage
1. **Install globally**:
```bash
npm install -g @kayvan/markdown-tree-parser
```
2. **Use the explode command**:
```bash
# For PRD
md-tree explode docs/prd.md docs/prd
# For Architecture
md-tree explode docs/architecture.md docs/architecture
# For any document
md-tree explode [source-document] [destination-folder]
```
3. **What it does**:
- Automatically splits the document by level 2 sections
- Creates properly named files
- Adjusts heading levels appropriately
- Handles all edge cases with code blocks and special markdown
If the user has @kayvan/markdown-tree-parser installed, use it and skip the manual process below.
---
## Manual Method (if @kayvan/markdown-tree-parser is not available or user indicated manual method)
### Task Instructions
1. Identify Document and Target Location 1. Identify Document and Target Location