← Back to Skills Marketplace
43622283

Mvp Kanban Skill

by Terry S Fisher · GitHub ↗ · v0.0.2 · MIT-0
cross-platform ⚠ suspicious
131
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install li-mvp-kanban-skill
Description
提供任务与泳道管理、批量操作、AI分析和语义搜索的看板系统,支持Web界面、REST API及MCP工具调用。
README (SKILL.md)

MVP Kanban Board Skill - v3.0.0

📖 描述

MVP 看板系统技能,支持任务管理、泳道管理、批量操作和 AI 分析。 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

  • 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

🚀 快速开始

方式 1: 从 ClawHub 安装

clawhub install mvp-kanban

方式 2: Docker 部署

docker pull your-dockerhub-username/mvp-kanban:latest

docker run -d \
  -p 9999:5000 \
  -v kanban-data:/app/data \
  --name mvp-kanban \
  your-dockerhub-username/mvp-kanban:latest

方式 3: 本地开发

git clone https://github.com/your-username/mvp-kanban.git
cd mvp-kanban/docker
pip install -r requirements.txt
python app.py

📋 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"}'

🛠️ 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

创建 ~/.openclaw/config/mcp.json

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

Docker Compose

version: 0.0.1

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

📊 系统要求

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

📖 文档

🏷️ 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})

🔄 版本

  • Docker 镜像: v3.0.0
  • Skill 版本: v3.0.0
  • API 版本: v3.0.0

👥 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!


访问 http://localhost:9999 开始使用!

Usage Guidance
Before installing, verify the image and source: ask the author for the canonical GitHub repo and Docker image (not placeholder 'your-dockerhub-username'), review the Dockerfile and source code, and prefer running the container in an isolated environment (VM or sandbox). Do not blindly copy mcp.json into your config—back up existing ~/.openclaw/config first. Scan the image with a container scanner (e.g., trivy) and inspect its contents (docker history, docker run with read-only flags) before exposing it to your host. If the publisher cannot provide a verifiable repository and signed releases, treat the image as untrusted.
Capability Analysis
Type: OpenClaw Skill Name: li-mvp-kanban-skill Version: 0.0.2 The skill bundle describes a standard Kanban board system with a Web UI, REST API, and 21 MCP tools for task management and AI-driven analysis. The provided files (SKILL.md, clawhub.yaml, mcp.json) consist of documentation and configuration templates that use placeholders (e.g., 'your-dockerhub-username') and standard Docker-based deployment patterns. No malicious code, data exfiltration logic, or harmful prompt injection attempts were found; the requested permissions (network and Docker) are aligned with the stated purpose of hosting a project management tool.
Capability Assessment
Purpose & Capability
The skill claims a kanban system with web UI, REST API and MCP tools—everything in SKILL.md is consistent with that purpose. However, the skill metadata lists no required binaries or env vars while the instructions clearly expect Docker (and Python for the service), so the declared requirements are incomplete/inconsistent.
Instruction Scope
Runtime instructions direct users to pull and run a Docker image (your-dockerhub-username/mvp-kanban:latest) and to write MCP config into ~/.openclaw/config/mcp.json with a cwd of /root/.openclaw/workspace/skills/mvp-kanban. These actions will execute code from an external image and modify user config; the instructions do not provide a verifiable upstream repo or image provenance and use placeholder usernames, which increases risk.
Install Mechanism
There is no formal install spec in the registry, but SKILL.md and clawhub.yaml rely on a Docker image hosted on Docker Hub under a placeholder username. Pulling and running an unverified container is a high-risk install mechanism because it can execute arbitrary code on the host. No signed releases, checksums, or known official image are provided.
Credentials
The skill does not request secret credentials or environment variables beyond minor settings (FLASK_ENV, PYTHONPATH in examples). It does ask you to create MCP entries that run docker and set PYTHONPATH inside the container; there are no apparent demands for unrelated credentials.
Persistence & Privilege
The skill is not always-enabled and is user-invocable. However, instructions tell the user to copy mcp.json into ~/.openclaw/config/mcp.json and to place files under /root/.openclaw/workspace/...—this modifies local OpenClaw configuration and workspace. That behavior is expected for MCP-enabled skills but should be done cautiously (don't overwrite existing configs blindly).
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install li-mvp-kanban-skill
  3. After installation, invoke the skill by name or use /li-mvp-kanban-skill
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.0.2
- Major update: MVP Kanban Board Skill v3.0.0 is released with comprehensive task management and AI features. - Added Web UI, REST API, and MCP tool support for managing tasks and lanes. - Introduced batch operations for creating, updating, and deleting tasks. - Enhanced AI capabilities, including bottleneck analysis, risk warnings, semantic search, and natural language commands. - Full documentation and quick start guides provided for multiple usage scenarios and deployment methods. - Supports customizable swimlanes, data persistence with SQLite, and multiple integration options.
Metadata
Slug li-mvp-kanban-skill
Version 0.0.2
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Mvp Kanban Skill?

提供任务与泳道管理、批量操作、AI分析和语义搜索的看板系统,支持Web界面、REST API及MCP工具调用。 It is an AI Agent Skill for Claude Code / OpenClaw, with 131 downloads so far.

How do I install Mvp Kanban Skill?

Run "/install li-mvp-kanban-skill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Mvp Kanban Skill free?

Yes, Mvp Kanban Skill is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Mvp Kanban Skill support?

Mvp Kanban Skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Mvp Kanban Skill?

It is built and maintained by Terry S Fisher (@43622283); the current version is v0.0.2.

💬 Comments