mirror of
https://github.com/cjo4m06/mcp-shrimp-task-manager.git
synced 2025-07-26 07:52:25 +08:00
更新 README 和中文文檔，新增目錄及各功能部分的標籤，強化使用指南與任務管理流程的描述，並調整相關內容以提升可讀性與結構化。
This commit is contained in:
siage
parent
b07672c805
commit
31065fa531
82
README.md
82
README.md
@ -1,5 +1,19 @@
|
||||
[English](README.md) | [中文](docs/zh/README.md)
|
||||
|
||||
## 目錄
|
||||
|
||||
- [✨ Features](#features1)
|
||||
- [🧭 Usage Guide](#usage-guide)
|
||||
- [🧠 Task Memory Function](#task-memory-function)
|
||||
- [🤔 Thought Chain Process](#thought-chain)
|
||||
- [📋 Project Rules Initialization](#project-rules)
|
||||
- [📚 Documentation Resources](#documentation)
|
||||
- [🔧 Installation and Usage](#installation)
|
||||
- [🔌 Using with MCP-Compatible Clients](#clients)
|
||||
- [💡 System Prompt Guidance](#prompt)
|
||||
- [🛠️ Available Tools Overview](#tools)
|
||||
- [📄 License](#license)
|
||||
|
||||
# MCP Shrimp Task Manager
|
||||
|
||||
[](https://smithery.ai/server/@cjo4m06/mcp-shrimp-task-manager)
|
||||
@ -12,7 +26,7 @@
|
||||
|
||||
Shrimp Task Manager guides Agents through structured workflows for systematic programming, enhancing task memory management mechanisms, and effectively avoiding redundant and repetitive coding work.
|
||||
|
||||
## ✨ Features
|
||||
## ✨ <a id="features1"></a>Features
|
||||
|
||||
- **Task Planning and Analysis**: Deep understanding and analysis of complex task requirements
|
||||
- **Intelligent Task Decomposition**: Automatically break down large tasks into manageable smaller tasks
|
||||
@ -25,25 +39,39 @@ Shrimp Task Manager guides Agents through structured workflows for systematic pr
|
||||
- **Thought Chain Process**: Step-by-step reasoning to analyze complex problems systematically
|
||||
- **Project Rules Initialization**: Define project standards and rules to maintain consistency across large projects
|
||||
|
||||
## 🔄 Task Management Workflow
|
||||
## 🧭 <a id="usage-guide"></a>Usage Guide
|
||||
|
||||
The system provides a complete task management lifecycle:
|
||||
Shrimp Task Manager offers a structured approach to AI-assisted programming through guided workflows and systematic task management.
|
||||
|
||||
1. **Start Planning** `plan_task`: Analyze task problems, determine requirement scope
|
||||
2. **In-depth Analysis** `analyze_task`: Check existing codebase to avoid duplicate work
|
||||
3. **Solution Reflection** `reflect_task`: Critically review analysis results, ensure comprehensive solutions
|
||||
4. **Task Decomposition** `split_tasks`: Break down complex tasks into smaller ones, establish clear dependencies
|
||||
5. **Task List** `list_tasks`: View all tasks and their execution status
|
||||
6. **Execute Task** `execute_task`: Execute specific tasks while assessing complexity
|
||||
7. **Result Verification** `verify_task`: Comprehensively check task completion
|
||||
8. **Task Completion** `complete_task`: Mark tasks as complete and generate reports, automatically update summaries
|
||||
9. **Task Management** `delete_task`: Manage incomplete tasks (completed tasks remain in the system)
|
||||
10. **Query Tasks** `query_task`: Search for related tasks in past memories using keywords
|
||||
11. **Display Task** `get_task_detail`: Display complete task guidance
|
||||
12. **Process Thought** `process_thought`: Conduct step-by-step reasoning for complex problem analysis
|
||||
13. **Initialize Project Rules** `init_project_rules`: Set up and maintain project standards and conventions
|
||||
### What is Shrimp?
|
||||
|
||||
## 🧠 Task Memory Function
|
||||
Shrimp is essentially a prompt template that guides AI Agents to better understand and work with your project. It uses a series of prompts to ensure the Agent aligns closely with your project's specific needs and conventions.
|
||||
|
||||
### First-Time Setup
|
||||
|
||||
When working with a new project, simply tell the Agent "init project rules". This will guide the Agent to generate a set of rules tailored to your project's specific requirements and structure.
|
||||
|
||||
### Task Planning Process
|
||||
|
||||
To develop or update features, use the command "plan task [your description]". The system will reference the previously established rules, attempt to understand your project, search for relevant code sections, and propose a comprehensive plan based on the current state of your project.
|
||||
|
||||
### Feedback Mechanism
|
||||
|
||||
During the planning process, Shrimp guides the Agent through multiple steps of thinking. You can review this process and provide feedback if you feel it's heading in the wrong direction. Simply interrupt and share your perspective - the Agent will incorporate your feedback and continue the planning process.
|
||||
|
||||
### Task Execution
|
||||
|
||||
When you're satisfied with the plan, use "execute task [task name or ID]" to implement it. If you don't specify a task name or ID, the system will automatically identify and execute the highest priority task.
|
||||
|
||||
### Continuous Mode
|
||||
|
||||
If you prefer to execute all tasks in sequence without manual intervention for each task, use "continuous mode" to automatically process the entire task queue.
|
||||
|
||||
### Token Limitation Note
|
||||
|
||||
Due to LLM token limits, context may be lost during lengthy conversations. If this occurs, simply open a new chat session and ask the Agent to continue execution. The system will pick up where it left off without requiring you to repeat the task details or context.
|
||||
|
||||
## 🧠 <a id="task-memory-function"></a>Task Memory Function
|
||||
|
||||
Shrimp Task Manager has long-term memory capabilities, automatically saving task execution history and providing reference experiences when planning new tasks.
|
||||
|
||||
@ -62,7 +90,7 @@ Shrimp Task Manager has long-term memory capabilities, automatically saving task
|
||||
|
||||
Through effective use of the task memory function, the system can continuously accumulate experience, with intelligence level and work efficiency continuously improving.
|
||||
|
||||
## 🤔 Thought Chain Process
|
||||
## 🤔 <a id="thought-chain"></a>Thought Chain Process
|
||||
|
||||
The Thought Chain feature enhances problem-solving through structured thinking:
|
||||
|
||||
@ -73,7 +101,7 @@ The Thought Chain feature enhances problem-solving through structured thinking:
|
||||
|
||||
When enabled (default setting), the system guides the Agent through step-by-step reasoning using the `process_thought` tool, ensuring thorough problem analysis before implementation.
|
||||
|
||||
## 📋 Project Rules Initialization
|
||||
## 📋 <a id="project-rules"></a>Project Rules Initialization
|
||||
|
||||
The Project Rules feature helps maintain consistency across your codebase:
|
||||
|
||||
@ -99,13 +127,13 @@ You can easily access this feature with simple natural language commands:
|
||||
|
||||
This tool is particularly valuable when your codebase expands or undergoes significant structural changes, helping maintain consistent development practices throughout the project lifecycle.
|
||||
|
||||
## 📚 Documentation Resources
|
||||
## 📚 <a id="documentation"></a>Documentation Resources
|
||||
|
||||
- [System Architecture](docs/en/architecture.md): Detailed system design and data flow explanation
|
||||
- [Prompt Customization Guide](docs/en/prompt-customization.md): Instructions for customizing tool prompts via environment variables
|
||||
- [Changelog](CHANGELOG.md): Record of all notable changes to this project
|
||||
|
||||
## 🔧 Installation and Usage
|
||||
## 🔧 <a id="installation"></a>Installation and Usage
|
||||
|
||||
### Installing via Smithery
|
||||
|
||||
@ -125,7 +153,7 @@ npm install
|
||||
npm run build
|
||||
```
|
||||
|
||||
## 🔌 Using with MCP-Compatible Clients
|
||||
## 🔌 <a id="clients"></a>Using with MCP-Compatible Clients
|
||||
|
||||
Shrimp Task Manager can be used with any client that supports the Model Context Protocol, such as Cursor IDE.
|
||||
|
||||
@ -158,7 +186,7 @@ or
|
||||
"mcpServers": {
|
||||
"shrimp-task-manager": {
|
||||
"command": "npx",
|
||||
"args": ["mcp-shrimp-task-manager"],
|
||||
"args": ["-y", "mcp-shrimp-task-manager"],
|
||||
"env": {
|
||||
"DATA_DIR": "/mcp-shrimp-task-manager/data"
|
||||
}
|
||||
@ -196,7 +224,7 @@ or
|
||||
"mcpServers": {
|
||||
"shrimp-task-manager": {
|
||||
"command": "npx",
|
||||
"args": ["mcp-shrimp-task-manager"],
|
||||
"args": ["-y", "mcp-shrimp-task-manager"],
|
||||
"env": {
|
||||
"DATA_DIR": "/path/to/project/data" // 必須使用絕對路徑
|
||||
}
|
||||
@ -249,7 +277,7 @@ Additionally, there are other system configuration variables:
|
||||
|
||||
For detailed instructions on customizing prompts, including supported parameters and examples, see the [Prompt Customization Guide](docs/en/prompt-customization.md).
|
||||
|
||||
## 💡 System Prompt Guidance
|
||||
## 💡 <a id="prompt"></a>System Prompt Guidance
|
||||
|
||||
### Cursor IDE Configuration
|
||||
|
||||
@ -285,7 +313,7 @@ If your tool doesn't support Custom modes, you can:
|
||||
- Manually paste the appropriate prompts at different stages
|
||||
- Or directly use simple commands like `Please plan the following task: ......` or `Please start executing the task...`
|
||||
|
||||
## 🛠️ Available Tools Overview
|
||||
## 🛠️ <a id="tools"></a>Available Tools Overview
|
||||
|
||||
After configuration, you can use the following tools:
|
||||
|
||||
@ -312,6 +340,6 @@ After configuration, you can use the following tools:
|
||||
- **MCP SDK**: Interface for seamless interaction with large language models
|
||||
- **UUID**: Generate unique and reliable task identifiers
|
||||
|
||||
## 📄 License
|
||||
## 📄 <a id="license"></a>License
|
||||
|
||||
This project is released under the MIT License
|
||||
|
||||
@ -1,5 +1,19 @@
|
||||
[English](../../README.md) | [中文](README.md)
|
||||
|
||||
## 目錄
|
||||
|
||||
- [✨ 功能特點](#功能特點1)
|
||||
- [📖 使用指南](#使用指南)
|
||||
- [🧠 任務記憶功能](#任務記憶功能)
|
||||
- [🤔 思維鏈過程](#思維鏈過程)
|
||||
- [📋 專案規範初始化](#專案規範初始化)
|
||||
- [📚 文件資源](#文件資源)
|
||||
- [🔧 安裝與使用](#安裝與使用)
|
||||
- [🔌 在支援 MCP 的客戶端中使用](#客戶端中使用)
|
||||
- [💡 系統提示詞指導](#系統提示詞指導)
|
||||
- [🛠️ 可用工具一覽](#可用工具一覽)
|
||||
- [📄 許可協議](#許可協議)
|
||||
|
||||
# MCP 蝦米任務管理器
|
||||
|
||||
[](https://smithery.ai/server/@cjo4m06/mcp-shrimp-task-manager)
|
||||
@ -8,7 +22,7 @@
|
||||
|
||||
蝦米任務管理器透過結構化的工作流程引導，協助 Agent 系統性規劃程式開發步驟，強化任務記憶管理機制，有效避免冗餘與重複的編程工作。
|
||||
|
||||
## ✨ 功能特點
|
||||
## ✨ <a id="功能特點1"></a>功能特點
|
||||
|
||||
- **任務規劃與分析**：深入理解與分析複雜任務需求
|
||||
- **智能任務拆分**：將大型任務自動拆分為可管理的小型任務
|
||||
@ -21,25 +35,39 @@
|
||||
- **思維鏈過程**：通過步驟化的推理系統性地分析複雜問題
|
||||
- **專案規範初始化**：定義專案標準和規則，維持大型專案的一致性
|
||||
|
||||
## 🔄 任務管理工作流程
|
||||
## 🧭 <a id="使用指南"></a>使用指南
|
||||
|
||||
本系統提供完整的任務管理生命週期：
|
||||
蝦米任務管理器提供結構化的 AI 輔助程式開發方法，通過引導式工作流程和系統化任務管理實現高效開發。
|
||||
|
||||
1. **開始規劃** `plan_task`：分析任務問題，確定需求範圍
|
||||
2. **深入分析** `analyze_task`：檢查現有代碼庫避免重複工作
|
||||
3. **方案反思** `reflect_task`：批判性審查分析結果，確保方案完善
|
||||
4. **任務拆分** `split_tasks`：將複雜任務分解為小型任務，建立明確依賴關係
|
||||
5. **任務列表** `list_tasks`：查看所有任務及其執行狀態
|
||||
6. **執行任務** `execute_task`：執行特定任務，同時評估複雜度
|
||||
7. **結果檢驗** `verify_task`：全面檢查任務完成情況
|
||||
8. **任務完成** `complete_task`：標記任務完成並生成報告，自動更新摘要
|
||||
9. **任務管理** `delete_task`：管理未完成的任務（已完成任務將保留在系統中）
|
||||
10. **查詢任務** `query_task`：透過關鍵字查詢以往記憶是否有相關任務
|
||||
11. **顯示任務** `get_task_detail`：顯示完整任務指導
|
||||
12. **思維處理** `process_thought`：進行步驟化推理，系統性分析複雜問題
|
||||
13. **初始化專案規範** `init_project_rules`：建立和維護專案標準與規範
|
||||
### 什麼是蝦米？
|
||||
|
||||
## 🧠 任務記憶功能
|
||||
蝦米本質上是一個提示詞範本，通過一系列提示詞引導 AI Agent 更好地理解和適應您的專案。它確保 Agent 能夠更貼近您專案的特定需求和慣例。
|
||||
|
||||
### 首次使用設置
|
||||
|
||||
在使用新專案時，只需對 Agent 說「init project rules」（初始化專案規則）。這將引導 Agent 生成一份符合您專案特定需求和結構的規則檔案。
|
||||
|
||||
### 任務規劃流程
|
||||
|
||||
要開發或更新功能，使用命令「plan task [您的描述]」（規劃任務 [您的描述]）。系統將參考先前建立的規則，嘗試理解您的專案，搜尋相關程式碼區塊，並根據專案的當前狀態提出全面的計劃。
|
||||
|
||||
### 反饋機制
|
||||
|
||||
在規劃過程中，蝦米引導 Agent 進行多步驟思考。您可以審查這個過程，如果您覺得某個部分偏離了您的目標，可以直接打斷並提出您的觀點。Agent 將採納您的反饋並繼續思考過程。
|
||||
|
||||
### 任務執行
|
||||
|
||||
當您對規劃內容滿意後，使用「execute task [任務名稱或 ID]」（執行任務 [任務名稱或 ID]）來實施計劃。如果您不指定任務名稱或 ID，系統將自動識別並執行最優先的任務。
|
||||
|
||||
### 連續模式
|
||||
|
||||
如果您希望連續執行所有任務而不需要為每個任務手動干預，可以使用「continuous mode」（連續模式）自動處理整個任務隊列。
|
||||
|
||||
### Token 限制注意事項
|
||||
|
||||
由於 LLM 的 Token 限制，在長時間對話中可能會喪失上下文。如果發生這種情況，只需開啟新的聊天會話並請 Agent 繼續執行即可。系統將從上次中斷的地方繼續，無需重複任務細節或上下文。
|
||||
|
||||
## 🧠 <a id="任務記憶功能"></a>任務記憶功能
|
||||
|
||||
蝦米任務管理器具備長期記憶功能，可以自動保存任務執行的歷史記錄，並在規劃新任務時提供參考經驗。
|
||||
|
||||
@ -58,7 +86,7 @@
|
||||
|
||||
通過有效利用任務記憶功能，系統能夠不斷積累經驗，智能化程度和工作效率將持續提升。
|
||||
|
||||
## 🤔 思維鏈過程
|
||||
## 🤔 <a id="思維鏈過程"></a>思維鏈過程
|
||||
|
||||
思維鏈功能通過結構化思考增強問題解決能力：
|
||||
|
||||
@ -69,7 +97,7 @@
|
||||
|
||||
當啟用此功能（預設設定）時，系統會引導 Agent 使用 `process_thought` 工具進行逐步推理，確保在實施前進行徹底的問題分析。
|
||||
|
||||
## 📋 專案規範初始化
|
||||
## 📋 <a id="專案規範初始化"></a>專案規範初始化
|
||||
|
||||
專案規範功能有助於維持代碼庫的一致性：
|
||||
|
||||
@ -95,13 +123,13 @@
|
||||
|
||||
當您的代碼庫擴展或經歷重大結構變化時，此工具特別有價值，有助於在整個專案生命週期中保持一致的開發實踐。
|
||||
|
||||
## 📚 文件資源
|
||||
## 📚 <a id="文件資源"></a>文件資源
|
||||
|
||||
- [系統架構](architecture.md)：詳細的系統設計與數據流說明
|
||||
- [提示詞自定義指南](prompt-customization.md)：透過環境變數自定義工具提示詞的說明
|
||||
- [更新日誌](CHANGELOG.md)：記錄此專案的所有重要變更
|
||||
|
||||
## 🔧 安裝與使用
|
||||
## 🔧 <a id="安裝與使用"></a>安裝與使用
|
||||
|
||||
### Installing via Smithery
|
||||
|
||||
@ -121,7 +149,7 @@ npm install
|
||||
npm run build
|
||||
```
|
||||
|
||||
## 🔌 在支援 MCP 的客戶端中使用
|
||||
## 🔌 <a id="客戶端中使用"></a>在支援 MCP 的客戶端中使用
|
||||
|
||||
蝦米任務管理器可以與任何支援 Model Context Protocol 的客戶端一起使用，例如 Cursor IDE。
|
||||
|
||||
@ -153,7 +181,7 @@ or
|
||||
"mcpServers": {
|
||||
"shrimp-task-manager": {
|
||||
"command": "npx",
|
||||
"args": ["mcp-shrimp-task-manager"],
|
||||
"args": ["-y", "mcp-shrimp-task-manager"],
|
||||
"env": {
|
||||
"DATA_DIR": "/mcp-shrimp-task-manager/data"
|
||||
}
|
||||
@ -190,7 +218,7 @@ or
|
||||
"mcpServers": {
|
||||
"shrimp-task-manager": {
|
||||
"command": "npx",
|
||||
"args": ["mcp-shrimp-task-manager"],
|
||||
"args": ["-y", "mcp-shrimp-task-manager"],
|
||||
"env": {
|
||||
"DATA_DIR": "/path/to/project/data" // 必須使用絕對路徑
|
||||
}
|
||||
@ -243,7 +271,7 @@ or
|
||||
|
||||
有關自定義提示詞的詳細說明，包括支援的參數和範例，請參閱[提示詞自定義指南](prompt-customization.md)。
|
||||
|
||||
## 💡 系統提示詞指導
|
||||
## 💡 <a id="系統提示詞指導"></a>系統提示詞指導
|
||||
|
||||
### Cursor IDE 配置
|
||||
|
||||
@ -279,7 +307,7 @@ or
|
||||
- 在不同階段手動貼上相應的提示詞
|
||||
- 或直接使用簡單命令如 `請規劃以下任務：......` 或 `請開始執行任務...`
|
||||
|
||||
## 🛠️ 可用工具一覽
|
||||
## 🛠️ <a id="可用工具一覽"></a>可用工具一覽
|
||||
|
||||
配置完成後，您可使用以下工具：
|
||||
|
||||
@ -299,13 +327,6 @@ or
|
||||
| | `verify_task` | 檢驗任務完成情況 |
|
||||
| | `complete_task` | 標記任務為已完成 |
|
||||
|
||||
## 🔧 技術實現
|
||||
|
||||
- **Node.js**：高效能的 JavaScript 運行時環境
|
||||
- **TypeScript**：提供強型別安全的開發環境
|
||||
- **MCP SDK**：與大型語言模型無縫互動的接口
|
||||
- **UUID**：生成唯一且可靠的任務識別碼
|
||||
|
||||
## 📄 許可協議
|
||||
## 📄 <a id="許可協議"></a>許可協議
|
||||
|
||||
本專案採用 MIT 許可協議發布
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user