Excalidraw Skill Pack
isatimur/excalidraw-skill-pack
Diagramas que argumentam, não caixas que rotulam
Ver no GitHubMCP server que habilita agentes de IA a gerar diagramas de alta qualidade no Excalidraw com uma metodologia opinionada focada em clareza visual e argumentação didática. Integra-se nativamente com Claude Code, Cursor, Codex, Gemini CLI e qualquer cliente MCP compatível, oferecendo múltiplos temas profissionais e um renderer agnóstico.
Instalação
npx convez-ai isatimur/excalidraw-skill-pack1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Gerar diagramas arquiteturais e fluxogramas de negócio com agentes IA
- Documentação técnica visual automatizada para projetos e APIs
- Criação de materiais educacionais e apresentações visuais programáticas
Veredito

Ferramental maduro e bem fundamentado que eleva a qualidade visual de diagramas gerados por IA através de metodologia e temas profissionais. Adequado para equipes que precisam produzir documentação visual de alto padrão sem intervenção manual.
README
A tradução para o português deste README ainda está na fila.
Install
| For | Command |
|---|---|
| Claude Code | npx @excalidraw-skill-pack/install claude-code |
| Cursor | npx @excalidraw-skill-pack/install cursor |
| GitHub Copilot | npx @excalidraw-skill-pack/install copilot |
| Codex | npx @excalidraw-skill-pack/install codex |
| Gemini CLI | npx @excalidraw-skill-pack/install gemini-cli |
| Any MCP agent | npx @excalidraw-skill-pack/mcp-server |
| Renderer only (Node) | npx @excalidraw-skill-pack/render diagram.excalidraw --theme stripe-press |
| Renderer only (Python) | pipx install excalidraw-skill-pack-render && excalidraw-render diagram.excalidraw --theme stripe-press |
Why this, not just another Excalidraw MCP?
Excalidraw's official MCP and most community servers solve plumbing: get an agent to emit valid JSON and render it. They produce correct boxes-and-arrows.
This pack solves taste: an opinionated methodology — the isomorphism test, evidence artifacts, multi-zoom architecture, container discipline, one-accent-per-diagram — that decides what to draw and why, so the output is a visual argument that teaches instead of a labeled grid. That's the part a weekend of MCP code can't copy, and it's why the book gallery looks the way it does.
Plumbing is a commodity now. Quality isn't.
Themes
Five themes ship in v0.1. Authoring a new theme is 20 lines of JSON + npm publish:
npx @excalidraw-skill-pack/create-theme my-brand
cd theme-my-brand && npm publish --access public
Published packages (v0.1)
| Channel | Package | Purpose |
|---|---|---|
| npm | @excalidraw-skill-pack/core | Methodology + bundled default-sketchy theme + schemas |
| npm | @excalidraw-skill-pack/render | Node renderer (excalidraw-render CLI) |
| npm | @excalidraw-skill-pack/mcp-server | stdio MCP server with 5 tools |
| npm | @excalidraw-skill-pack/install | One-command adapter installer |
| npm | @excalidraw-skill-pack/create-theme | Scaffolder for new theme packages |
| npm | @excalidraw-skill-pack/theme-stripe-press | Editorial / book-grade |
| npm | @excalidraw-skill-pack/theme-notion | Rounded, off-white |
| npm | @excalidraw-skill-pack/theme-whiteboard | Low-fi, bright, sketchy |
| npm | @excalidraw-skill-pack/theme-dark | Inverted contrast |
| PyPI | excalidraw-skill-pack-render | Python renderer (excalidraw-render CLI) |
Proof
This skill drew 77 diagrams for the published technical book From Copilot to Colleague — argument spines, chapter openers, concept figures, and inline explainers, all from the methodology in this repo. No other Excalidraw generator can point at a corpus like that. A curated set — the book's argument spine plus all ten chapter openers — ships as source .excalidraw files in examples/book; the full 77 are live across fromcopilottocolleague.com.
Methodology
Diagrams are arguments. The shape should BE the meaning.
- Isomorphism Test: would the structure alone communicate the concept?
- Evidence artifacts: real code snippets, actual API names, concrete formats — not placeholder text.
- One accent per diagram. Two means a competing argument; split it.
Read the full methodology (it's also what the AI agent reads).
License
MIT. Contributions welcome — see CONTRIBUTING.md.