Patent Diagram Generator logo

Patent Diagram Generator

Community
RobThePCGuy
patent-diagram-generator

Create patent-style technical diagrams including flowcharts, block diagrams, and system architectures using Graphviz with reference numbering

Overview

PublisherRobThePCGuy
RepositoryClaude-Patent-Creator
Skill namepatent-diagram-generator
Stars
203
Forks
33
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 RobThePCGuy on GitHub. Read the source before you install it.

Installation

Install the Patent Diagram Generator 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.
    https://github.com/RobThePCGuy/Claude-Patent-Creator/tree/main/skills/patent-diagram-generator
  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/RobThePCGuy/Claude-Patent-Creator.git /tmp/Claude-Patent-Creator
mkdir -p .claude/skills
cp -r /tmp/Claude-Patent-Creator/skills/patent-diagram-generator .claude/skills/patent-diagram-generator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Patent Diagram Generator 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 Patent Diagram Generator 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 Patent Diagram Generator 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.

Patent Diagram Generator Skill

Create patent-style technical diagrams including flowcharts, block diagrams, and system architectures using Graphviz.

When to Use

Invoke this skill when users ask to:

  • Create flowcharts for method claims
  • Generate block diagrams for system claims
  • Draw system architecture diagrams
  • Create technical illustrations for patents
  • Add reference numbers to diagrams
  • Generate patent figures

What This Skill Does

  1. Flowchart Generation:

    • Method step flowcharts
    • Decision trees
    • Process flows with branches
    • Patent-style step numbering
  2. Block Diagram Creation:

    • System component diagrams
    • Hardware architecture diagrams
    • Software module diagrams
    • Component interconnections
  3. Custom Diagram Rendering:

    • Render Graphviz DOT code
    • Support multiple formats (SVG, PNG, PDF)
    • Multiple layout engines (dot, neato, fdp, circo, twopi)
  4. Patent-Style Formatting:

    • Add reference numbers (10, 20, 30, etc.)
    • Use clear labels and connections
    • Professional formatting for USPTO filing

Required Dependencies

This skill requires Graphviz to be installed:

Windows:

bash
choco install graphviz

Linux:

bash
sudo apt install graphviz

Mac:

bash
brew install graphviz

Python Package:

bash
pip install graphviz

How to Use

When this skill is invoked:

  1. Load diagram generator:

    python
    import os
    import sys
    sys.path.insert(0, os.environ.get('CLAUDE_PLUGIN_ROOT', '.'))
    from mcp_server.diagram_generator import PatentDiagramGenerator
    
    generator = PatentDiagramGenerator()
  2. Create flowchart from steps:

    python
    steps = [
        {"id": "start", "label": "Start", "shape": "ellipse", "next": ["step1"]},
        {"id": "step1", "label": "Initialize System", "shape": "box", "next": ["decision"]},
        {"id": "decision", "label": "Is Valid?", "shape": "diamond", "next": ["step2", "error"]},
        {"id": "step2", "label": "Process Data", "shape": "box", "next": ["end"]},
        {"id": "error", "label": "Handle Error", "shape": "box", "next": ["end"]},
        {"id": "end", "label": "End", "shape": "ellipse", "next": []}
    ]
    
    diagram_path = generator.create_flowchart(
        steps=steps,
        filename="method_flowchart",
        output_format="svg"
    )
  3. Create block diagram:

    python
    blocks = [
        {"id": "input", "label": "Input\\nSensor", "type": "input"},
        {"id": "cpu", "label": "Central\\nProcessor", "type": "process"},
        {"id": "memory", "label": "Memory\\nStorage", "type": "storage"},
        {"id": "output", "label": "Output\\nDisplay", "type": "output"}
    ]
    
    connections = [
        ["input", "cpu", "raw data"],
        ["cpu", "memory", "store"],
        ["memory", "cpu", "retrieve"],
        ["cpu", "output", "processed data"]
    ]
    
    diagram_path = generator.create_block_diagram(
        blocks=blocks,
        connections=connections,
        filename="system_diagram",
        output_format="svg"
    )
  4. Render custom DOT code:

    python
    dot_code = """
    digraph PatentSystem {
        rankdir=LR;
        node [shape=box, style=rounded];
    
        Input [label="User Input\\n(10)"];
        Processor [label="Processing Unit\\n(20)"];
        Output [label="Display\\n(30)"];
    
        Input -> Processor [label="data"];
        Processor -> Output [label="result"];
    }
    """
    
    diagram_path = generator.render_dot_diagram(
        dot_code=dot_code,
        filename="custom_diagram",
        output_format="svg",
        engine="dot"
    )
  5. Add reference numbers:

    python
    # After creating a diagram, add patent-style reference numbers
    reference_map = {
        "Input Sensor": 10,
        "Central Processor": 20,
        "Memory Storage": 30,
        "Output Display": 40
    }
    
    annotated_path = generator.add_reference_numbers(
        svg_path=diagram_path,
        reference_map=reference_map
    )

Diagram Templates

Get common templates:

python
templates = generator.get_diagram_templates()

# Available templates:
# - simple_flowchart: Basic process flow
# - system_block: System architecture
# - method_steps: Sequential method
# - component_hierarchy: Hierarchical structure

Shape Types

Flowchart Shapes

  • ellipse: Start/End points
  • box: Process steps
  • diamond: Decision points
  • parallelogram: Input/Output operations
  • cylinder: Database/Storage

Block Diagram Types

  • input: Input devices/sensors
  • output: Output devices/displays
  • process: Processing units
  • storage: Memory/storage
  • decision: Control logic
  • default: General components

Layout Engines

  • dot: Hierarchical (top-down/left-right)
  • neato: Spring model layout
  • fdp: Force-directed layout
  • circo: Circular layout
  • twopi: Radial layout

Output Formats

  • svg: Scalable Vector Graphics (best for editing)
  • png: Raster image (good for viewing)
  • pdf: Portable Document Format (USPTO compatible)

Patent-Style Reference Numbers

Convention:

  • Main components: 10, 20, 30, 40, ...
  • Sub-components: 12, 14, 16 (under 10)
  • Elements: 22, 24, 26 (under 20)

Example labeling:

"Input Sensor (10)"
"  - Detector Element (12)"
"  - Signal Processor (14)"
"Central Unit (20)"
"  - CPU Core (22)"
"  - Cache (24)"

Presentation Format

When creating diagrams:

  1. Describe what will be generated: "Creating a flowchart for the authentication method with 5 steps..."

  2. Generate the diagram: Run Python code to create SVG/PNG/PDF

  3. Show file location: "Diagram created: ${CLAUDE_PLUGIN_ROOT}/python\diagrams\method_flowchart.svg"

  4. List reference numbers (if added):

    Reference Numbers:
    - Input Module (10)
    - Processing Unit (20)
    - Output Interface (30)

Common Use Cases

  1. Method Claims → Flowcharts

    • Show sequential steps
    • Include decision branches
    • Number steps (S1, S2, S3...)
  2. System Claims → Block Diagrams

    • Show components and connections
    • Use reference numbers
    • Indicate data flow directions
  3. Architecture Diagrams → Custom DOT

    • Complex system layouts
    • Multiple interconnections
    • Hierarchical structures

Error Handling

If Graphviz is not installed:

  1. Check installation: dot -V
  2. Install for your OS (see above)
  3. Verify Python package: pip show graphviz
  4. Test generation: python scripts/test_diagrams.py

Tools Available

  • Bash: To run Python diagram generation
  • Write: To save DOT code or diagrams
  • Read: To load existing diagrams or templates

Frequently asked questions

What does the Patent Diagram Generator AI skill do?

Create patent-style technical diagrams including flowcharts, block diagrams, and system architectures using Graphviz with reference numbering

Why use Patent Diagram Generator on TypingMind?

Because you install it once and use it with any model. Patent Diagram Generator 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 Patent Diagram Generator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/RobThePCGuy/Claude-Patent-Creator/tree/main/skills/patent-diagram-generator. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Patent Diagram Generator?

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 Patent Diagram Generator?

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

Is the Patent Diagram Generator AI skill free?

Yes. It is published on GitHub by RobThePCGuy 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 👇