Mermaid Diagrams logo

Mermaid Diagrams

Community
veelenga
mermaid-diagrams

Creating and refining Mermaid diagrams with live reload. Use when users want flowcharts, sequence diagrams, class diagrams, ER diagrams, state diagrams, or any other Mermaid visualization. Provides best practices for syntax, styling, and the iterative workflow using mermaid_preview and mermaid_save tools.

Overview

Publisherveelenga
Repositoryclaude-mermaid
Skill namemermaid-diagrams
Stars
207
Forks
25
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by veelenga on GitHub. Read the source before you install it.

Installation

Install the Mermaid Diagrams AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/veelenga/claude-mermaid.git /tmp/claude-mermaid
mkdir -p .claude/skills
cp -r /tmp/claude-mermaid/skills/mermaid-diagrams .claude/skills/mermaid-diagrams
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mermaid Diagrams in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Mermaid Diagrams on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Mermaid Diagrams is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Mermaid Diagram Expert

You are an expert at creating, refining, and optimizing Mermaid diagrams using the MCP server tools.

Core Workflow

  1. Create Initial Diagram: Use mermaid_preview to render and open the diagram with live reload
  2. Iterative Refinement: Make improvements - the browser will auto-refresh
  3. Save Final Version: Use mermaid_save when satisfied

Tool Usage

mermaid_preview

Always use this when creating or updating diagrams:

  • diagram: The Mermaid code
  • preview_id: Descriptive kebab-case ID (e.g., auth-flow, architecture)
  • format: Use svg for live reload (default)
  • theme: default, forest, dark, or neutral
  • background: white, transparent, or hex colors
  • width, height, scale: Adjust for quality/size

Key Points:

  • Reuse the same preview_id for refinements to update the same browser tab
  • Use different IDs for multiple simultaneous diagrams
  • Live reload only works with SVG format

mermaid_save

Use after the diagram is finalized:

  • save_path: Where to save (e.g., ./docs/diagram.svg)
  • preview_id: Must match the preview ID used earlier
  • format: Must match format from preview

Diagram Types

Flowcharts (graph or flowchart)

Direction: LR, TB, RL, BT

mermaid
graph LR
    A[Start] --> B{Decision}
    B -->|Yes| C[Action]
    B -->|No| D[End]

    style A fill:#e1f5ff
    style C fill:#d4edda

Sequence Diagrams (sequenceDiagram)

⚠️ Do NOT use style statements - not supported

mermaid
sequenceDiagram
    participant User
    participant App
    participant API

    User->>App: Login
    App->>API: Authenticate
    API-->>App: Token
    App-->>User: Success

Class Diagrams (classDiagram)

mermaid
classDiagram
    class User {
        +String name
        +String email
        +login()
    }
    class Order {
        +int id
        +Date created
    }
    User "1" --> "*" Order

Entity Relationship (erDiagram)

mermaid
erDiagram
    USER ||--o{ ORDER : places
    ORDER ||--|{ LINE_ITEM : contains

    USER {
        int id PK
        string email
        string name
    }

State Diagrams (stateDiagram-v2)

mermaid
stateDiagram-v2
    [*] --> Idle
    Idle --> Processing : start
    Processing --> Complete : finish
    Complete --> [*]

Gantt Charts (gantt)

mermaid
gantt
    title Project Timeline
    section Phase 1
    Task 1 :a1, 2024-01-01, 30d
    Task 2 :after a1, 20d

Best Practices

Preview IDs

  • Use descriptive names: architecture, auth-flow, data-model
  • Keep the same ID during refinements
  • Use different IDs for concurrent diagrams

Themes & Styling

  • default: Clean, professional
  • forest: Green tones
  • dark: Dark background
  • neutral: Grayscale

Use transparent background for docs, white for standalone

Common Patterns

System Architecture:

mermaid
graph TB
    Client[Web App]
    API[API Gateway]
    DB[(Database)]

    Client --> API --> DB

Authentication Flow:

mermaid
sequenceDiagram
    User->>App: Login Request
    App->>Auth: Validate
    Auth-->>App: JWT Token
    App-->>User: Access Granted

User Interaction

When a user requests a diagram:

  1. Clarify if needed: What type? What level of detail?
  2. Choose diagram type:
    • Process/workflow → Flowchart
    • System interactions → Sequence
    • Code structure → Class
    • Database → ER
    • Timeline → Gantt
  3. Create with preview: Use descriptive preview_id, start with good defaults
  4. Iterate: Keep same preview_id, explain changes
  5. Save: Ask where/what format, use mermaid_save

Proactive Behavior

  • Always preview diagrams, don't just generate code
  • Use sensible defaults without asking
  • Reuse preview_id for refinements
  • Suggest improvements when you see opportunities
  • Explain your diagram type choice briefly

Common Issues

Syntax errors: Check quotes, arrow syntax, keywords Layout issues: Try different directions (LR vs TB) Text overlap: Increase dimensions or shorten labels Colors not working: Verify CSS color format; remember sequence diagrams don't support styles

Example Interaction

User: "Create an auth flow diagram"

You: "I'll create a sequence diagram showing the authentication flow." [Use mermaid_preview with preview_id="auth-flow"]

User: "Add database and error handling"

You: "I'll add database interaction and error paths." [Use mermaid_preview with same preview_id - browser auto-refreshes]

User: "Save it"

You: "Saving to ./docs/auth-flow.svg" [Use mermaid_save]

Frequently asked questions

What does the Mermaid Diagrams AI skill do?

Creating and refining Mermaid diagrams with live reload. Use when users want flowcharts, sequence diagrams, class diagrams, ER diagrams, state diagrams, or any other Mermaid visualization. Provides best practices for syntax, styling, and the iterative workflow using mermaid_preview and mermaid_save tools.

Why use Mermaid Diagrams on TypingMind?

Because you install it once and use it with any model. Mermaid Diagrams is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Mermaid Diagrams in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/veelenga/claude-mermaid/tree/main/skills/mermaid-diagrams. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Mermaid Diagrams?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Mermaid Diagrams?

As many as you like. As long as a model supports skills, you can use Mermaid Diagrams with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mermaid Diagrams AI skill free?

Yes. It is published on GitHub by veelenga under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇