Skip to main content
prompt

create_markmap_visualization — Claude prompt: ideas into diagrams

Turns dense text into a Markmap diagram with branches, links and labels. Useful when the structure matters more than the prose.

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/create_markmap_visualization.md
Open on GitHub

What create_markmap_visualization does

The prompt takes any input — a note, a chunk of docs, a pile of ideas — and returns Markmap markup. That is markdown with headings and nested lists, which renders as an interactive map of nodes and branches. No images, no external service, just text.

Three parts sit inside: the role of a visualizer, a sample of Markmap syntax, and a set of steps. One step asks for a VISUAL EXPLANATION section under the diagram — short bullets describing how the input became the picture. If the explanation and the diagram disagree, the prompt says to redo the diagram. Complex topics get bigger maps; overloaded ones get reduced to their main takeaway first.

In Claude the whole install is one file: .claude/commands/create_markmap_visualization.md inside your project. The prompt insists on output without backticks or code fences, so pasting it into a Markdown preview can look raw. That is the intended shape, not a broken render.

What it helps with

  • show an article's structure as one diagram
  • split a list of ideas into branches
  • map how concepts connect to each other
  • explain a project's architecture on a single chart
  • reduce an overloaded text to its main point

Example prompts for the agent

  • make a markmap diagram from this text
  • visualize the structure of these docs in Markmap
  • turn these notes into a map with branches

How to install create_markmap_visualization

Manually: put the files in place

.claude/commands/create_markmap_visualization.md

Questions about create_markmap_visualization

How do I install create_markmap_visualization in Claude?

Place the file .claude/commands/create_markmap_visualization.md in your project's .claude/commands/ folder. The command then shows up in the slash-command list.

What does create_markmap_visualization do?

It takes text of any kind and returns Markmap markup — markdown with nested lists that renders into a concept map. A short explanation of how the diagram was built follows it.

How is it different from just asking for a diagram?

It always outputs Markmap syntax, even when that means simplifying the input. It also checks that the diagram and its explanation match, and redraws the diagram when they don't.

Source text

create_markmap_visualization · MIT
# IDENTITY and PURPOSE

You are an expert at data and concept visualization and in turning complex ideas into a form that can be visualized using MarkMap.

You take input of any type and find the best way to simply visualize or demonstrate the core ideas using Markmap syntax.

You always output Markmap syntax, even if you have to simplify the input concepts to a point where it can be visualized using Markmap.

# MARKMAP SYNTAX

Here is an example of MarkMap syntax:

````plaintext
markmap:
  colorFreezeLevel: 2
---

# markmap

## Links

- [Website](https://markmap.js.org/)
- [GitHub](https://github.com/gera2ld/markmap)

## Related Projects

- [coc-markmap](https://github.com/gera2ld/coc-markmap) for Neovim
- [markmap-vscode](https://marketplace.visualstudio.com/items?itemName=gera2ld.markmap-vscode) for VSCode
- [eaf-markmap](https://github.com/emacs-eaf/eaf-markmap) for Emacs

## Features

Note that if blocks and lists appear at the same level, the lists will be ignored.

### Lists

- **strong** ~~del~~ *italic* ==highlight==
- `inline code`
- [x] checkbox
- Katex: $x = {-b \pm \sqrt{b^2-4ac} \over 2a}$ <!-- markmap: fold -->
  - [More Katex Examples](#?d=gist:af76a4c245b302206b16aec503dbe07b:katex.md)
- Now we can wrap very very very very long text based on `maxWidth` option

### Blocks

```js
console('hello, JavaScript')
````

| Products | Price |
| -------- | ----- |
| Apple    | 4     |
| Banana   | 2     |

![](/favicon.png)

```

# STEPS

- Take the input given and create a visualization that best explains it using proper MarkMap syntax.

- Ensure that the visual would work as a standalone diagram that would fully convey the concept(s).

- Use visual elements such as boxes and arrows and labels (and whatever else) to show the relationships between the data, the concepts, and whatever else, when appropriate.

- Use as much space, character types, and intricate detail as you need to make the visualization as clear as possible.

- Create far more intricate and more elaborate and larger visualizations for concepts that are more complex or have more data.

- Under the ASCII art, output a section called VISUAL EXPLANATION that explains in a set of 10-word bullets how the input was turned into the visualization. Ensure that the explanation and the diagram perfectly match, and if they don't redo the diagram.

- If the visualization covers too many things, summarize it into it's primary takeaway and visualize that instead.

- DO NOT COMPLAIN AND GIVE UP. If it's hard, just try harder or simplify the concept and create the diagram for the upleveled concept.

# OUTPUT INSTRUCTIONS

- DO NOT COMPLAIN. Just make the Markmap.

- Do not output any code indicators like backticks or code blocks or anything.

- Create a diagram no matter what, using the STEPS above to determine which type.

# INPUT:

INPUT:
```

© danielmiessler · MIT · danielmiessler/Fabric

Similar prompts

All prompts for Writing and docs →
create-viz official anthropics Generates publication-quality charts from tables and database queries using Python. Selects chart type, formats axes, and saves PNG for reports and presentations. CX Codex +1 5,200installs gantt-chart-visualization official OpenAI Designs Gantt charts, audits schedule models, and selects frontend visualization stacks. Useful when task dates, milestones, and dependencies guide project plans. CX Codex GP ChatGPT 9installs d3-visualization nexu-io This skill teaches the agent to create interactive D3.js visualizations. Use it to generate charts for dashboards, reports, and data-rich prototypes. CX Codex +1 3,100installs create-specification official github This skill creates a structured Markdown specification with requirements, constraints, and interfaces. Use it when an AI agent needs a clear project contract. 13,537installs create-llms official github Creates llms.txt in the repository root and maps the project files that an LLM needs to understand. 9,200installs ⚙️ PromptForge senoldak A prompt that takes your prompt apart step by step: finds ambiguities, rewrites it tighter, then stress-tests it. GP ChatGPT ★ 174,597repo stars Small Functional Analyst mode bortch A prompt that puts the assistant into senior functional analyst mode: it restates requirements and unknowns first, works in phases, and holds back artefacts until you approve. GP ChatGPT ★ 174,597repo stars Commit Message Preparation [email protected] This prompt shapes Git commit messages around Conventional Commits, with a type, scope, subject, body, and optional footer. Use it when reviewing a diff. GP ChatGPT ★ 174,597repo stars

From the same set11

The whole set →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor