Mermaid Diagram Specialist

Overview

Purpose: Expert in creating comprehensive Mermaid diagrams for documentation, architecture visualization, and process mapping

Category: Tech Primary Users: tech-writer, architecture-validator, product-technical, tech-lead

When to Use This Skill

• Creating architecture documentation
• Visualizing workflows and processes
• Documenting data models (ERDs)
• Explaining sequence flows
• Creating state machines
• Documenting component relationships
• Creating decision trees
• Visualizing user journeys

Prerequisites

Required:

• Understanding of the system/process to document
• Access to technical specifications
• Knowledge of diagram type needed

Optional:

• Design system colors for consistency
• Existing documentation to reference

Input

What the skill needs:

• Process/system description
• Entities and relationships (for ERDs)
• Component interactions (for sequence diagrams)
• Architecture layers (for C4 diagrams)
• States and transitions (for state diagrams)

Workflow

Step 1: Diagram Type Selection

Objective: Choose appropriate diagram type for requirements

Available Diagram Types:

1. Flowchart: Decision flows, algorithms, processes
2. Sequence Diagram: API interactions, message flows
3. ERD: Database schemas, entity relationships
4. Class Diagram: Object-oriented design
5. State Diagram: State machines, lifecycle
6. Gantt Chart: Project timelines, schedules
7. C4 Diagram: Architecture at different levels
8. Pie/Bar Charts: Data visualization
9. Git Graph: Version control flows
10. User Journey: User experience flows

Decision Matrix:

• Process with decisions → Flowchart
• API/system interactions → Sequence Diagram
• Database structure → ERD
• System architecture → C4 Diagram
• Object relationships → Class Diagram
• State transitions → State Diagram
• Project timeline → Gantt Chart

Validation:

• Diagram type matches content
• Complexity appropriate
• Audience considered
• Purpose clear

Output: Selected diagram type

Step 2: Flowchart Creation

Objective: Create process and decision flow diagrams

Syntax:

flowchart TD
    Start([Start]) --> Input[/User Input/]
    Input --> Validate{Valid?}
    Validate -->|Yes| Process[Process Data]
    Validate -->|No| Error[Show Error]
    Error --> Input
    Process --> Save[(Save to DB)]
    Save --> Success[/Success Response/]
    Success --> End([End])

Node Shapes:

• [Rectangle] - Process step
• ([Rounded]) - Start/End
• {Diamond} - Decision
• [/Parallelogram/] - Input/Output
• [(Database)] - Data storage
• ((Circle)) - Connector

Direction Options:

• TD - Top to Down
• LR - Left to Right
• BT - Bottom to Top
• RL - Right to Left

Example - Booking Flow:

flowchart TD
    Start([User Initiates Booking]) --> CheckDates[Check Date Availability]
    CheckDates --> Available{Dates Available?}
    Available -->|No| ShowError[/Show Unavailable Message/]
    ShowError --> End([End])
    Available -->|Yes| CreateBooking[Create Pending Booking]
    CreateBooking --> Payment[Process Payment]
    Payment --> PaymentSuccess{Payment Success?}
    PaymentSuccess -->|No| CancelBooking[Cancel Booking]
    CancelBooking --> ShowError
    PaymentSuccess -->|Yes| ConfirmBooking[Confirm Booking]
    ConfirmBooking --> SendEmail[/Send Confirmation Email/]
    SendEmail --> SaveDB[(Save to Database)]
    SaveDB --> Success[/Show Success/]
    Success --> End

Validation:

• All paths covered
• Decision points clear
• Start and end defined
• Flow direction logical

Output: Process flowchart

Step 3: Sequence Diagram Creation

Objective: Document API interactions and message flows

Syntax:

sequenceDiagram
    actor User
    participant Frontend
    participant API
    participant DB
    participant Payment

    User->>Frontend: Click "Book"
    Frontend->>API: POST /api/bookings
    API->>DB: Check availability
    DB-->>API: Available
    API->>Payment: Process payment
    Payment-->>API: Payment successful
    API->>DB: Create booking
    DB-->>API: Booking created
    API-->>Frontend: 201 Created
    Frontend-->>User: Show confirmation

Participant Types:

• actor - Human user
• participant - System/Service
• database - Database

Arrow Types:

• -> - Solid line (synchronous)
• --> - Dotted line (response)
• ->> - Solid arrow (async message)
• -->> - Dotted arrow (async response)

Example - Authentication Flow:

sequenceDiagram
    actor User
    participant Frontend
    participant API
    participant Clerk
    participant DB

    User->>Frontend: Enter credentials
    Frontend->>Clerk: Login request
    Clerk->>Clerk: Validate credentials
    alt Credentials valid
        Clerk-->>Frontend: JWT token
        Frontend->>API: Request with token
        API->>Clerk: Verify token
        Clerk-->>API: Token valid
        API->>DB: Fetch user data
        DB-->>API: User data
        API-->>Frontend: User session
        Frontend-->>User: Logged in
    else Credentials invalid
        Clerk-->>Frontend: Auth error
        Frontend-->>User: Show error
    end

Validation:

• All participants identified
• Message flow logical
• Return messages shown
• Alt/loop blocks used correctly

Output: Sequence diagram

Step 4: ERD Creation

Objective: Document database schema and relationships

Syntax:

erDiagram
    USER ||--o{ BOOKING : creates
    ACCOMMODATION ||--o{ BOOKING : "booked for"
    USER {
        uuid id PK
        string email UK
        string name
        timestamp created_at
    }
    BOOKING {
        uuid id PK
        uuid user_id FK
        uuid accommodation_id FK
        date check_in
        date check_out
        enum status
    }
    ACCOMMODATION {
        uuid id PK
        string name
        text description
        decimal price_per_night
    }

Relationship Types:

• ||--|| - One to one
• ||--o{ - One to many
• }o--o{ - Many to many
• ||--o| - One to zero or one

Cardinality Symbols:

• || - Exactly one
• o| - Zero or one
• }o - Zero or more
• }| - One or more

Example - Full Hospeda ERD:

erDiagram
    USER ||--o{ BOOKING : creates
    USER ||--o{ REVIEW : writes
    USER ||--o{ ACCOMMODATION : owns
    ACCOMMODATION ||--o{ BOOKING : "has bookings"
    ACCOMMODATION ||--o{ REVIEW : "has reviews"
    ACCOMMODATION }o--o{ AMENITY : includes
    BOOKING ||--|| PAYMENT : "has payment"

    USER {
        uuid id PK
        string clerk_id UK
        string email UK
        string name
        enum role
        timestamp created_at
    }

    ACCOMMODATION {
        uuid id PK
        uuid owner_id FK
        string name
        text description
        decimal price_per_night
        int max_guests
        enum status
    }

    BOOKING {
        uuid id PK
        uuid user_id FK
        uuid accommodation_id FK
        date check_in
        date check_out
        int guests
        enum status
        decimal total_price
    }

    REVIEW {
        uuid id PK
        uuid user_id FK
        uuid accommodation_id FK
        int rating
        text comment
        timestamp created_at
    }

    PAYMENT {
        uuid id PK
        uuid booking_id FK
        string mercadopago_id UK
        decimal amount
        enum status
        timestamp processed_at
    }

    AMENITY {
        uuid id PK
        string name
        string icon
    }

Validation:

• All entities defined
• Relationships accurate
• Cardinality correct
• Primary/Foreign keys marked

Output: ERD diagram

Step 5: C4 Architecture Diagrams

Objective: Document system architecture at different levels

Context Level (System in environment):

C4Context
    title System Context - Hospeda Platform

    Person(guest, "Guest", "Tourist looking for accommodation")
    Person(owner, "Owner", "Accommodation owner")
    System(hospeda, "Hospeda Platform", "Tourism booking platform")

    System_Ext(clerk, "Clerk", "Authentication provider")
    System_Ext(mercadopago, "Mercado Pago", "Payment processor")
    System_Ext(email, "Email Service", "Transactional emails")

    Rel(guest, hospeda, "Searches and books", "HTTPS")
    Rel(owner, hospeda, "Manages listings", "HTTPS")
    Rel(hospeda, clerk, "Authenticates users", "API")
    Rel(hospeda, mercadopago, "Processes payments", "API")
    Rel(hospeda, email, "Sends notifications", "SMTP")

Container Level (Applications and data stores):

C4Container
    title Container - Hospeda Platform

    Person(user, "User")

    Container
how to use mermaid-diagram-specialist
CursorClaude CodeClineCodexWindsurfGooseGitHub CopilotVS CodeGemini CLIKiloOpencodeKimi CLIRoo ClineAiderContinueZedBolt.newLovablev0Replit AgentSweepSmol DeveloperDevinCavemanAmpAntigravity
How to use mermaid-diagram-specialist on Cursor
AI-first code editor with Composer
1
Prerequisites
Before installing skills in Cursor, ensure your development environment meets these requirements:
›Cursor installed and configured on your development machine
›Node.js version 16.0+ with npm package manager (verify with node --version)
›Active project directory or workspace where you want to add mermaid-diagram-specialist
2
Execute installation command
Execute the skills CLI command in your project's root directory to begin installation:
$npx skills add https://github.com/davila7/claude-code-templates --skill mermaid-diagram-specialistcopy
The skills CLI fetches mermaid-diagram-specialist from GitHub repository davila7/claude-code-templates and configures it for Cursor.
3
Select Cursor when prompted
The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:
◆ Which agents do you want to install to?
│
│ ── Universal (.agents/skills) ── always included ────
│   • Amp
│   • Antigravity
│   • Cline
│   • Codex
│ ●Cursor(selected)
│   • Cursor
│   • Windsurf
4
Verify installation
Confirm successful installation by checking the skill directory location:
.cursor/skills/mermaid-diagram-specialist
Reload or restart Cursor to activate mermaid-diagram-specialist. Access the skill through slash commands (e.g., /mermaid-diagram-specialist) or your agent's skill management interface.
⚠
Security & Verification Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.
Additional Resources
›View source code on GitHub›Skills CLI documentation›Learn more about Cursor›What are agent skills?