Drawbridge logo

Drawbridge

Community
alexknowshtml
drawbridge

Generate Excalidraw diagrams with a hand-drawn aesthetic using Drawbridge. Use when user asks for: flowcharts, dependency diagrams, project visualization, task maps, or "make a diagram of this". Pushes elements to a live Excalidraw canvas via HTTP API, or renders to PNG/SVG.

Overview

Publisheralexknowshtml
Repositorydrawbridge
Skill namedrawbridge
Stars
73
Forks
3
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 alexknowshtml on GitHub. Read the source before you install it.

Installation

Install the Drawbridge 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/alexknowshtml/drawbridge/tree/main/skills
  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/alexknowshtml/drawbridge.git /tmp/drawbridge
mkdir -p .claude/skills
cp -r /tmp/drawbridge/skills .claude/skills/drawbridge
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Drawbridge 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 Drawbridge 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 Drawbridge 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.

Drawbridge Diagram Skill

Generate hand-drawn style diagrams as Excalidraw JSON. Uses the simplified element format with convertToExcalidrawElements handling all the heavy lifting (text measurement, container binding, arrow routing).

Element Format (Simplified)

Only specify what matters. convertToExcalidrawElements fills in all required internal properties (groupIds, frameId, seeds, versions, etc.).

Required Fields (all elements)

type, id (unique string), x, y

Defaults (skip these)

strokeColor="#1e1e1e", backgroundColor="transparent", fillStyle="solid", strokeWidth=2, roughness=1, opacity=100

Labeled Shapes (PREFERRED)

Add label to any shape for auto-centered text. No separate text elements needed:

json
{ "type": "rectangle", "id": "r1", "x": 100, "y": 100, "width": 200, "height": 80,
  "roundness": { "type": 3 }, "backgroundColor": "#a5d8ff", "fillStyle": "solid",
  "label": { "text": "API Server", "fontSize": 20 } }
  • Works on rectangle, ellipse, diamond
  • Text auto-centers and container auto-resizes to fit
  • Always include "roundness": { "type": 3 } for rounded corners

Standalone Text (titles, annotations only)

json
{ "type": "text", "id": "t1", "x": 150, "y": 50, "text": "System Architecture", "fontSize": 28 }
  • x is the LEFT edge of the text
  • To center text at position cx: x = cx - (text.length * fontSize * 0.5) / 2
  • textAlign does NOT control horizontal position — it only affects multi-line wrapping

Arrows

json
{ "type": "arrow", "id": "a1", "x": 300, "y": 150, "width": 200, "height": 0,
  "points": [[0,0],[200,0]], "endArrowhead": "arrow" }
  • points: [dx, dy] offsets from element x,y
  • endArrowhead: null | "arrow" | "bar" | "dot" | "triangle"

Arrow Labels

Annotate arrows with text:

json
{ "type": "arrow", "id": "a1", "x": 300, "y": 150, "width": 200, "height": 0,
  "points": [[0,0],[200,0]], "endArrowhead": "arrow",
  "label": { "text": "API call", "fontSize": 16 } }

Arrow Bindings

Bind arrows to shapes so they stay connected when shapes are moved. Use start and end with the target element's id:

json
{
  "type": "arrow", "id": "a1", "x": 300, "y": 150, "width": 200, "height": 0,
  "points": [[0,0],[200,0]], "endArrowhead": "arrow",
  "start": { "id": "box1" },
  "end": { "id": "box2" }
}

IMPORTANT: Use start/end (skeleton format), NOT startBinding/endBinding (internal format). convertToExcalidrawElements resolves the bindings automatically, including setting up boundElements on the target shapes.

The binding point is calculated from the arrow's position relative to the shape. Position the arrow's x,y to start at the right edge of the source shape for a left-to-right connection.

Background Zones

Group related elements with low-opacity rectangles:

json
{ "type": "rectangle", "id": "zone1", "x": 80, "y": 80, "width": 540, "height": 400,
  "backgroundColor": "#d3f9d8", "fillStyle": "solid", "roundness": { "type": 3 },
  "strokeColor": "#22c55e", "strokeWidth": 1, "opacity": 35 }

Add a zone label as standalone text:

json
{ "type": "text", "id": "zone1-label", "x": 100, "y": 86, "text": "Frontend Layer",
  "fontSize": 16, "strokeColor": "#15803d" }

Color Palette

Primary Colors (strokes, text)

NameHexUse
Blue#4a9eedPrimary actions, links
Amber#f59e0bWarnings, highlights
Green#22c55eSuccess, positive
Red#ef4444Errors, negative
Purple#8b5cf6Accents, special
Cyan#06b6d4Info, secondary

Fills (pastel, for shape backgrounds)

ColorHexUse
Light Blue#a5d8ffInput, sources, primary
Light Green#b2f2bbSuccess, output, completed
Light Orange#ffd8a8Warning, pending, external
Light Purple#d0bfffProcessing, middleware
Light Red#ffc9c9Error, critical, alerts
Light Yellow#fff3bfNotes, decisions, planning
Light Teal#c3fae8Storage, data, memory

Background Zones (use with opacity: 30-35)

ColorHexUse
Blue zone#dbe4ffUI / frontend layer
Purple zone#e5dbffLogic / agent layer
Green zone#d3f9d8Data / tool layer

Sizing Rules

Font Sizes

  • Minimum 16 for body text, labels, descriptions
  • Minimum 20 for titles and headings
  • Minimum 14 for secondary annotations only (sparingly)
  • NEVER use fontSize below 14

Element Sizes

  • Minimum 120x60 for labeled rectangles/ellipses
  • 20-30px gaps between elements minimum
  • Prefer fewer, larger elements over many tiny ones

Drawing Order (CRITICAL)

Array order = z-order (first = back, last = front).

Emit progressively: background zone → shape → its arrows → next shape

  • GOOD: zone → box1 → arrow1 → box2 → arrow2 → box3
  • BAD: box1 → box2 → box3 → arrow1 → arrow2

This matters for streaming to the live viewer where elements appear one at a time.

Complete Examples

Two Connected Labeled Boxes

json
[
  { "type": "rectangle", "id": "b1", "x": 100, "y": 100, "width": 200, "height": 100,
    "roundness": { "type": 3 }, "backgroundColor": "#a5d8ff", "fillStyle": "solid",
    "label": { "text": "Start", "fontSize": 20 } },
  { "type": "arrow", "id": "a1", "x": 300, "y": 150, "width": 150, "height": 0,
    "points": [[0,0],[150,0]], "endArrowhead": "arrow",
    "start": { "id": "b1" },
    "end": { "id": "b2" } },
  { "type": "rectangle", "id": "b2", "x": 450, "y": 100, "width": 200, "height": 100,
    "roundness": { "type": 3 }, "backgroundColor": "#b2f2bb", "fillStyle": "solid",
    "label": { "text": "End", "fontSize": 20 } }
]

System Architecture with Zones

json
[
  { "type": "text", "id": "title", "x": 200, "y": 10, "text": "System Architecture", "fontSize": 28 },
  { "type": "rectangle", "id": "zone-fe", "x": 80, "y": 60, "width": 300, "height": 200,
    "backgroundColor": "#dbe4ff", "fillStyle": "solid", "roundness": { "type": 3 },
    "strokeColor": "#4a9eed", "strokeWidth": 1, "opacity": 35 },
  { "type": "text", "id": "zone-fe-label", "x": 100, "y": 66, "text": "Frontend",
    "fontSize": 16, "strokeColor": "#1971c2" },
  { "type": "rectangle", "id": "app", "x": 120, "y": 100, "width": 200, "height": 80,
    "roundness": { "type": 3 }, "backgroundColor": "#a5d8ff", "fillStyle": "solid",
    "label": { "text": "React App", "fontSize": 20 } },
  { "type": "arrow", "id": "a1", "x": 320, "y": 140, "width": 150, "height": 0,
    "points": [[0,0],[150,0]], "endArrowhead": "arrow",
    "label": { "text": "REST API", "fontSize": 14 } },
  { "type": "rectangle", "id": "api", "x": 470, "y": 100, "width": 200, "height": 80,
    "roundness": { "type": 3 }, "backgroundColor": "#d0bfff", "fillStyle": "solid",
    "label": { "text": "API Server", "fontSize": 20 } }
]

Output Options

1. Push to Excalidraw Live (real-time)

Push elements to the live viewer via HTTP API:

bash
curl -s -X POST http://localhost:3062/api/session/SESSION_NAME/elements \
  -H "Content-Type: application/json" \
  -d '{"elements": [...]}'

Live viewer URL: http://localhost:3060/#SESSION_NAME (or your configured host)

API endpoints:

  • POST /api/session/:id/elements — Replace all elements
  • POST /api/session/:id/append — Add elements to existing
  • POST /api/session/:id/clear — Clear canvas
  • POST /api/session/:id/undo — Undo last operation
  • GET /api/session/:id — Get current elements

2. Save as .excalidraw file

Wrap elements in the document structure:

json
{
  "type": "excalidraw",
  "version": 2,
  "source": "https://excalidraw.com",
  "elements": [ /* your elements array */ ],
  "appState": { "viewBackgroundColor": "#ffffff", "gridSize": null },
  "files": {}
}

3. Render to SVG or PNG

bash
# From .excalidraw file (skeleton or resolved elements both work)
npx tsx scripts/render.ts input.excalidraw output.png
npx tsx scripts/render.ts input.excalidraw output.svg

# From a live session
curl -s http://localhost:3062/api/session/SESSION_NAME | \
  python3 -c "import json,sys; d=json.load(sys.stdin); json.dump({'type':'excalidraw','version':2,'source':'https://excalidraw.com','elements':d['elements'],'appState':{'viewBackgroundColor':'#ffffff','gridSize':None},'files':{}}, open('/tmp/diagram.excalidraw','w'))"
npx tsx scripts/render.ts /tmp/diagram.excalidraw /tmp/diagram.png

Uses headless Chromium + Excalidraw 0.18. Handles skeleton elements (with label, start/end) automatically via convertToExcalidrawElements. Takes ~5-8 seconds.

Generation Workflow

  1. Plan layout — Decide zones, flow direction, element grouping
  2. Generate elements — Follow progressive drawing order
  3. Push to live viewer — For real-time review with user
  4. Render to PNG/SVG — For embedding in docs, reports, or sharing

Frequently asked questions

What does the Drawbridge AI skill do?

Generate Excalidraw diagrams with a hand-drawn aesthetic using Drawbridge. Use when user asks for: flowcharts, dependency diagrams, project visualization, task maps, or "make a diagram of this". Pushes elements to a live Excalidraw canvas via HTTP API, or renders to PNG/SVG.

Why use Drawbridge on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/alexknowshtml/drawbridge/tree/main/skills. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Drawbridge?

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 Drawbridge?

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

Is the Drawbridge AI skill free?

It is published on GitHub by alexknowshtml. 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 👇