@zeyue0329/xiaoma-cli 1.0.49 → 1.6.4

package/xiaoma-core/tasks/generate-rag-questions.md

@@ -1,312 +0,0 @@
-# 生成知识库查询问题清单任务
-
-## 任务概述
-
-根据需求文档(req.txt)生成结构化的知识库查询问题清单，并保存到项目的 `docs/rag/` 目录下。
-
-## 输入
-
-- **req_file**: 需求文档路径（默认: req.txt）
-
-## 输出
-
-- **输出目录**: `docs/rag/`
-- **主文件**: `docs/rag/_questions.md` - 完整的问题清单
-- **解析结果**: `docs/rag/_requirement-parsing.yaml` - 需求解析结果
-
-## 执行流程
-
-### 步骤 1: 环境准备
-
-```yaml
-执行动作:
-  - 检查需求文档是否存在
-  - 如果 docs/rag/ 目录不存在，创建该目录
-  - 如果目录已存在，询问用户是否覆盖现有文件
-```
-
-### 步骤 2: 读取需求文档
-
-```yaml
-执行动作:
-  - 读取指定的需求文档 {req_file}
-  - 如果文件不存在，提示用户并终止
-  - 显示文档摘要信息（字数、段落数等）
-```
-
-### 步骤 3: 需求文档深度解析
-
-按照 `rag-questions-tmpl.yaml` 模板的第一阶段进行解析，提取以下要素：
-
-```yaml
-解析内容:
-  业务领域:
-    - 主领域识别
-    - 子领域/模块识别
-
-  功能点:
-    - 功能名称和描述
-    - 输入/输出定义
-    - 涉及的实体
-
-  用户角色:
-    - 角色名称
-    - 操作列表
-    - 权限级别
-
-  数据实体:
-    - 实体名称和属性
-    - 实体间关系（一对一/一对多/多对一/多对多）
-    - 关联字段
-
-  业务流程:
-    - 流程名称和触发条件
-    - 步骤详情（序号、名称、执行者、前置步骤、触发条件、输入/输出数据）
-    - 异常分支
-
-  技术组件:
-    - 组件名称
-    - 用途描述
-
-  模糊点:
-    - 位置标记
-    - 内容描述
-    - 可能的理解方式
-```
-
-**交互点**: 展示解析结果，请用户确认或补充修正
-
-### 步骤 4: 生成问题清单
-
-基于解析结果，按照 `rag-questions-tmpl.yaml` 模板生成四类问题：
-
-#### A. 业务知识问题
-- A1-业务规则详解（P0）
-- A2-业务流程详解（P0）- 重点：步骤间关联、节点详情
-- A3-数据关联关系详解（P0）- 重点：一对一/一对多/多对多
-- A4-边界情况与异常处理（P1）
-
-#### B. 技术知识问题
-- B1-整体项目技术架构（P0）
-- B2-中间件使用规范（P0）- 要求提供代码Demo
-- B3-Java编码规范（P0）
-- B4-SQL规范（P0）
-- B5-数据模型（P0）
-- B6-接口规范（P1）
-- B7-代码实现模式（P1）
-
-#### C. 历史追溯问题
-- C1-历史需求（P1）
-- C2-决策记录（P2）
-- C3-已知问题（P1）
-
-#### D. 约束条件问题
-- D1-技术约束（P1）
-- D2-安全合规（P0）
-- D3-性能要求（P1）
-- D4-团队规范（P2）
-
-**交互点**: 展示生成的问题清单，请用户确认或调整
-
-### 步骤 5: 问题优先级排序
-
-```yaml
-优先级规则:
-  P0_阻塞级:
-    - 缺失会导致完全无法理解需求
-    - 涉及核心业务规则
-    - 影响架构决策
-    - 涉及安全合规
-
-  P1_重要级:
-    - 影响需求完整性
-    - 涉及边界情况处理
-    - 影响实现方案选择
-    - 涉及性能要求
-
-  P2_补充级:
-    - 有助于优化实现
-    - 提供额外上下文
-    - 历史参考信息
-```
-
-### 步骤 6: 保存问题清单
-
-将生成的问题清单保存到 `docs/rag/_questions.md`，格式如下：
-
-```markdown
-# 知识库查询问题清单
-
-## 元信息
-- 源文档: {req_file}
-- 生成时间: {timestamp}
-- 总问题数: {total_count}
-- P0问题: {p0_count} | P1问题: {p1_count} | P2问题: {p2_count}
-
----
-
-## P0 阻塞级问题（必须回答）
-
-### A. 业务知识
-
-#### 1. [A1-001] {问题标题}
-- **关联需求**: "{相关需求描述}"
-- **预期答案类型**: {答案类型}
-- **子问题**:
-  - {子问题1}
-  - {子问题2}
-  - ...
-
-### B. 技术知识
-
-#### 1. [B1-001] {问题标题}
-- **关联需求**: "{相关需求描述}"
-- **预期答案类型**: {答案类型}
-- **子问题**:
-  - {子问题1}
-  - {子问题2}
-  - ...
-- **注意**: 请提供相关代码示例
-
----
-
-## P1 重要级问题（强烈建议回答）
-
-...
-
----
-
-## P2 补充级问题（可选回答）
-
-...
-
----
-
-## 下一步操作指引
-
-完成问题清单生成后，请按以下步骤继续：
-
-1. **查询知识库**: 将上述问题发送给知识库MCP获取答案
-2. **知识落地**: 使用 `*land-knowledge` 命令将答案保存到 `docs/rag/` 对应子目录
-3. **生成PRD**: 使用 `*create-prd-from-rag` 命令基于知识生成PRD文档
-```
-
-### 步骤 7: 保存解析结果
-
-将需求解析结果保存到 `docs/rag/_requirement-parsing.yaml`：
-
-```yaml
-# 需求解析结果
-# 生成时间: {timestamp}
-# 源文档: {req_file}
-
-requirement_parsing:
-  business_domain: {domain}
-  sub_domains: [{sub_domains}]
-
-  features:
-    - name: {feature_name}
-      description: {description}
-      input: {input}
-      output: {output}
-      entities: [{entities}]
-
-  roles:
-    - name: {role_name}
-      actions: [{actions}]
-      permission_level: {level}
-
-  entities:
-    - name: {entity_name}
-      attributes: [{attributes}]
-      relationships:
-        - target: {target_entity}
-          type: {one-to-one|one-to-many|many-to-one|many-to-many}
-          field: {field_name}
-
-  processes:
-    - name: {process_name}
-      trigger: {trigger_condition}
-      steps:
-        - index: {n}
-          name: {step_name}
-          actor: {actor}
-          previous_step: {prev}
-          trigger_from_previous: {condition}
-          input_data: {input}
-          output_data: {output}
-          data_changes: {changes}
-      exception_branches: [{branches}]
-
-  tech_components:
-    - name: {component}
-      purpose: {purpose}
-
-  ambiguities:
-    - location: {loc}
-      content: {content}
-      interpretations: [{interpretations}]
-```
-
-### 步骤 8: 生成目录结构
-
-创建后续知识落地所需的目录结构：
-
-```bash
-docs/rag/
-├── _questions.md              # 问题清单（本任务生成）
-├── _requirement-parsing.yaml  # 需求解析结果（本任务生成）
-├── _index.md                  # 知识索引（后续生成）
-├── business/                  # 业务知识目录
-├── technical/                 # 技术知识目录
-│   ├── middleware/           # 中间件规范
-│   ├── coding-standards/     # 编码规范
-│   └── sql-standards/        # SQL规范
-├── history/                   # 历史信息目录
-└── constraints/               # 约束条件目录
-```
-
-### 步骤 9: 完成提示
-
-```yaml
-完成输出:
-  - 显示生成的文件列表和路径
-  - 显示问题统计信息（各类别数量）
-  - 提供下一步操作建议
-```
-
----
-
-## 交互模式说明
-
-本任务支持两种模式：
-
-### 交互模式（默认）
-- 每个关键步骤后暂停，等待用户确认
-- 允许用户调整解析结果和问题清单
-- 适合首次使用或复杂需求
-
-### YOLO模式
-- 一次性完成所有步骤
-- 自动使用默认值
-- 适合熟悉流程后快速生成
-
-可通过 `*yolo` 命令切换模式。
-
----
-
-## 依赖模板
-
-- `rag-questions-tmpl.yaml` - 问题生成模板
-
-## 输出文件
-
-| 文件 | 路径 | 说明 |
-|------|------|------|
-| 问题清单 | `docs/rag/_questions.md` | 完整的知识库查询问题 |
-| 解析结果 | `docs/rag/_requirement-parsing.yaml` | 需求文档解析的结构化结果 |
-
-## 后续命令
-
-- `*land-knowledge` - 将知识库返回的内容结构化存储
-- `*create-prd-from-rag` - 基于RAG知识生成PRD

package/xiaoma-core/tasks/index-docs.md

@@ -1,175 +0,0 @@
-<!-- Powered by XiaoMa™ Core -->
-
-# Index Documentation Task
-
-## Purpose
-
-This task maintains the integrity and completeness of the `docs/index.md` file by scanning all documentation files and ensuring they are properly indexed with descriptions. It handles both root-level documents and documents within subfolders, organizing them hierarchically.
-
-## Task Instructions
-
-You are now operating as a Documentation Indexer. Your goal is to ensure all documentation files are properly cataloged in the central index with proper organization for subfolders.
-
-### Required Steps
-
-1. First, locate and scan:
-   - The `docs/` directory and all subdirectories
-   - The existing `docs/index.md` file (create if absent)
-   - All markdown (`.md`) and text (`.txt`) files in the documentation structure
-   - Note the folder structure for hierarchical organization
-
-2. For the existing `docs/index.md`:
-   - Parse current entries
-   - Note existing file references and descriptions
-   - Identify any broken links or missing files
-   - Keep track of already-indexed content
-   - Preserve existing folder sections
-
-3. For each documentation file found:
-   - Extract the title (from first heading or filename)
-   - Generate a brief description by analyzing the content
-   - Create a relative markdown link to the file
-   - Check if it's already in the index
-   - Note which folder it belongs to (if in a subfolder)
-   - If missing or outdated, prepare an update
-
-4. For any missing or non-existent files found in index:
-   - Present a list of all entries that reference non-existent files
-   - For each entry:
-     - Show the full entry details (title, path, description)
-     - Ask for explicit confirmation before removal
-     - Provide option to update the path if file was moved
-     - Log the decision (remove/update/keep) for final report
-
-5. Update `docs/index.md`:
-   - Maintain existing structure and organization
-   - Create level 2 sections (`##`) for each subfolder
-   - List root-level documents first
-   - Add missing entries with descriptions
-   - Update outdated entries
-   - Remove only entries that were confirmed for removal
-   - Ensure consistent formatting throughout
-
-### Index Structure Format
-
-The index should be organized as follows:
-
-```markdown
-# Documentation Index
-
-## Root Documents
-
-### [Document Title](./document.md)
-
-Brief description of the document's purpose and contents.
-
-### [Another Document](./another.md)
-
-Description here.
-
-## Folder Name
-
-Documents within the `folder-name/` directory:
-
-### [Document in Folder](./folder-name/document.md)
-
-Description of this document.
-
-### [Another in Folder](./folder-name/another.md)
-
-Description here.
-
-## Another Folder
-
-Documents within the `another-folder/` directory:
-
-### [Nested Document](./another-folder/document.md)
-
-Description of nested document.
-```
-
-### Index Entry Format
-
-Each entry should follow this format:
-
-```markdown
-### [Document Title](relative/path/to/file.md)
-
-Brief description of the document's purpose and contents.
-```
-
-### Rules of Operation
-
-1. NEVER modify the content of indexed files
-2. Preserve existing descriptions in index.md when they are adequate
-3. Maintain any existing categorization or grouping in the index
-4. Use relative paths for all links (starting with `./`)
-5. Ensure descriptions are concise but informative
-6. NEVER remove entries without explicit confirmation
-7. Report any broken links or inconsistencies found
-8. Allow path updates for moved files before considering removal
-9. Create folder sections using level 2 headings (`##`)
-10. Sort folders alphabetically, with root documents listed first
-11. Within each section, sort documents alphabetically by title
-
-### Process Output
-
-The task will provide:
-
-1. A summary of changes made to index.md
-2. List of newly indexed files (organized by folder)
-3. List of updated entries
-4. List of entries presented for removal and their status:
-   - Confirmed removals
-   - Updated paths
-   - Kept despite missing file
-5. Any new folders discovered
-6. Any other issues or inconsistencies found
-
-### Handling Missing Files
-
-For each file referenced in the index but not found in the filesystem:
-
-1. Present the entry:
-
-   ```markdown
-   Missing file detected:
-   Title: [Document Title]
-   Path: relative/path/to/file.md
-   Description: Existing description
-   Section: [Root Documents | Folder Name]
-
-   Options:
-
-   1. Remove this entry
-   2. Update the file path
-   3. Keep entry (mark as temporarily unavailable)
-
-   Please choose an option (1/2/3):
-   ```
-
-2. Wait for user confirmation before taking any action
-3. Log the decision for the final report
-
-### Special Cases
-
-1. **Sharded Documents**: If a folder contains an `index.md` file, treat it as a sharded document:
-   - Use the folder's `index.md` title as the section title
-   - List the folder's documents as subsections
-   - Note in the description that this is a multi-part document
-
-2. **README files**: Convert `README.md` to more descriptive titles based on content
-
-3. **Nested Subfolders**: For deeply nested folders, maintain the hierarchy but limit to 2 levels in the main index. Deeper structures should have their own index files.
-
-## Required Input
-
-Please provide:
-
-1. Location of the `docs/` directory (default: `./docs`)
-2. Confirmation of write access to `docs/index.md`
-3. Any specific categorization preferences
-4. Any files or directories to exclude from indexing (e.g., `.git`, `node_modules`)
-5. Whether to include hidden files/folders (starting with `.`)
-
-Would you like to proceed with documentation indexing? Please provide the required input above.

package/xiaoma-core/tasks/kb-mode-interaction.md

@@ -1,77 +0,0 @@
-<!-- Powered by XiaoMa™ Core -->
-
-# KB Mode Interaction Task
-
-## Purpose
-
-Provide a user-friendly interface to the BMad knowledge base without overwhelming users with information upfront.
-
-## Instructions
-
-When entering KB mode (\*kb-mode), follow these steps:
-
-### 1. Welcome and Guide
-
-Announce entering KB mode with a brief, friendly introduction.
-
-### 2. Present Topic Areas
-
-Offer a concise list of main topic areas the user might want to explore:
-
-**What would you like to know more about?**
-
-1. **Setup & Installation** - Getting started with BMad
-2. **Workflows** - Choosing the right workflow for your project
-3. **Web vs IDE** - When to use each environment
-4. **Agents** - Understanding specialized agents and their roles
-5. **Documents** - PRDs, Architecture, Stories, and more
-6. **Agile Process** - How BMad implements Agile methodologies
-7. **Configuration** - Customizing BMad for your needs
-8. **Best Practices** - Tips for effective BMad usage
-
-Or ask me about anything else related to XiaoMa-Cli!
-
-### 3. Respond Contextually
-
-- Wait for user's specific question or topic selection
-- Provide focused, relevant information from the knowledge base
-- Offer to dive deeper or explore related topics
-- Keep responses concise unless user asks for detailed explanations
-
-### 4. Interactive Exploration
-
-- After answering, suggest related topics they might find helpful
-- Maintain conversational flow rather than data dumping
-- Use examples when appropriate
-- Reference specific documentation sections when relevant
-
-### 5. Exit Gracefully
-
-When user is done or wants to exit KB mode:
-
-- Summarize key points discussed if helpful
-- Remind them they can return to KB mode anytime with \*kb-mode
-- Suggest next steps based on what was discussed
-
-## Example Interaction
-
-**User**: \*kb-mode
-
-**Assistant**: I've entered KB mode and have access to the full BMad knowledge base. I can help you with detailed information about any aspect of XiaoMa-Cli.
-
-**What would you like to know more about?**
-
-1. **Setup & Installation** - Getting started with BMad
-2. **Workflows** - Choosing the right workflow for your project
-3. **Web vs IDE** - When to use each environment
-4. **Agents** - Understanding specialized agents and their roles
-5. **Documents** - PRDs, Architecture, Stories, and more
-6. **Agile Process** - How BMad implements Agile methodologies
-7. **Configuration** - Customizing BMad for your needs
-8. **Best Practices** - Tips for effective BMad usage
-
-Or ask me about anything else related to XiaoMa-Cli!
-
-**User**: Tell me about workflows
-
-**Assistant**: [Provides focused information about workflows from the KB, then offers to explore specific workflow types or related topics]