Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
生成和编辑各种类型的图表(drawio、mermaid、excalidraw)。支持流程图、时序图、类图、ER图、思维导图、架构图、网络拓扑图等常见图表类型。能够根据自然语言描述创建新图表,也能读取并修改已有的 drawio/mermaid/excalidraw 文件。使用独立的 MCP server (mcp-diagram-generator) 生成图表文件,减少 token 消耗并保证输出一致性。支持自动配置管理,默认输出路径为项目目录下的 diagrams/{format}/,支持自定义路径和自动创建目录。
生成和编辑各种类型的图表(drawio、mermaid、excalidraw)。支持流程图、时序图、类图、ER图、思维导图、架构图、网络拓扑图等常见图表类型。能够根据自然语言描述创建新图表,也能读取并修改已有的 drawio/mermaid/excalidraw 文件。使用独立的 MCP server (mcp-diagram-generator) 生成图表文件,减少 token 消耗并保证输出一致性。支持自动配置管理,默认输出路径为项目目录下的 diagrams/{format}/,支持自定义路径和自动创建目录。
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Generate and edit diagrams in multiple formats (drawio, mermaid, excalidraw) by creating structured JSON descriptions and delegating file generation to the mcp-diagram-generator MCP server. Contact Information If you encounter any issues, please contact AlkaidY at tccio2023@gmail.com.
IMPORTANT: This skill requires the mcp-diagram-generator MCP server to be installed and configured.
Before using this skill, verify the MCP server is available by checking if you can access these tools: mcp__mcp-diagram-generator__get_config mcp__mcp-diagram-generator__generate_diagram mcp__mcp-diagram-generator__init_config If these tools are NOT available, you need to configure the MCP server first (see below).
Option 1: Using npx (Recommended - Auto-downloads the package) Add the following to your Claude Code configuration file: Global config (~/.claude.json) for all projects, or Project config (.claude.json) for specific project { "mcpServers": { "mcp-diagram-generator": { "command": "npx", "args": ["-y", "mcp-diagram-generator"] } } } After adding this configuration: Restart Claude Code The MCP server will auto-download via npx on first use No manual installation needed Option 2: Local Development (For developers) If you're developing the MCP server locally: { "mcpServers": { "mcp-diagram-generator": { "command": "node", "args": ["/absolute/path/to/mcp-diagram-generator/dist/index.js"] } } }
After configuration, verify it works: Check configuration: Call get_config() tool If successful, you'll see current paths and initialization status If the tool doesn't exist, check your configuration file syntax
Issue: "Tool not found" error Solution: MCP server not configured. Follow installation steps above. Issue: Configuration looks correct but tools still not available Solution: Restart Claude Code to reload MCP server configuration
On first use, the MCP server will automatically: Create default configuration file (.diagram-config.json) Create default output directories if they don't exist Use sensible defaults: diagrams/{format}/ You can customize paths at any time using the init_config tool.
Simple example - just provide diagram spec, let the server handle the rest: User: "创建一个网络拓扑图" Skill will: Generate JSON spec Call generate_diagram with only diagram_spec parameter Server auto-creates directories and saves to diagrams/{format}/{title}-{date}.{ext}
Extract from user's natural language: Diagram type: flowchart, sequence diagram, class diagram, ER diagram, mindmap, architecture diagram, network topology Content: nodes, relationships, nested structure (for network topology) Style/theme: if mentioned (e.g., "clean style", "detailed") Output preferences: specific filename? custom path?
Use format-selection-guide.md to decide: FormatBest FordrawioComplex diagrams, network topology with nested containers, fine-grained styling, manual editingmermaidQuick generation, code-friendly, version control, documentationexcalidrawHand-drawn style, creative/diagrammatic flexibility, informal sketches
Create a JSON description following the JSON Schema. Key structure: { "format": "drawio", "title": "diagram name", "elements": [ { "id": "unique-id", "type": "container|node|edge", "name": "display name", "level": "environment|datacenter|zone|device", // for network topology "style": {...}, "geometry": {...}, "children": [...] // for nested containers } ] } Important: Use unique IDs for all elements. For nested structures, maintain parent-child relationships.
Option A: Use defaults (recommended) { "diagram_spec": <the JSON object created above> // output_path is optional - server will use configured default // filename is optional - server will auto-generate based on title and date } The MCP server will: Validate the JSON schema Generate the appropriate XML/JSON/markdown Auto-create output directories if needed Save to configured default path (e.g., diagrams/drawio/network-topology-2025-02-03.drawio) Option B: Specify custom path { "diagram_spec": <the JSON object>, "output_path": "custom/path/to/diagram.drawio", "filename": "my-custom-name" // optional, overrides auto-generated filename } Option C: Just provide filename, use default directory { "diagram_spec": <the JSON object>, "filename": "my-diagram.drawio" // Saves to diagrams/{format}/my-diagram.drawio }
Read the existing file to understand structure Parse the diagram (use MCP tool if available, or read raw file) Modify the JSON description based on user's change request Generate new diagram (overwrite or create new file)
Initialize with defaults: Call: init_config() Result: Creates .diagram-config.json with default paths Initialize with custom paths: Call: init_config({ paths: { drawio: "output/diagrams/drawio", mermaid: "output/diagrams/mermaid", excalidraw: "output/diagrams/excalidraw" } })
Call: get_config() Returns: Current paths and initialization status
Call: set_output_path({ format: "drawio", path: "custom/drawio-path" })
Simple process flows, decision trees Use mermaid for quick output Use drawio for complex layouts with multiple branches
Show interactions over time between components mermaid recommended (native support) Use drawio if custom styling needed
Show classes, methods, relationships mermaid recommended (compact, standard UML) drawio for detailed diagrams with many classes
Database schema, entity relationships mermaid recommended drawio for complex schemas with many relationships
Hierarchical ideas, brainstorming mermaid recommended (native support) excalidraw for creative/hand-drawn style
System architecture, component relationships drawio recommended for complex systems mermaid for high-level overviews
Network environments, datacenters, zones, devices Must use drawio (4-layer nesting: environment → datacenter → zone → device) See network-topology-examples.md for patterns
Network topology diagrams require a 4-level hierarchical structure: Environment (level="environment") └── Datacenter (level="datacenter") └── Zone (level="zone") └── Device (type="node") Style conventions: Environment: fillColor: #e1d5e7, strokeColor: #9673a6 (purple) Datacenter: fillColor: #d5e8d4, strokeColor: #82b366 (green) Zone: fillColor: #fff2cc, strokeColor: #d6b656 (yellow) Device: Based on device type (router, switch, firewall, etc.) Device types and styles: Router: strokeColor: #607D8B (blue-gray) Switch: strokeColor: #4CAF50 (green) Firewall: strokeColor: #F44336 (red) PC/Server: strokeColor: #607D8B (blue-gray)
User: "画一个用户登录流程图,包含登录验证、重定向、错误处理" Generate JSON: { "format": "mermaid", "title": "用户登录流程", "elements": [ {"type": "node", "id": "start", "name": "开始", "geometry": {"x": 0, "y": 0}}, {"type": "node", "id": "login", "name": "输入用户名密码", "geometry": {"x": 0, "y": 100}}, {"type": "node", "id": "validate", "name": "验证", "geometry": {"x": 0, "y": 200}}, {"type": "node", "id": "success", "name": "登录成功", "geometry": {"x": -100, "y": 300}}, {"type": "node", "id": "error", "name": "显示错误", "geometry": {"x": 100, "y": 300}}, {"type": "edge", "source": "start", "target": "login"}, {"type": "edge", "source": "login", "target": "validate"}, {"type": "edge", "source": "validate", "target": "success", "label": "成功"}, {"type": "edge", "source": "validate", "target": "error", "label": "失败"} ] } Call MCP: generate_diagram({ diagram_spec: <above JSON>, format: "mermaid" // No output_path needed - auto-saves to diagrams/mermaid/ })
User: "创建一个网络拓扑图,包含省中心机房(上联区、汇聚区、终端区),连接到生产网" Generate JSON with nested containers (see json-schema-guide.md for details). Call MCP: generate_diagram({ diagram_spec: <network topology JSON>, filename: "省中心网络拓扑" // Optional, for custom filename })
format-selection-guide.md: When to use drawio vs mermaid vs excalidraw json-schema-guide.md: Complete JSON schema with examples for all diagram types network-topology-examples.md: Example JSON for network topology patterns
No templates needed - MCP server handles all generation
Not used - all generation delegated to MCP server
If mcp-diagram-generator is not available, you need to install it. Option 1: Using npx (Recommended) Add to your Claude Code/OpenCode settings: { "mcpServers": { "diagram-generator": { "command": "npx", "args": ["-y", "mcp-diagram-generator"] } } } Option 2: Local Development Install dependencies: cd mcp-diagram-generator && npm install Build: npm run build Configure with local path: { "mcpServers": { "diagram-generator": { "command": "node", "args": ["/absolute/path/to/mcp-diagram-generator/dist/index.js"] } } }
If MCP server returns validation error: Check json-schema-guide.md Verify all required fields are present Ensure all IDs are unique Check parent-child relationships
Old behavior: Error if directory doesn't exist New behavior: Directory is created automatically ✅ If you still see directory errors: Check write permissions for the project directory Verify configuration with get_config() Reinitialize with init_config()
The server automatically uses the correct extension based on format: drawio → .drawio mermaid → .md excalidraw → .excalidraw You don't need to specify extension in filename parameter.
Verify level field matches hierarchy (environment/datacenter/zone) Check parent IDs are correct in child elements Ensure geometry coordinates are relative to parent container
Let the server manage output paths for consistency: { "diagram_spec": <spec> // Don't specify output_path unless necessary }
Titles are used for auto-generated filenames: { "title": "生产环境网络拓扑-亦庄与西五环", // Generates: 生产环境网络拓扑-亦庄与西五环-2025-02-03.drawio }
Instead of specifying output_path every time, configure once: First time: init_config({ paths: { drawio: "custom/path" } }) After that: Just use generate_diagram() without output_path
get_config() // Shows all paths and status
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Largest current source with strong distribution and engagement signals.