Diagram logo

Diagram

CommunityPopular
Yeachan-Heo
diagram

Use the smallest visual when prose must carry structure—control flow, call depth, module ownership, or change shape: pseudocode, call tree, component/file tree, Mermaid diagram, or diff. Skip it when prose already answers the question.

Overview

PublisherYeachan-Heo
Repositoryoh-my-claudecode
Skill namediagram
Stars
39.8K
Forks
3.6K
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 Yeachan-Heo on GitHub. Read the source before you install it.

Installation

Install the Diagram 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/Yeachan-Heo/oh-my-claudecode/tree/main/skills/diagram
  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/Yeachan-Heo/oh-my-claudecode.git /tmp/oh-my-claudecode
mkdir -p .claude/skills
cp -r /tmp/oh-my-claudecode/skills/diagram .claude/skills/diagram
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Diagram 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 Diagram 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 Diagram 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.

Diagrams are load-bearing, not decoration. Reach for one only when prose forces the reader to hold a whole shape in their head at once — then pick the smallest view that lets them see the shape instead of reconstructing it from sentences. Everything here renders in the conversation as text blocks or Mermaid; at most one artifact file is ever written.

The vocabulary

Pick one view; two at most. More is noise.

Pseudocode — logic without language noise. Reduces a decision to its branching shape:

text
on(request)
  if state file locked by another writer
    queue and return pending
  acquire lock
  write
  release

Call tree — runtime control flow. Depth shows who owns the flow; annotate where the interesting edge is:

text
acquireStateFileLockSync()
  resolveLockPath()
  openExclusive()
  writePid()

Component tree — UI or module structure, with the boundaries that matter annotated inline:

tsx
<SettingsPage> (src/routes/settings)
  <SessionList> (owns its fetches)
  <DangerZone>
    <ConfirmButton> (disabled until typed confirmation)

File tree — where responsibility lives; keep it shallow, one annotation per directory:

text
src/
├── hooks/        # hook registry + types
├── tools/        # MCP tool handlers
└── workflow/     # registry + projections

Mermaid — interaction between parties, dataflow, or state transitions:

Diff — the shape of a change when the surrounding structure already exists. Match the diff to the topic:

a component change:

diff
 <SettingsPage>
   <SessionList />
   <DangerZone>
+    <ConfirmButton />
   </DangerZone>

a file-layout change:

diff
 src/tools/
-└── state-tools.ts
+└── state-tools/
+   ├── handlers.ts
+   └── schema.ts

a control-flow change:

diff
 commit()
   stage()
     hashBlobs()
+  writeObject()
   updateRef()
+    acquireStateFileLock()

a state-machine change:

diff
 on(request)
-  write immediately
+  if locked
+    queue and return pending
+  acquire lock
+  write
+  release

The whole block — when elision would hide who owns what or the order things run in, show the complete unit once, copyable:

ts
export function isRegistryEnabled(): boolean {
  const flag = process.env.OMC_WORKFLOW_REGISTRY;
  return flag !== '0' && flag !== 'false';
}

When text runs out

A UI layout, a before/after comparison, or a concept too dense for Mermaid: write one focused HTML file — a diagram, an infographic, or a few slides — styled after the product's own colors, type, and components, filled with real labels and data, working on desktop and mobile. Open it with the platform opener (start on Windows, open on macOS, xdg-open on Linux) and stop there: one artifact, not a gallery.

Discipline

  • Place each visual directly beside the two or three sentences it supports.
  • Carry only the calls, files, props, states, and boundaries that answer the current question — every extra node is a decoding tax on the reader.
  • If the honest answer fits in one sentence, write the sentence.

Frequently asked questions

What does the Diagram AI skill do?

Use the smallest visual when prose must carry structure—control flow, call depth, module ownership, or change shape: pseudocode, call tree, component/file tree, Mermaid diagram, or diff. Skip it when prose already answers the question.

Why use Diagram on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Yeachan-Heo/oh-my-claudecode/tree/main/skills/diagram. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Diagram?

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 Diagram?

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

Is the Diagram AI skill free?

Yes. It is published on GitHub by Yeachan-Heo 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 👇