Agent Skills

beautiful-mermaid

Render Mermaid diagrams as SVG and PNG using the Beautiful Mermaid library. Use when the user asks to render a Mermaid diagram.

Install

npx skills add https://github.com/intellectronica/agent-skills --skill beautiful-mermaid
SKILL.md

Beautiful Mermaid Diagram Rendering

Render Mermaid diagrams as SVG and PNG images using the Beautiful Mermaid library.

Dependencies

This skill requires the agent-browser skill for PNG rendering. Load it before proceeding with PNG capture.

Supported Diagram Types

  • Flowchart - Process flows, decision trees, CI/CD pipelines
  • Sequence - API calls, OAuth flows, database transactions
  • State - State machines, connection lifecycles
  • Class - UML class diagrams, design patterns
  • Entity-Relationship - Database schemas, data models

Available Themes

Default, Dracula, Solarized, Zinc Dark, Tokyo Night, Tokyo Night Storm, Tokyo Night Light, Catppuccin Latte, Nord, Nord Light, GitHub Dark, GitHub Light, One Dark.

If no theme is specified, use default.

Common Syntax Patterns

Flowchart Edge Labels

Use pipe syntax for edge labels:

A -->|label| B
A ---|label| B

Avoid space-dash syntax which can cause incomplete renders:

A -- label --> B   # May cause issues

Node Labels with Special Characters

Wrap labels containing special characters in quotes:

A["Label with (parens)"]
B["Label with / slash"]

Workflow

Step 1: Generate or Validate Mermaid Code

If the user provides a description rather than code, generate valid Mermaid syntax. Consult references/mermaid-syntax.md for full syntax details.

Step 2: Render SVG

Run the rendering script to produce an SVG file:

bun run scripts/render.ts --code "graph TD; A-->B" --output diagram --theme default

Or from a file:

bun run scripts/render.ts --input diagram.mmd --output diagram --theme tokyo-night

Alternative runtimes:

npx tsx scripts/render.ts --code "..." --output diagram
deno run --allow-read --allow-write --allow-net scripts/render.ts --code "..." --output diagram

This produces <output>.svg in the current working directory.

Step 3: Create HTML Wrapper

Run the HTML wrapper script to prepare for screenshot:

bun run scripts/create-html.ts --svg diagram.svg --output diagram.html

This creates a minimal HTML file that displays the SVG with proper padding and background.

Step 4: Capture High-Resolution PNG with agent-browser

Use the agent-browser CLI to capture a high-quality screenshot. Refer to the agent-browser skill for full CLI documentation.

# Set 4K viewport for high-resolution capture
agent-browser set viewport 3840 2160

# Open the HTML wrapper
agent-browser open "file://$(pwd)/diagram.html"

# Wait for render to complete
agent-browser wait 1000

# Capture full-page screenshot
agent-browser screenshot --full diagram.png

# Close browser
agent-browser close

For even higher resolution on complex diagrams, increase the viewport further or use the --padding option when creating the HTML wrapper to give the diagram more space.

Step 5: Clean Up Intermediary Files

After rendering, remove all intermediary files. Only the final .svg and .png should remain.

Files to clean up:

  • The HTML wrapper file (e.g., diagram.html)
  • Any temporary .mmd files created to hold diagram code
  • Any other files created during the rendering process
rm diagram.html

If a temporary .mmd file was created, remove it as well.

Output

Both outputs are always produced:

  • SVG: Vector format, infinitely scalable, small file size
  • PNG: High-resolution raster, captured at 4K (3840×2160) viewport with minimum 1200px diagram width

Files are saved to the current working directory unless the user explicitly specifies a different path.

Theme Selection Guide

Theme Background Best For
default Light grey General use
dracula Dark purple Dark mode preference
tokyo-night Dark blue Modern dark aesthetic
tokyo-night-storm Darker blue Higher contrast
nord Dark arctic Muted, calm visuals
nord-light Light arctic Light mode with soft tones
github-dark GitHub dark Matches GitHub UI
github-light GitHub light Matches GitHub UI
catppuccin-latte Warm light Soft pastel aesthetic
solarized Tan/cream Solarized colour scheme
one-dark Atom dark Atom editor aesthetic
zinc-dark Neutral dark Minimal, no colour bias

Troubleshooting

Theme not applied

Check the render script output for the bg and fg values, or inspect the SVG's opening tag for --bg and --fg CSS custom properties.

Diagram appears cut off or incomplete

  • Check edge label syntax — use -->|label| pipe notation, not -- label -->
  • Verify all node IDs are unique
  • Check for unclosed brackets in node labels

Render produces empty or malformed SVG

  • Validate Mermaid syntax at https://mermaid.live before rendering
  • Check for special characters that need escaping (wrap in quotes)
  • Ensure flowchart direction is specified (graph TD, graph LR, etc.)

Related skills

ai-image-generationgenmedia-labs713KGenerate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model catalog: FLUX 2 (Klein 9B/4B, Pro, Dev, Flash, Turbo, Max), Google Nano Banana 2 / Pro, OpenAI GPT Image 2, ByteDance Seedream 5 / 4-5 / 4-0 and Dreamina 4-0, Alibaba Qwen Image and Z-Image Turbo, Wan 2-7. Covers both text-to-image (t2i) and image-to-image / edit (i2i) endpoints — the skill picks the right model for the user's actual intent (typography precision, photoreal portraits, sub-secoai-image-generation101-skills547KGenerate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stnano-banana-2prime-skills424KGenerate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Nano Banana 2's strengths (rapid iteration, in-image typography rendering, predictable framing, optional web-grounded context), the resolution-tier pricing, the safety-tolerance dial, and when to route to Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream insteimage-editprime-skills424KEdit images on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Nano Banana Edit (batch up to 20, identity-preserving default), OpenAI GPT Image 2 Edit (multilingual in-image text rewrite, multi-ref composition, layout precision), Flux Kontext Pro (single-ref high-fidelity local edit), or Z-Image Turbo Inpaint (mask-driven precise region edit). Bundles each model's documented prompting patterns so the skill gets sharper

Search skills and MCP servers

Fuzzy search across 23,137 skills and servers