Diagramming logo

Diagramming

Community
ynulihao
diagramming

Create technical diagrams using Mermaid syntax for architecture, sequences, ERDs, flowcharts, and state machines. Use for visualizing system design, data flows, and processes. Triggers: diagram, mermaid, architecture diagram, sequence diagram, flowchart, ERD, entity relationship, state diagram, C4 model, component diagram, visualize, draw.

Overview

Publisherynulihao
RepositoryAgentSkillOS
Skill namediagramming
Stars
612
Forks
76
Bundled files
Instructions only
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 ynulihao on GitHub. Read the source before you install it.

Installation

Install the Diagramming 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/ynulihao/AgentSkillOS.git /tmp/AgentSkillOS
mkdir -p .claude/skills
cp -r /tmp/AgentSkillOS/data/skill_seeds/diagramming .claude/skills/diagramming
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Diagramming 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 Diagramming 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 Diagramming 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.

Diagramming

Overview

Create clear, maintainable technical diagrams using Mermaid syntax. This skill covers architecture diagrams, sequence diagrams, entity-relationship diagrams, flowcharts, and state diagrams for documenting software systems.

Instructions

1. Choose the Right Diagram Type

Diagram TypeUse When
Architecture/C4Showing system structure and components
SequenceShowing interactions over time
ERDShowing data models and relationships
FlowchartShowing decision logic and processes
StateShowing state transitions

2. General Mermaid Principles

  • Keep diagrams focused on one concept
  • Use consistent naming conventions
  • Add descriptive labels to relationships
  • Limit complexity (split large diagrams)
  • Use comments for documentation

Best Practices

  • Simplicity: One diagram, one concept
  • Consistency: Same naming across related diagrams
  • Readability: Left-to-right or top-to-bottom flow
  • Labels: Always label relationships and transitions
  • Context: Include a title and brief description

Examples

Architecture Diagrams (C4 Model)

Context Diagram (Level 1)
mermaid
C4Context
    title System Context Diagram for E-Commerce Platform

    Person(customer, "Customer", "A user who purchases products")
    Person(admin, "Admin", "Manages products and orders")

    System(ecommerce, "E-Commerce Platform", "Allows customers to browse and purchase products")

    System_Ext(payment, "Payment Gateway", "Handles payment processing")
    System_Ext(shipping, "Shipping Provider", "Handles order fulfillment")
    System_Ext(email, "Email Service", "Sends notifications")

    Rel(customer, ecommerce, "Browses, purchases")
    Rel(admin, ecommerce, "Manages")
    Rel(ecommerce, payment, "Processes payments")
    Rel(ecommerce, shipping, "Creates shipments")
    Rel(ecommerce, email, "Sends emails")
Container Diagram (Level 2)
mermaid
C4Container
    title Container Diagram for E-Commerce Platform

    Person(customer, "Customer")

    Container_Boundary(ecommerce, "E-Commerce Platform") {
        Container(web, "Web Application", "React", "Customer-facing UI")
        Container(api, "API Gateway", "Node.js", "REST API")
        Container(cart, "Cart Service", "Node.js", "Shopping cart management")
        Container(catalog, "Catalog Service", "Python", "Product catalog")
        Container(order, "Order Service", "Java", "Order processing")
        ContainerDb(db, "Database", "PostgreSQL", "Stores all data")
        ContainerQueue(queue, "Message Queue", "RabbitMQ", "Async messaging")
    }

    Rel(customer, web, "Uses", "HTTPS")
    Rel(web, api, "Calls", "JSON/HTTPS")
    Rel(api, cart, "Routes to")
    Rel(api, catalog, "Routes to")
    Rel(api, order, "Routes to")
    Rel(cart, db, "Reads/writes")
    Rel(catalog, db, "Reads")
    Rel(order, db, "Reads/writes")
    Rel(order, queue, "Publishes events")
Component Diagram (Level 3)
mermaid
flowchart TB
    subgraph "Order Service"
        controller[Order Controller]
        service[Order Service]
        repo[Order Repository]
        validator[Order Validator]
        publisher[Event Publisher]
    end

    subgraph "External"
        db[(PostgreSQL)]
        queue[RabbitMQ]
    end

    controller --> service
    service --> validator
    service --> repo
    service --> publisher
    repo --> db
    publisher --> queue

Sequence Diagrams

Basic Request Flow
mermaid
sequenceDiagram
    autonumber
    participant C as Client
    participant G as API Gateway
    participant A as Auth Service
    participant S as Service
    participant D as Database

    C->>G: POST /api/resource
    G->>A: Validate token
    A-->>G: Token valid

    G->>S: Forward request
    S->>D: Query data
    D-->>S: Return results

    S-->>G: Response (200 OK)
    G-->>C: Response with data
Error Handling Flow
mermaid
sequenceDiagram
    participant C as Client
    participant S as Service
    participant D as Database

    C->>S: POST /api/users
    S->>S: Validate input

    alt Validation fails
        S-->>C: 400 Bad Request
    else Validation passes
        S->>D: INSERT user
        alt Database error
            D-->>S: Constraint violation
            S-->>C: 409 Conflict
        else Success
            D-->>S: User created
            S-->>C: 201 Created
        end
    end
Async Processing
mermaid
sequenceDiagram
    participant C as Client
    participant API as API
    participant Q as Queue
    participant W as Worker
    participant N as Notification

    C->>API: Submit job
    API->>Q: Enqueue job
    API-->>C: 202 Accepted (job ID)

    Note over Q,W: Async processing

    Q->>W: Dequeue job
    W->>W: Process job
    W->>N: Send notification
    N-->>C: Job complete notification

Entity-Relationship Diagrams

Basic ERD
mermaid
erDiagram
    USER ||--o{ ORDER : places
    USER {
        uuid id PK
        string email UK
        string name
        timestamp created_at
    }

    ORDER ||--|{ ORDER_ITEM : contains
    ORDER {
        uuid id PK
        uuid user_id FK
        decimal total
        string status
        timestamp created_at
    }

    ORDER_ITEM }|--|| PRODUCT : references
    ORDER_ITEM {
        uuid id PK
        uuid order_id FK
        uuid product_id FK
        int quantity
        decimal price
    }

    PRODUCT ||--o{ PRODUCT_CATEGORY : "belongs to"
    PRODUCT {
        uuid id PK
        string name
        text description
        decimal price
        int stock
    }

    CATEGORY ||--o{ PRODUCT_CATEGORY : contains
    CATEGORY {
        uuid id PK
        string name
        uuid parent_id FK
    }

    PRODUCT_CATEGORY {
        uuid product_id PK,FK
        uuid category_id PK,FK
    }
ERD with Relationships Explained
mermaid
erDiagram
    CUSTOMER ||--o{ ORDER : "places (1:N)"
    ORDER ||--|{ LINE_ITEM : "contains (1:N, required)"
    PRODUCT ||--o{ LINE_ITEM : "appears in (1:N)"
    CUSTOMER }|--|| ADDRESS : "has billing (N:1, required)"
    CUSTOMER }o--o{ ADDRESS : "has shipping (N:N)"

Relationship notation:

  • || exactly one
  • o| zero or one
  • }| one or more
  • }o zero or more

Flowcharts

Decision Logic
mermaid
flowchart TD
    A[Start: User Login] --> B{Valid credentials?}
    B -->|Yes| C{2FA enabled?}
    B -->|No| D[Show error message]
    D --> A

    C -->|Yes| E[Send 2FA code]
    E --> F{Code valid?}
    F -->|Yes| G[Create session]
    F -->|No| H{Attempts < 3?}
    H -->|Yes| E
    H -->|No| I[Lock account]

    C -->|No| G
    G --> J[Redirect to dashboard]
    J --> K[End]
    I --> K
Process Flow
mermaid
flowchart LR
    subgraph "CI Pipeline"
        A[Push Code] --> B[Run Tests]
        B --> C{Tests Pass?}
        C -->|Yes| D[Build Image]
        C -->|No| E[Notify Developer]
        D --> F[Push to Registry]
    end

    subgraph "CD Pipeline"
        F --> G[Deploy to Staging]
        G --> H[Run E2E Tests]
        H --> I{Tests Pass?}
        I -->|Yes| J[Deploy to Production]
        I -->|No| K[Rollback]
    end

State Diagrams

Order State Machine
mermaid
stateDiagram-v2
    [*] --> Draft: Create order

    Draft --> Pending: Submit
    Draft --> Cancelled: Cancel

    Pending --> Confirmed: Payment received
    Pending --> Cancelled: Payment failed
    Pending --> Cancelled: Timeout (24h)

    Confirmed --> Processing: Begin fulfillment
    Confirmed --> Cancelled: Customer cancel

    Processing --> Shipped: Ship order
    Processing --> Cancelled: Out of stock

    Shipped --> Delivered: Delivery confirmed
    Shipped --> Returned: Return initiated

    Delivered --> Returned: Return requested
    Delivered --> [*]: Complete

    Returned --> Refunded: Process refund
    Refunded --> [*]: Complete

    Cancelled --> [*]: Complete
Connection State Machine
mermaid
stateDiagram-v2
    [*] --> Disconnected

    Disconnected --> Connecting: connect()
    Connecting --> Connected: success
    Connecting --> Disconnected: failure

    Connected --> Disconnected: disconnect()
    Connected --> Reconnecting: connection lost

    Reconnecting --> Connected: success
    Reconnecting --> Disconnected: max retries

    note right of Reconnecting
        Exponential backoff
        Max 5 retries
    end note

Class Diagrams

mermaid
classDiagram
    class Repository~T~ {
        <<interface>>
        +findById(id: string) T
        +findAll() List~T~
        +save(entity: T) T
        +delete(id: string) void
    }

    class UserRepository {
        -db: Database
        +findById(id: string) User
        +findAll() List~User~
        +save(entity: User) User
        +delete(id: string) void
        +findByEmail(email: string) User
    }

    class User {
        +id: string
        +email: string
        +name: string
        +createdAt: Date
        +validate() boolean
    }

    Repository~T~ <|.. UserRepository
    UserRepository --> User

Frequently asked questions

What does the Diagramming AI skill do?

Create technical diagrams using Mermaid syntax for architecture, sequences, ERDs, flowcharts, and state machines. Use for visualizing system design, data flows, and processes. Triggers: diagram, mermaid, architecture diagram, sequence diagram, flowchart, ERD, entity relationship, state diagram, C4 model, component diagram, visualize, draw.

Why use Diagramming on TypingMind?

Because you install it once and use it with any model. Diagramming 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 Diagramming in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ynulihao/AgentSkillOS/tree/main/data/skill_seeds/diagramming. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Diagramming?

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 Diagramming?

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

Is the Diagramming AI skill free?

It is published on GitHub by ynulihao. Check the repository for licensing terms. 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 👇