Mermaid Config logo

Mermaid Config

Community
diegomarino
mermaid-config

Change theme, output format, or check plugin dependencies

Overview

Publisherdiegomarino
Repositoryclaude-toolshed
Skill namemermaid-config
Stars
58
Forks
5
Bundled files
Instructions only
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 diegomarino on GitHub. Read the source before you install it.

Installation

Install the Mermaid Config 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/diegomarino/claude-toolshed/tree/main/plugins/mermaid/skills/mermaid-config
  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/diegomarino/claude-toolshed.git /tmp/claude-toolshed
mkdir -p .claude/skills
cp -r /tmp/claude-toolshed/plugins/mermaid/skills/mermaid-config .claude/skills/mermaid-config
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mermaid Config 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 Mermaid Config 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 Mermaid Config 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.

/mermaid-config

User request: "$ARGUMENTS"

Task

Interactive config wizard: view and update plugin settings, or run a dependency health check.

Config file

All settings are stored in .claude/mermaid.json in the current project directory.

Default values (used when file does not exist):

json
{
  "theme": "zinc-light",
  "output_directory": "./diagrams",
  "auto_validate": true,
  "auto_render": false,
  "output_format": "svg"
}

Process

Step 1: Resolve Plugin Path

bash
PLUGIN_DIR=$(find "$HOME/.claude/plugins/cache" -type d -name "mermaid" -path "*/skills/mermaid" 2>/dev/null | head -1)

If empty:

bash
PLUGIN_DIR=$(find "$HOME" -maxdepth 8 -type d -name "mermaid" -path "*/skills/mermaid" 2>/dev/null | head -1)

Use $PLUGIN_DIR in all subsequent commands.

Step 2: Read current config

If .claude/mermaid.json exists, read it. Otherwise use defaults above.

Step 3: If argument provided

If the user passed arguments (e.g. theme dracula or auto_render true), apply directly:

  • Parse as {setting} {value}
  • For theme: accept any of the 15 beautiful-mermaid theme names or custom
  • Validate value is allowed (see options below)
  • Update .claude/mermaid.json
  • Confirm: "✅ {setting} set to {value}"
  • Done.

Step 4: If no argument — show interactive menu

Display:

Current config (.claude/mermaid.json):

  1. theme             → {current}   (zinc-light, github-dark, dracula, … 15 themes + custom)
  2. output_directory  → {current}
  3. auto_validate     → {current}   (true | false)
  4. auto_render       → {current}   (true | false)
  5. output_format     → {current}   (svg)
  6. custom theme      → configure themeVariables
  7. Run health check

What would you like to change? (enter 1-7)

Step 5: Handle selection

If 1 (theme):

Available themes (beautiful-mermaid):

  Light:
   1. zinc-light           clean, neutral light
   2. github-light         GitHub-style light
   3. catppuccin-latte     warm pastel light
   4. nord-light           arctic light palette
   5. solarized-light      Solarized light
   6. tokyo-night-light    Tokyo Night light variant

  Dark:
   7. zinc-dark            clean, neutral dark
   8. github-dark          GitHub-style dark
   9. catppuccin-mocha     warm pastel dark
  10. nord                 arctic dark palette
  11. dracula              Dracula purple
  12. solarized-dark       Solarized dark
  13. tokyo-night          Tokyo Night
  14. tokyo-night-storm    Tokyo Night Storm variant
  15. one-dark             Atom One Dark

  16. custom               define your own colors

Enter 1-16:

Update theme in .claude/mermaid.json.

If 2 (output_directory): Ask for path. Update config.

Special values:

  • "same" — save output in the same directory as the input file. Falls back to ./diagrams when there is no input file reference (e.g. text-only /mermaid-diagram calls).

If 3 (auto_validate): Toggle true/false. Update config.

If 4 (auto_render): Toggle true/false. Update config.

If 5 (output_format):

Available formats:
  1. svg   — vector, only supported format

Enter 1:

Update output_format in .claude/mermaid.json.

If 6 (custom theme): Present the current values and prompt for each variable (leave blank to keep current):

Custom theme colors (beautiful-mermaid format):

  bg      → {current or #ffffff}   background color (required)
  fg      → {current or #1a1a2e}   foreground/text color (required)
  line    → {current or #666666}   arrow and line color (optional)
  accent  → {current or #4a90d9}   accent/highlight color (optional)
  muted   → {current or #999999}   muted text color (optional)

Accept a hex color (#rrggbb) for each. Set theme to "custom" and save all entered values under themeVariables in .claude/mermaid.json.

Example saved config:

json
{
  "theme": "custom",
  "themeVariables": {
    "bg": "#1a1b26",
    "fg": "#a9b1d6",
    "line": "#565f89",
    "accent": "#7aa2f7",
    "muted": "#565f89"
  }
}

If 7 (health check): See Health Check section below.

Step 6: Write updated config

Create .claude/ directory if it doesn't exist:

bash
mkdir -p .claude

Write updated settings to .claude/mermaid.json (merge with existing, don't overwrite unrelated keys).

Confirm: "✅ Config saved to .claude/mermaid.json"


Health Check

Run when user selects option 7.

Check 1: Node.js

bash
node --version 2>&1

✅ if v18.0.0 or higher | ❌ if not found or older → "Install Node.js 18+: https://nodejs.org"

Check 2: beautiful-mermaid (local node_modules)

bash
ls "$PLUGIN_DIR/scripts/node_modules/beautiful-mermaid" 2>/dev/null && echo "found" || echo "not found"
  • ✅ if "found" → show version from $PLUGIN_DIR/scripts/node_modules/beautiful-mermaid/package.json

  • ❌ if "not found" → auto-install:

    bash
    npm install --prefix "$PLUGIN_DIR/scripts"

    Confirm: "✅ beautiful-mermaid installed"

Check 3: Render smoke test

bash
printf 'flowchart TD\n    A --> B' | node "$PLUGIN_DIR/scripts/render.js" /dev/stdin --output /tmp/mermaid-health-check.svg 2>&1

✅ if exit 0 and /tmp/mermaid-health-check.svg contains <svg | ❌ if error → show the JSON error message

Output format

Mermaid plugin — dependency check

  ✅ Node.js v22.1.0      required runtime
  ✅ beautiful-mermaid     v1.1.3 — installed
  ✅ Render smoke test     SVG generated OK

Features:
  ✅ Generate diagrams    ✅ Validate    ✅ Render SVG
  ℹ️  PNG not supported   (use SVG — works everywhere Git renders markdown)

Frequently asked questions

What does the Mermaid Config AI skill do?

Change theme, output format, or check plugin dependencies

Why use Mermaid Config on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/diegomarino/claude-toolshed/tree/main/plugins/mermaid/skills/mermaid-config. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Mermaid Config?

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 Mermaid Config?

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

Is the Mermaid Config AI skill free?

It is published on GitHub by diegomarino. Check the repository for licensing terms. 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 👇