← 返回 Skills 市场
43622283

Mvp Kanban Complete Skill

作者 Terry S Fisher · GitHub ↗ · v0.0.2 · MIT-0
cross-platform ⚠ suspicious
121
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install li-mvp-kanban-complete-skill
功能描述
提供完整MVP看板任务管理,支持任务和泳道管理、批量操作、AI分析、向量搜索,含Docker镜像和21个MCP工具接口。
使用说明 (SKILL.md)

MVP Kanban Board Skill - v0.0.1

📖 描述

MVP 看板系统 - 完整的任务管理技能,包含 Docker 镜像和完整源代码。 支持任务管理、泳道管理、批量操作、AI 分析和向量搜索。 通过 MCP 协议提供 21 个工具,支持 Web 界面、REST API 和 MCP 工具调用。

✨ 功能特性

  • 完整应用 - 包含 Docker 镜像和所有源代码
  • 任务管理 - 增删改查、拖拽移动、双击编辑
  • 泳道管理 - 自定义泳道、颜色、图标
  • 批量操作 - 批量创建/更新/删除任务
  • AI 分析 - 瓶颈识别、风险预警、建议生成
  • 向量搜索 - 语义级任务搜索
  • 自然语言 - 中文命令解析
  • Web 界面 - 可视化操作、拖拽交互
  • 数据持久化 - SQLite 数据库
  • MCP 集成 - 21 个 MCP 工具

🚀 快速开始

方式 1: 从 ClawHub 安装(推荐)

clawhub install mvp-kanban

方式 2: 本地安装

# 1. 复制 Skill 到 OpenClaw
cp -r mvp-kanban-complete-skill ~/.openclaw/workspace/skills/mvp-kanban

# 2. 进入目录
cd ~/.openclaw/workspace/skills/mvp-kanban

# 3. 构建 Docker 镜像
docker build -t mvp-kanban:latest docker/

# 4. 启动服务
docker-compose up -d

# 5. 访问 Web 界面
# http://localhost:9999

方式 3: 使用预构建镜像

# 拉取 Docker 镜像
docker pull your-dockerhub-username/mvp-kanban:latest

# 运行
docker run -d -p 9999:5000 -v kanban-data:/app/data mvp-kanban:latest

📁 包结构

mvp-kanban-complete-skill/
├── SKILL.md                    # 本文件
├── clawhub.yaml                # ClawHub 配置
├── mcp.json                    # MCP 配置
├── README.md                   # 快速开始
├── docker/                     # Docker 镜像部分
│   ├── Dockerfile
│   ├── docker-compose.yml
│   ├── .dockerignore
│   ├── app.py                  # Flask 应用
│   ├── database.py             # 数据库模块
│   ├── mcp_server.py           # MCP Server
│   ├── nlp_parser.py           # NLP 解析器
│   └── templates/              # Web 界面
├── src/                        # 完整源代码
│   ├── app.py
│   ├── database.py
│   ├── mcp_server.py
│   ├── mcp_client.py
│   ├── nlp_parser.py
│   └── templates/
└── docs/                       # 完整文档
    ├── API.md
    ├── WEB_UI_GUIDE.md
    ├── USAGE_METHODS.md
    ├── QUICK_TEST.md
    └── ...

🛠️ MCP 工具(21 个)

任务管理(7 个)

  1. list_projects - 列出所有项目
  2. get_project_details - 获取项目详情
  3. add_project - 添加项目
  4. update_project_status - 更新状态
  5. update_project_full - 完整更新
  6. move_project - 移动项目
  7. delete_project - 删除项目

泳道管理(5 个)

  1. list_lanes - 列出泳道
  2. add_lane - 添加泳道
  3. update_lane - 更新泳道
  4. delete_lane - 删除泳道
  5. get_lane_details - 泳道详情

批量操作(3 个)

  1. batch_create_projects - 批量创建
  2. batch_update_projects - 批量更新
  3. batch_delete_projects - 批量删除

AI 功能(4 个)

  1. analyze_board - AI 看板分析
  2. search_similar_projects - 向量搜索
  3. nlp_command - 自然语言命令
  4. llm_search - 向量搜索

辅助功能(2 个)

  1. get_board_metrics - 获取统计指标
  2. get_project_history - 变更历史

⚙️ 配置

MCP 配置

安装后自动配置 ~/.openclaw/config/mcp.json

{
  "mcpServers": {
    "kanban": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "mvp-kanban:latest",
        "python",
        "mcp_server.py"
      ],
      "cwd": "/root/.openclaw/workspace/skills/mvp-kanban/docker",
      "env": {
        "PYTHONPATH": "/app"
      }
    }
  }
}

Docker Compose

version: 0.0.1

services:
  kanban:
    image: mvp-kanban:latest
    container_name: mvp-kanban
    ports:
      - "9999:5000"
    volumes:
      - kanban-data:/app/data
    environment:
      - FLASK_ENV=production
    restart: unless-stopped

📖 使用方式

Web 界面

访问 http://localhost:9999

  • 点击"➕ 添加任务"创建任务
  • 双击任务卡片编辑
  • 拖拽任务移动
  • 悬停显示操作按钮

REST API

# 添加任务
curl -X POST http://localhost:9999/api/projects \
  -H "Content-Type: application/json" \
  -d '{"name":"任务","lane":"feature","priority":"high"}'

# 更新任务
curl -X PUT http://localhost:9999/api/projects/1 \
  -H "Content-Type: application/json" \
  -d '{"status":"in_progress"}'

# AI 分析
curl http://localhost:9999/api/llm/analyze

MCP 工具

from mcp import Client

client = Client("kanban")

# 添加任务
await client.call_tool("add_project", {
    "name": "安全加固",
    "lane": "security",
    "priority": "high"
})

# AI 分析
analysis = await client.call_tool("analyze_board")

自然语言

curl -X POST http://localhost:9999/api/llm/command \
  -H "Content-Type: application/json" \
  -d '{"command":"添加一个高优先级安全任务给张三"}'

📊 系统要求

  • Docker 20.10+
  • Python 3.12+
  • 内存:512MB
  • 存储:100MB

🏷️ 泳道

默认泳道:

  • 🚀 功能开发 (feature)
  • 🔒 安全加固 (security)
  • ⚙️ DevOps (devops)
  • 🐛 Bug 修复 (bugfix)

支持自定义泳道!

🎯 使用场景

场景 推荐方式
日常管理 Web 界面
开发集成 REST API
AI 自动化 MCP 工具
批量导入 REST API 批量接口
快速记录 自然语言命令

📝 示例

CI/CD 集成

# GitHub Actions 发现 bug 自动创建任务
import requests

requests.post("http://localhost:9999/api/projects", json={
    "name": f"修复:{bug_title}",
    "lane": "bugfix",
    "priority": "high",
    "assignee": "developer"
})

AI 助手

# AI 理解后自动调用 MCP
command = "添加一个高优先级的安全任务给张三"
await client.call_tool("nlp_command", {"command": command})

🔧 开发

本地开发模式

cd ~/.openclaw/workspace/skills/mvp-kanban/src

# 安装依赖
pip install -r requirements.txt

# 运行开发服务器
python app.py

构建 Docker 镜像

cd ~/.openclaw/workspace/skills/mvp-kanban/docker

# 构建
docker build -t mvp-kanban:latest .

# 测试
docker run -p 9999:5000 mvp-kanban:latest

🔄 版本

  • Skill 版本: v0.0.1
  • Docker 镜像: v0.0.1
  • API 版本: v0.0.1

👥 作者

DevSecOps Team

📄 许可证

MIT License

🐛 问题反馈

提交 Issue 到:https://github.com/your-username/mvp-kanban/issues

🎉 贡献

欢迎提交 Pull Request!

📖 更多文档


访问 http://localhost:9999 开始使用!

安全使用建议
This package appears to implement a full self‑hosted Kanban app and includes Docker files and a post_install hook that will build and launch a container and add an MCP entry to ~/.openclaw/config/mcp.json. Before installing: 1) Review the Dockerfile and all server source (app.py, mcp_server.py, database.py, nlp_parser.py) for any unexpected network calls, backdoors, or commands run during image build. 2) Check whether mcp.json creation/merge will overwrite any existing MCP configuration; back up ~/.openclaw/config first. 3) Run the service in an isolated environment (local VM or disposable host) rather than on production or a machine with sensitive data. 4) Prefer binding to localhost and verify docker-compose ports (some docs conflict between 0.0.0.0 and 127.0.0.1). 5) Verify the Dockerfile sets a non‑root user and resource limits; if not, modify before running. 6) If you rely on the 'no external network' claim, search the code for outbound network calls and check dependencies (sqlite-vec, mcp) for third‑party behavior. 7) Ask the author to clarify conflicting documentation (root vs non-root, port binding, whether mcp.json is merged or overwritten) and to add an explicit opt‑in step before auto-starting services.
功能分析
Type: OpenClaw Skill Name: li-mvp-kanban-complete-skill Version: 0.0.2 The bundle is a legitimate Kanban board application featuring task management, MCP tools, and a Flask-based web interface. The code is well-documented, uses standard libraries (Flask, SQLite), and includes proactive security configurations in its Docker setup, such as non-root user execution and resource limits. No malicious intent, data exfiltration, or unauthorized execution patterns were detected across the source code or the extensive documentation.
能力评估
Purpose & Capability
Name/description, code files (Flask app, DB, MCP server, NLP parser) and Docker artifacts are consistent with a self‑hosted Kanban application that exposes REST + MCP tools and vector search. The requested artifacts (Docker build/run, MCP integration) are reasonable for that purpose.
Instruction Scope
Runtime instructions and hooks will write/modify ~/.openclaw/config/mcp.json, build a Docker image and run docker-compose (post_install hook). That modifies user configuration and starts a networked service automatically. SKILL.md and clawhub.yaml indicate automatic MCP config creation (may overwrite existing file) — this is a scope expansion that should be explicit and reversible. No explicit user consent/merge step is enforced in the scripts.
Install Mechanism
There is no separate install spec, but the package includes a post_install hook that runs 'docker build' and 'docker-compose up -d' from the skill directory. Building and running a local Docker image from unreviewed source is moderately risky (it executes arbitrary code as part of the image build and container start) but is coherent with shipping a full application.
Credentials
The skill declares no required environment variables or credentials. The config and runtime do not request cloud keys or unrelated secrets. This is proportionate to the stated local-app purpose.
Persistence & Privilege
The skill auto-starts a service (via post_install and service entries) and writes an MCP configuration file under ~/.openclaw/config. While 'always: false' and autonomous invocation are normal, auto‑creating/modifying a global config file and auto‑launching a container are elevated behaviors that should be highlighted to the user. Also some docs claim it runs as root and others claim non-root — conflicting privileges.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install li-mvp-kanban-complete-skill
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /li-mvp-kanban-complete-skill 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v0.0.2
MVP Kanban Board Skill 0.0.2 - Added comprehensive SKILL.md documentation covering all features, setup instructions, usage guides, and tool references. - Documentation now details MCP integration, Docker usage, REST API, and natural language support. - Clarifies system requirements, default lanes, development workflow, and contribution guidelines. - Includes links to extended docs and feedback channels for easier onboarding. - No underlying code or functional changes were specified for this release.
元数据
Slug li-mvp-kanban-complete-skill
版本 0.0.2
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Mvp Kanban Complete Skill 是什么?

提供完整MVP看板任务管理,支持任务和泳道管理、批量操作、AI分析、向量搜索,含Docker镜像和21个MCP工具接口。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 121 次。

如何安装 Mvp Kanban Complete Skill?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install li-mvp-kanban-complete-skill」即可一键安装,无需额外配置。

Mvp Kanban Complete Skill 是免费的吗?

是的,Mvp Kanban Complete Skill 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Mvp Kanban Complete Skill 支持哪些平台?

Mvp Kanban Complete Skill 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Mvp Kanban Complete Skill?

由 Terry S Fisher(@43622283)开发并维护,当前版本 v0.0.2。

💬 留言讨论