033 Architecture Diagrams logo

033 Architecture Diagrams

Community
jabrena
033-architecture-diagrams

Use when you need to generate Java project diagrams — including UML sequence diagrams, UML class diagrams, C4 model diagrams, UML state machine diagrams, UML Deployment Diagrams, ER (Entity Relationship) diagrams, and bounded-context diagrams — through a modular, step-based interactive process that adapts to your specific visualization needs. This should trigger for requests such as Generate UML diagram; Create sequence diagram; Create class diagram; Create state machine diagram; Create deployment diagram; Create C4 diagram; Create bounded-context diagram; Create context-map diagram. Part of Plinth Toolkit

Overview

Publisherjabrena
Repositoryplinth
Skill name033-architecture-diagrams
Stars
455
Forks
95
Bundled files
7
LicenseApache-2.0
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.

  • 7 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the 033 Architecture 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.
    https://github.com/jabrena/plinth/tree/main/skills/033-architecture-diagrams
  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/jabrena/plinth.git /tmp/plinth
mkdir -p .claude/skills
cp -r /tmp/plinth/skills/033-architecture-diagrams .claude/skills/033-architecture-diagrams
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable 033 Architecture 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 033 Architecture 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 033 Architecture 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.

Java Diagrams Generator with modular step-based configuration

Generate comprehensive Java project diagrams through a modular, step-based interactive process that covers UML sequence diagrams, UML class diagrams, C4 model diagrams, UML state machine diagrams, UML Deployment Diagrams, ER (Entity Relationship) diagrams, and bounded-context diagrams using PlantUML syntax. This is an interactive SKILL.

What is covered in this Skill?

  • UML sequence diagram generation for application workflows and API interactions
  • UML class diagram generation for package structure and class relationships
  • C4 model diagram generation for Context, Container, and Component diagrams
  • UML state machine diagram generation for entity lifecycles and business workflows
  • UML Deployment Diagram generation for runtime topology, nodes, execution environments, deployed components, data stores, queues, external systems, and communication paths
  • ER diagram generation from SQL schema (DDL, migrations) using PlantUML Chen notation
  • Bounded-context diagram generation for DDD context maps across one or more repositories
  • PlantUML syntax for all diagram types
  • File organization strategies: single-file, separate-files, or integrated with existing documentation
  • Final diagram validation with PlantUML syntax checking
  • PlantUML validation and PNG/SVG rendering with a trusted local PlantUML installation or repository-approved wrapper

Constraints

Before applying any diagram generation, ensure the project validates. If validation fails, stop immediately — do not proceed until all validation errors are resolved.

  • MANDATORY: Run ./mvnw validate or mvn validate before applying any diagram generation
  • SAFETY: If validation fails, stop immediately — do not proceed until all validation errors are resolved
  • BEFORE READING DIAGRAM REFERENCES: Run the question flow embedded in this SKILL.md first. Ask the diagram preference questions one by one, collect selected diagram families and output preferences, then read only the implementation references selected by the user's answers
  • C4 SCOPE: C4 diagrams are restricted to Context, Container, and Component diagrams
  • SUPPLY CHAIN: Generated PlantUML diagrams must use trusted local includes only; do not use remote !include URLs for C4 or icon libraries
  • TOOLING SAFETY: Use only trusted local PlantUML tooling or a repository-approved wrapper; do not pull or run remote container images as part of this skill

When to use this skill

  • Generate UML diagram
  • Create sequence diagram
  • Create class diagram
  • Create state machine diagram
  • Create deployment diagram
  • Create C4 diagram
  • Generate ER diagram
  • Create bounded-context diagram
  • Create context-map diagram

Workflow

  1. Validate project state

Run ./mvnw validate or mvn validate before applying any diagram generation.

Step constraints:

  • If validation fails, stop and ask to resolve errors first
  1. Ask diagram assessment questions before reading references

Run this XML-included question flow before reading any diagram-family implementation reference. Ask questions one-by-one in strict order, wait for the user's answer to each question, and record selected diagram families, C4 scope, bounded-context repository scope, output organization, file format, and documentation preference before continuing.

IMPORTANT: You MUST ask these questions in the exact order and wording shown here. The very first question to the user MUST be "Question 1: What diagrams do you want to generate?". Do not ask any other questions prior to it.

Diagrams Selection

Conditional Flow Rules:

  • Based on your selection here, only the relevant diagram generation steps will be executed.
  • If you choose "Skip", no diagrams will be generated.
  • Each diagram type has its own conditional follow-up questions.

Question 1: What diagrams do you want to generate?

Options:

  • UML sequence diagrams
  • UML class diagrams
  • UML state-machine diagrams
  • C4 model diagrams (Context, Container, Component)
  • UML Deployment Diagrams
  • ER diagrams (Entity Relationship)
  • Bounded-context diagrams
  • All diagrams
  • Skip

Question 2: For UML sequence diagrams, which types would you like to generate? Ask this question only if you selected "UML sequence diagrams" or "All diagrams" in Question 1.

Options:

  • Main application flows (user journeys, authentication, core features)
  • API interactions (REST endpoints, request/response patterns)
  • Complex business logic flows (multi-step processes, transactions)
  • All sequence diagram types
  • Skip

Question 3: For UML class diagrams, which scope would you like to cover? Ask this question only if you selected "UML class diagrams" or "All diagrams" in Question 1.

Options:

  • All packages (complete project structure)
  • Core business logic packages only
  • Specific packages (I'll specify which ones)
  • Skip

Question 4: For UML class diagrams, what level of detail do you prefer? Ask this question only if you selected "UML class diagrams" or "All diagrams" in Question 1 and did not select "Skip" in Question 3.

Options:

  • High-level (classes and relationships only)
  • Detailed (include key methods and attributes)
  • Full detail (all public methods, attributes, and annotations)

Question 5: For C4 model diagrams, which levels would you like to generate? Ask this question only if you selected "C4 model diagrams" or "All diagrams" in Question 1.

Options:

  • Complete C4 model (Context, Container, Component)
  • High-level diagrams only (Context and Container)
  • Component diagrams only
  • Specific C4 levels (Context, Container, and/or Component)
  • Skip

Question 6: For UML state-machine diagrams, which types would you like to generate? Ask this question only if you selected "UML state-machine diagrams" or "All diagrams" in Question 1.

Options:

  • Entity lifecycles (domain object state transitions like Order, User, Document)
  • Business workflows (process state machines like approval, payment, shipping)
  • System behaviors (component operational states like connections, jobs, transactions)
  • User interactions (UI component state transitions like forms, wizards, dialogs)
  • All state machine types
  • Skip

Question 7: For ER diagrams, which schema scope would you like to cover? Ask this question only if you selected "ER diagrams (Entity Relationship)" or "All diagrams" in Question 1.

Options:

  • Complete database schema (all tables)
  • Core domain tables only
  • Specific tables (I'll specify which ones)
  • Skip

Question 8: For bounded-context diagrams, which repositories should be represented? Ask this question only if you selected "Bounded-context diagrams" or "All diagrams" in Question 1.

Options:

  • Current repository only
  • One or more local repository paths (I'll provide paths)
  • One or more repository URLs (I'll provide URLs)
  • A named repository list (I'll provide names and context)
  • Skip

For each repository in scope, collect what is available: repository name or path, bounded context, domain or subdomain, owning team, application type, owned data store, exposed interfaces, consumed interfaces, and known relationships.


Question 9: For UML Deployment Diagrams, what source material should be used first? Ask this question only if you selected "UML Deployment Diagrams" or "All diagrams" in Question 1.

Options:

  • Existing deployment diagram image or topology sketch (I'll provide the image)
  • System description file (I'll provide the file path)
  • Repository documentation, configuration, or deployment descriptors
  • Ask me for missing deployment topology details
  • Skip

When a deployment image or system description file is provided, use it as source material before asking fallback questions. Ask only for missing or ambiguous deployment facts such as actors, services, CI/CD systems, runtime nodes, execution environments, deployed artifacts or components, external systems, data stores, queues, protocols, ports, relationships, and infrastructure or network boundaries.


Question 10: How would you like to organize the generated diagram files?

Options:

  • Single directory (all diagrams in /diagrams folder)
  • Organized by type (separate folders for each diagram type)
  • Organized by package/domain (group related diagrams together)
  • Integrated with existing documentation structure

Question 11: What file format would you prefer for the diagrams?

Options:

  • PlantUML source files (.puml) only
  • PlantUML with markdown documentation
  • Both PlantUML and generated images (requires PlantUML rendering)
  • Integrated into existing documentation files

Question 12: Would you like to include explanatory documentation with the diagrams?

Options:

  • Yes, comprehensive explanations for each diagram
  • Yes, brief descriptions and usage notes
  • No, just the diagrams
  • Integrate explanations into existing documentation

After all applicable questions are answered, confirm the selections and map them to references:

  • If UML sequence diagrams are selected, read references/033-architecture-diagrams-uml-sequence.md.
  • If UML class diagrams are selected, read references/033-architecture-diagrams-uml-class.md.
  • If C4 model diagrams are selected, read references/033-architecture-diagrams-c4.md.
  • If UML state-machine diagrams are selected, read references/033-architecture-diagrams-state-machine.md.
  • If UML Deployment Diagrams are selected, read references/033-architecture-diagrams-deployment.md.
  • If ER diagrams are selected, read references/033-architecture-diagrams-er.md.
  • If bounded-context diagrams are selected, read references/033-architecture-diagrams-bounded-context.md.
  • If All diagrams is selected, read all seven focused diagram-family references.
  • If Skip is selected for a diagram family, do not read that diagram-family reference.
  • Do not read unselected diagram-family references.
  1. Read selected references and generate PlantUML diagrams

Create requested diagrams in PlantUML syntax using only the selected focused references, project inputs, and repository context.

  1. Validate and finalize outputs

Check generated diagrams for syntax correctness and consistency with selected scope before final delivery.

Use an already installed PlantUML CLI or a repository-approved wrapper to validate and render generated .puml files. If PlantUML is not available, report the missing trusted tool and provide setup guidance instead of downloading or running remote execution artifacts.

Validate PlantUML syntax without generating images:

bash
plantuml -checkonly diagrams

Render PNG images:

bash
plantuml -tpng diagrams

Render SVG images:

bash
plantuml -tsvg diagrams

Point the command at the directory or .puml file containing generated diagrams. Do not pull or run external container images during validation.

Reference

For detailed guidance, examples, and constraints, see:

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the 033 Architecture Diagrams AI skill do?

Use when you need to generate Java project diagrams — including UML sequence diagrams, UML class diagrams, C4 model diagrams, UML state machine diagrams, UML Deployment Diagrams, ER (Entity Relationship) diagrams, and bounded-context diagrams — through a modular, step-based interactive process that adapts to your specific visualization needs. This should trigger for requests such as Generate UML diagram; Create sequence diagram; Create class diagram; Create state machine diagram; Create deployment diagram; Create C4 diagram; Create bounded-context diagram; Create context-map diagram. Part o...

Why use 033 Architecture Diagrams on TypingMind?

Because you install it once and use it with any model. 033 Architecture 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 033 Architecture Diagrams in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jabrena/plinth/tree/main/skills/033-architecture-diagrams. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use 033 Architecture 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 033 Architecture Diagrams?

As many as you like. As long as a model supports skills, you can use 033 Architecture Diagrams with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the 033 Architecture Diagrams AI skill free?

Yes. It is published on GitHub by jabrena under the Apache-2.0 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 👇