Diagram To Image logo

Diagram To Image

Community
sugarforever
diagram-to-image

Convert Mermaid diagrams and Markdown tables to images (PNG) for platforms that don't support rich formatting. Use when user asks to "convert to image", "export as PNG", "make this an image", or has content for X/Twitter that needs visual exports.

Overview

Publishersugarforever
Repository01coder-agent-skills
Skill namediagram-to-image
Stars
139
Forks
37
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

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

Installation

Install the Diagram To Image 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/sugarforever/01coder-agent-skills/tree/main/skills/diagram-to-image
  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/sugarforever/01coder-agent-skills.git /tmp/01coder-agent-skills
mkdir -p .claude/skills
cp -r /tmp/01coder-agent-skills/skills/diagram-to-image .claude/skills/diagram-to-image
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Diagram To Image 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 To Image 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 To Image 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.

Diagram to Image

Convert Mermaid diagrams and Markdown tables to PNG images via the mermaid-red API (diagramless.xyz). Produces high-quality, styled output with custom themes — no heavy local dependencies needed.

When to Use

Use this skill when:

  • User has a Mermaid diagram that needs to be converted to an image
  • User has a Markdown table that needs to be converted to an image
  • User is writing content for X/Twitter and needs visual exports
  • User asks to "convert to image", "export as PNG", "make this an image", or similar

Prerequisites

The bundled script uses Node.js built-in fetch (Node 18+). No npm install needed.

bash
# The render script is bundled with this skill:
SKILL_DIR=~/.claude/skills/diagram-to-image/scripts
ls $SKILL_DIR/diagram-to-image.mjs

Smart Output Location

IMPORTANT: Determine the best output location based on context. Follow this decision tree:

1. User Specifies Path

If user explicitly mentions a path or filename, use that.

2. Project Context Detection

Check for common image/asset directories in the current project:

bash
# Check for existing image directories (in order of preference)
ls -d ./images ./assets ./img ./static ./public/images ./assets/images 2>/dev/null | head -1

Use the first existing directory found. Common patterns:

  • ./images/ - General projects
  • ./assets/ - Web projects
  • ./assets/images/ - Structured web projects
  • ./public/images/ - Next.js, React projects
  • ./static/ - Hugo, other static site generators
  • ./img/ - Short form convention

3. Article/Document Context

If user is writing an article or document:

  • Look for the document's directory
  • Create images/ subdirectory if appropriate
  • Name the image based on the document name + descriptor

4. Conversation Context

Analyze the conversation to determine:

  • What the diagram represents → Use for filename (e.g., auth-flow.png, user-journey.png)
  • Related file being discussed → Place image near that file
  • Topic being discussed → Use for naming

5. Default Fallback

If no context clues:

  • Use current working directory
  • Generate descriptive filename from diagram content

Filename Generation

Create meaningful filenames based on content analysis:

Content PatternExample Filename
flowchart with auth/loginauth-flow.png
sequenceDiagram with APIapi-sequence.png
erDiagramentity-relationship.png
pie chart about Xx-distribution.png
gantt chartproject-timeline.png
Table with comparisoncomparison-table.png
Table with datadata-table.png

Rules:

  • Use kebab-case (lowercase with hyphens)
  • Keep names concise but descriptive (2-4 words)
  • Avoid generic names like diagram.png or image.png
  • Include topic/subject when identifiable

Conversion Process

Step 1: Analyze Context

Before converting, gather context:

  1. Check current working directory
  2. Look for existing image directories
  3. Analyze diagram/table content for naming
  4. Consider any files or topics mentioned in conversation

Step 2: Determine Output Path

bash
# Example logic (implement mentally, not as literal script)
if user_specified_path:
    output_path = user_specified_path
elif exists("./images"):
    output_path = "./images/{generated_name}.png"
elif exists("./assets"):
    output_path = "./assets/{generated_name}.png"
elif exists("./public/images"):
    output_path = "./public/images/{generated_name}.png"
else:
    output_path = "./{generated_name}.png"

Step 3: Create Temporary Input File

bash
# For Mermaid diagrams
cat > /tmp/diagram.mmd << 'DIAGRAM_EOF'
<mermaid content>
DIAGRAM_EOF

# For Markdown tables
cat > /tmp/table.md << 'TABLE_EOF'
<table content>
TABLE_EOF

Step 4: Convert via mermaid-red API

The API auto-detects content type (mermaid vs table). Both use the same command.

Using the bundled script:

bash
# Mermaid diagram
node ~/.claude/skills/diagram-to-image/scripts/diagram-to-image.mjs /tmp/diagram.mmd -o <output_path>.png

# Markdown table
node ~/.claude/skills/diagram-to-image/scripts/diagram-to-image.mjs /tmp/table.md -o <output_path>.png

# With custom theme
node ~/.claude/skills/diagram-to-image/scripts/diagram-to-image.mjs /tmp/diagram.mmd -o <output_path>.png --theme ocean

# Force content type (if auto-detect gets it wrong)
node ~/.claude/skills/diagram-to-image/scripts/diagram-to-image.mjs /tmp/table.md -o <output_path>.png --type table

Available options:

  • --theme <name> — default, dark, forest, neutral, ocean, emerald, midnight, slate, lavender, blueprint
  • --type <type> — auto (default), mermaid, table
  • --scale <n> — 1-4 (default: 2, for 2x DPI)
  • --bg <color> — Background color (default: white, use "transparent" for no bg)
  • --server <url> — Override server (default: https://diagramless.xyz)

Piping from stdin also works:

bash
echo "graph TD; A-->B" | node ~/.claude/skills/diagram-to-image/scripts/diagram-to-image.mjs -o out.png
cat /tmp/table.md | node ~/.claude/skills/diagram-to-image/scripts/diagram-to-image.mjs --type table -o table.png

Step 5: Report Result

After conversion, tell the user:

  1. Full path where image was saved
  2. Why that location was chosen (briefly)
  3. File size in bytes (printed by the script)
  4. Suggest they can specify a different location if needed

Examples

Example 1: Project with images/ directory

Context: User is in a project that has ./images/ directory, discussing authentication.

User: "Convert this to an image"

flowchart TD
    A[Login] --> B{Valid?}
    B -->|Yes| C[Dashboard]
    B -->|No| D[Error]

Action:

  1. Detect ./images/ exists
  2. Analyze content → authentication flow
  3. Generate filename: login-flow.png
  4. Save content to /tmp/diagram.mmd
  5. Run: node ~/.claude/skills/diagram-to-image/scripts/diagram-to-image.mjs /tmp/diagram.mmd -o ./images/login-flow.png

Example 2: Writing X article about AI with ocean theme

Context: User mentioned writing an article about AI agents for X.

User: "Make this a PNG with ocean theme"

flowchart LR
    User --> Agent --> Tools --> Response

Action:

  1. Save content to /tmp/diagram.mmd
  2. Run: node ~/.claude/skills/diagram-to-image/scripts/diagram-to-image.mjs /tmp/diagram.mmd -o ./ai-agent-flow.png --theme ocean

Example 3: Data comparison table

User: "Export this table as image"

| Model | Speed | Accuracy |
|-------|-------|----------|
| GPT-4 | Slow | High |
| Claude | Fast | High |

Action:

  1. Save content to /tmp/table.md
  2. Run: node ~/.claude/skills/diagram-to-image/scripts/diagram-to-image.mjs /tmp/table.md -o ./model-comparison.png (auto-detects as table)

Example 4: User specifies location

User: "Save this diagram to ~/Desktop/my-chart.png"

Action: Use exactly ~/Desktop/my-chart.png as output path.

Error Handling

  • If the API server is unreachable, the script prints a clear error message
  • If content type auto-detection fails, use --type mermaid or --type table explicitly
  • For local development/testing, use --server http://localhost:3000

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 Diagram To Image AI skill do?

Convert Mermaid diagrams and Markdown tables to images (PNG) for platforms that don't support rich formatting. Use when user asks to "convert to image", "export as PNG", "make this an image", or has content for X/Twitter that needs visual exports.

Why use Diagram To Image on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/sugarforever/01coder-agent-skills/tree/main/skills/diagram-to-image. 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 Diagram To Image?

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 To Image?

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

Is the Diagram To Image AI skill free?

Yes. It is published on GitHub by sugarforever 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 👇