Agent skill

Plantuml Guide

by wentorai in wentorai/research-plugins

Create UML diagrams and architecture visualizations with PlantUML

MITAuto-check passedDevelopment

Install Plantuml Guide

skills CLI
$ npx skills add wentorai/research-plugins --skill plantuml-guide -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install wentorai/research-plugins plantuml-guide --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/wentorai/research-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tools/diagram/plantuml-guide .claude/skills/plantuml-guide && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
plantuml-guide
GitHub stars
298
Used in
1 other repo
Token cost
~2.1k tokens
SKILL.md length
253 words
Files
1
Skills in repo
405
Repo updated
First seen
Licence
MIT

At a glance

Create UML diagrams and architecture visualizations with PlantUML

  • Works in 6 steps: Version control your diagrams: Store… → Use consistent styling: Define… → Keep diagrams focused: One diagram per… → …
  • Tasks that involve Diagrams
  • SKILL.md covers Getting Started, Sequence Diagrams, Class Diagrams and Activity Diagrams (Flowcharts), plus 7 more sections
  • Calls pip, java and docker; reaches plantuml.com

What it does

Plantuml Guide is an agent skill from wentorai/research-plugins. Create UML diagrams and architecture visualizations with PlantUML

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Diagrams. The repository describes itself as: 350+ academic research skills, MCP configs, and plugins for Research-Claw and AI agents. The licence is MIT.

When your agent uses it

  • Tasks that involve Diagrams

Example prompts

  • “/plantuml-guide”

Requirements

  • Python 3
  • Docker

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Version control your diagrams: Store .puml files alongside code/documentation in git.
  2. Use consistent styling: Define skinparams at the top of each file for consistent colors and fonts.
  3. Keep diagrams focused: One diagram per concept; split complex architectures into multiple views.
  4. Add legends and notes: Use note left of, note right of, or legend blocks to clarify semantics.
  5. Automate rendering: Include PlantUML rendering in CI/CD pipelines to keep documentation current.
  6. Export as SVG: Prefer SVG over PNG for scalable diagrams in papers and presentations.

What it can do on your machine

Read from SKILL.md and the folder at commit bf44b3c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pip
    • java
    • docker

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • plantuml.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Plantuml Guide loads about 2.1k tokens when it runs. Until then it costs about 20 tokens; SKILL.md has 253 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~20
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from wentorai/research-plugins at commit bf44b3c, republished under its MIT licence (© wentorai). 253 words, ~2,076 tokens.

Download SKILL.mdSave it as .claude/skills/plantuml-guide/SKILL.md (or your agent's skills folder).
name
plantuml-guide
description
Create UML diagrams and architecture visualizations with PlantUML

PlantUML Guide

Create UML diagrams, architecture visualizations, flowcharts, and other technical diagrams using PlantUML's text-based notation for reproducible, version-controllable diagrams.

Getting Started

PlantUML generates diagrams from plain text descriptions. Diagrams are defined in .puml files and rendered to PNG, SVG, or PDF.

Installation Options
MethodCommand / URLBest For
VS Code extensionInstall "PlantUML" by jebbsIDE integration
CLI (Java JAR)java -jar plantuml.jar diagram.pumlBatch processing
Online serverplantuml.com/plantumlQuick prototyping
Dockerdocker run plantuml/plantuml-serverSelf-hosted server
Pythonpip install plantumlPython integration
Jupyterpip install iplantumlNotebook integration
Basic Syntax
plantuml
@startuml
title My First Diagram

Alice -> Bob: Hello
Bob --> Alice: Hi there!

@enduml

Sequence Diagrams

Model interactions between components over time:

plantuml
@startuml
title Research Paper Submission Workflow

actor Author
participant "Submission\nSystem" as SS
participant "Editor" as Ed
participant "Reviewer 1" as R1
participant "Reviewer 2" as R2

Author -> SS: Submit manuscript
activate SS
SS -> Ed: Notify new submission
activate Ed

Ed -> SS: Assign reviewers
SS -> R1: Review request
SS -> R2: Review request

activate R1
activate R2

R1 -> SS: Submit review (Accept)
deactivate R1
R2 -> SS: Submit review (Minor revision)
deactivate R2

Ed -> SS: Decision: Minor revision
SS -> Author: Revision request
deactivate Ed
deactivate SS

Author -> SS: Submit revised manuscript
activate SS
SS -> Ed: Notify revision
Ed -> SS: Accept
SS -> Author: Acceptance notification
deactivate SS

@enduml

Class Diagrams

Model system structure and relationships:

plantuml
@startuml
title Research Data Model

class Paper {
  +id: UUID
  +title: String
  +abstract: String
  +doi: String
  +year: Integer
  +venue: String
  --
  +getCitations(): List<Paper>
  +getAuthors(): List<Author>
  +getBibTeX(): String
}

class Author {
  +id: UUID
  +name: String
  +orcid: String
  +affiliation: String
  +h_index: Integer
  --
  +getPapers(): List<Paper>
  +getCoauthors(): List<Author>
}

class Dataset {
  +id: UUID
  +name: String
  +doi: String
  +license: String
  +size_bytes: Long
  --
  +download(): File
  +getCitation(): String
}

class Experiment {
  +id: UUID
  +description: String
  +date: Date
  +config: JSON
  --
  +run(): Results
  +getMetrics(): Map
}

Paper "1" -- "*" Author : authored by >
Paper "1" -- "*" Dataset : uses >
Paper "1" -- "*" Experiment : contains >
Dataset "1" -- "*" Experiment : used in >
Paper "1" -- "*" Paper : cites >

@enduml

Activity Diagrams (Flowcharts)

Model workflows and decision processes:

plantuml
@startuml
title Systematic Review Screening Process

start

:Import records from databases;
:Remove duplicates;

:Screen title and abstract;

if (Meets inclusion criteria?) then (yes)
  :Retrieve full text;
  if (Full text available?) then (yes)
    :Screen full text;
    if (Meets all criteria?) then (yes)
      :Include in review;
      :Extract data;
      if (Suitable for meta-analysis?) then (yes)
        :Include in meta-analysis;
      else (no)
        :Include in narrative synthesis;
      endif
    else (no)
      :Exclude with reason;
    endif
  else (no)
    :Mark as unavailable;
  endif
else (no)
  :Exclude;
endif

:Compile PRISMA flow diagram;
stop

@enduml

Component Diagrams

Model system architecture:

plantuml
@startuml
title Research Platform Architecture

package "Web Frontend" {
  [React SPA] as SPA
  [Dashboard] as Dash
  [Skills Browser] as Skills
}

package "API Gateway" {
  [FastAPI Server] as API
  [Auth Service] as Auth
  [Rate Limiter] as RL
}

package "Backend Services" {
  [Paper Search] as PS
  [Citation Graph] as CG
  [Skill Registry] as SR
}

package "Data Layer" {
  database "PostgreSQL" as PG
  database "Redis Cache" as Redis
  database "Elasticsearch" as ES
}

package "External APIs" {
  [Unpaywall] as UP
  [CrossRef] as CR
  [OpenAlex] as OA
}

SPA --> API : HTTPS
Dash --> API : HTTPS
Skills --> API : HTTPS

API --> Auth : validate token
API --> RL : check rate limit
API --> PS : search request
API --> CG : graph query
API --> SR : skill lookup

PS --> ES : full-text search
PS --> S2 : paper metadata
PS --> CR : DOI resolution

CG --> PG : citation data
CG --> OA : citation graph

SR --> PG : skill metadata
SR --> Redis : cache

@enduml

State Diagrams

Model system states and transitions:

plantuml
@startuml
title Paper Lifecycle States

[*] --> Draft

Draft --> Submitted : Author submits
Submitted --> UnderReview : Editor assigns reviewers
Submitted --> DeskRejected : Editor rejects

UnderReview --> RevisionRequired : Minor/Major revision
UnderReview --> Accepted : Accept as is
UnderReview --> Rejected : Reject

RevisionRequired --> UnderReview : Author resubmits
RevisionRequired --> Withdrawn : Author withdraws

Accepted --> InProduction : Copy editing
InProduction --> Published : Online first
Published --> [*]

DeskRejected --> [*]
Rejected --> [*]
Withdrawn --> [*]

@enduml

Gantt Charts

Plan research timelines:

plantuml
@startuml
title Research Project Timeline

Project starts 2025-01-01

[Literature Review] starts 2025-01-01 and lasts 8 weeks
[Research Design] starts at [Literature Review]'s end and lasts 4 weeks
[IRB Approval] starts at [Research Design]'s end and lasts 6 weeks
[Data Collection] starts at [IRB Approval]'s end and lasts 12 weeks
[Data Analysis] starts at [Data Collection]'s end and lasts 8 weeks
[Paper Writing] starts at [Data Analysis]'s end and lasts 10 weeks
[Peer Review] starts at [Paper Writing]'s end and lasts 12 weeks
[Revision] starts at [Peer Review]'s end and lasts 6 weeks

-- Milestones --
[Proposal Defense] happens at [Research Design]'s end
[Conference Presentation] happens at [Data Analysis]'s end
[Submission] happens at [Paper Writing]'s end

@enduml

Mind Maps

Organize research topics:

plantuml
@startmindmap
title Machine Learning Research Landscape

* Machine Learning
** Supervised Learning
*** Classification
**** SVM
**** Decision Trees
**** Neural Networks
*** Regression
**** Linear Regression
**** Gradient Boosting
** Unsupervised Learning
*** Clustering
**** K-Means
**** DBSCAN
*** Dimensionality Reduction
**** PCA
**** t-SNE
**** UMAP
** Reinforcement Learning
*** Model-Free
**** DQN
**** PPO
*** Model-Based
**** Dreamer
**** MuZero
** Deep Learning
*** CNNs
*** Transformers
*** GANs
*** Diffusion Models

@endmindmap

Integration with LaTeX

latex
\usepackage{plantuml}

\begin{plantuml}
@startuml
Alice -> Bob: Hello
Bob --> Alice: Hi
@enduml
\end{plantuml}

% Compile with: pdflatex -shell-escape paper.tex

Integration with Markdown (Mermaid Alternative)

Many Markdown renderers (GitHub, GitLab, Notion) support Mermaid natively. PlantUML can be used via plugins or pre-rendering:

python
# Pre-render PlantUML to SVG for Markdown embedding
import plantuml

server = plantuml.PlantUML(url="http://www.plantuml.com/plantuml/svg/")
svg_content = server.processes("""
@startuml
Alice -> Bob: Hello
@enduml
""")

with open("diagram.svg", "wb") as f:
    f.write(svg_content)

Best Practices

  1. Version control your diagrams: Store .puml files alongside code/documentation in git.
  2. Use consistent styling: Define skinparams at the top of each file for consistent colors and fonts.
  3. Keep diagrams focused: One diagram per concept; split complex architectures into multiple views.
  4. Add legends and notes: Use note left of, note right of, or legend blocks to clarify semantics.
  5. Automate rendering: Include PlantUML rendering in CI/CD pipelines to keep documentation current.
  6. Export as SVG: Prefer SVG over PNG for scalable diagrams in papers and presentations.

© wentorai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/tools/diagram/plantuml-guide of wentorai/research-plugins.

Open the folder on GitHubat commit bf44b3c

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in wentorai/research-plugins, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Plantuml Guide next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Plantuml Guide compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Plantuml Guide this skillwentorai/research-plugins2981 repos~2.1kAutomated safety check: PassMIT
Archify Diagramstt-a1i/archify82k—~2.9kAutomated safety check: PassMIT
JSON Canvasheyitsnoah/claudesidian2.6k18 repos~3.5kAutomated safety check: PassMIT
Diagram Designcathrynlavery/diagram-design49k1 repos~7.6kAutomated safety check: PassMIT
Fireworks Tech Graphtisfeng/Easydict15k1 repos~1.4kAutomated safety check: PassMIT
Excalidraw Diagramcoleam00/excalidraw-diagram-skill5k2 repos~6.1kAutomated safety check: PassNone

Similar skills

  • Archify Diagrams

    tt-a1i/archify

    Creates interactive architecture, workflow, sequence, data-flow and lifecycle diagrams as standalone HTML with inline SVG, themes and image or video export.

    82k GitHub stars~2.9k tokensUpdated today
    DevelopmentAuto-check passed
  • JSON Canvas

    heyitsnoah/claudesidian

    Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections.

    2.6k GitHub starsUsed in 18 repos~3.5k tokens
    DevelopmentAuto-check passed
  • Diagram Design

    cathrynlavery/diagram-design

    Creates branded diagrams, from architecture, flowchart and sequence to charts and maps, as self-contained HTML with inline SVG, with import from draw.io, Mermaid and Excalidraw.

    49k GitHub starsUsed in 1 repo~7.6k tokens
    DevelopmentAuto-check passed
  • Fireworks Tech Graph

    tisfeng/Easydict

    Create precise SVG technical diagrams, export PNG or offline HTML, and animate supported semantic SVGs to GIF.

    15k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed
  • Excalidraw Diagram

    coleam00/excalidraw-diagram-skill

    Create Excalidraw diagram JSON files that make visual arguments.

    5k GitHub starsUsed in 2 repos~6.1k tokens
    DevelopmentAuto-check passed
  • Draw.io Diagram Studio

    Agents365-ai/drawio-skill

    Creates and edits editable draw.io diagrams from descriptions, code, infrastructure files, SQL and API schemas, with sync, review, test and export tools.

    10k GitHub stars~2.4k tokensUpdated today
    DevelopmentAuto-check: notes

More from wentorai/research-plugins

All 405 skills in this repo
  • Abstract Writing Guide

    wentorai/research-plugins

    Craft structured research abstracts that maximize clarity and journal acceptance

    298 GitHub starsUsed in 1 repo~1.7k tokens
    Auto-check passed
  • Academic Citation Manager

    wentorai/research-plugins

    Manage academic citations across BibTeX, APA, MLA, and Chicago formats

    298 GitHub starsUsed in 1 repo~2.7k tokens
    Auto-check passed
  • Academic Paper Summarizer

    wentorai/research-plugins

    Summarize academic papers with structured extraction of key elements

    298 GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed
  • Academic Study Methods

    wentorai/research-plugins

    Evidence-based study techniques for academic learning and retention

    298 GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed
  • Academic Tone Guide

    wentorai/research-plugins

    Adjust writing tone and register for academic audiences and venues

    298 GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check passed
  • Academic Translation Guide

    wentorai/research-plugins

    Academic translation, post-editing, and Chinglish correction guide

    298 GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check passed

Categories

Questions about Plantuml Guide

What does Plantuml Guide do?

Create UML diagrams and architecture visualizations with PlantUML. Plantuml Guide is an agent skill from wentorai/research-plugins.

When should I use Plantuml Guide?

Plantuml Guide fits situations like: tasks that involve Diagrams.

How do I install Plantuml Guide in Claude Code?

Run `npx skills add wentorai/research-plugins --skill plantuml-guide -a claude-code`. Or copy the skill folder (skills/tools/diagram/plantuml-guide in wentorai/research-plugins) into .claude/skills/plantuml-guide in your project. Claude Code loads it when a task matches its description.

How do I install Plantuml Guide in Codex?

Run `npx skills add wentorai/research-plugins --skill plantuml-guide -a codex`. Or copy the skill folder (skills/tools/diagram/plantuml-guide in wentorai/research-plugins) into .agents/skills/plantuml-guide in your project. Codex loads it when a task matches its description.

Can I use Plantuml Guide in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add wentorai/research-plugins --skill plantuml-guide -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/plantuml-guide, .gemini/skills/plantuml-guide, .github/skills/plantuml-guide and .opencode/skills/plantuml-guide in your project.

What does Plantuml Guide need to run?

Going by SKILL.md and its folder, Plantuml Guide needs the command-line tools its instructions call (pip, java and docker). Our summary lists: Python 3; Docker.

Does Plantuml Guide access the network?

SKILL.md names 1 domain. In commands or code: plantuml.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Plantuml Guide safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Plantuml Guide use?

Plantuml Guide is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Plantuml Guide use?

About 2.1k tokens (SKILL.md is roughly 8.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Plantuml Guide?

Skills that share tags, products or a category with Plantuml Guide: Archify Diagrams (tt-a1i/archify, 82k stars), JSON Canvas (heyitsnoah/claudesidian, 2.6k stars), Diagram Design (cathrynlavery/diagram-design, 49k stars) and Fireworks Tech Graph (tisfeng/Easydict, 15k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Plantuml Guide?

wentorai (a GitHub user) maintains it in wentorai/research-plugins, which has 298 GitHub stars. The repository holds 405 skills in this directory. The repository was last updated on June 19, 2026.

Source: wentorai/research-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.