🤖
AI EngineeringPython

Excalidraw

by softaworks

Excalidraw is an AI Engineering skill for Claude Code, published by softaworks in agent-toolkit.

2.4K stars219 forkson softaworks/agent-toolkitAdded 2026/08/18+1% in starsRepository updated 2026/03/05
agent-skillsaiautomationclaudeclaude-codecoding-agentdevelopment
Install in seconds
Install Excalidraw
Copy Excalidraw into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/softaworks/agent-toolkit/tree/main/skills/excalidraw ~/.claude/skills/excalidraw

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/softaworks/agent-toolkit.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/excalidraw/SKILL.md in softaworks/agent-toolkit
Installs to
~/.claude/skills/excalidraw
Collection
One of 25 skills cataloged from this repository
Category
AI Engineering2451 skills

What Excalidraw does

Excalidraw delegates all operations on .excalidraw files to subagents so the main agent never reads verbose diagram JSON directly, preventing context exhaustion. Use it whenever a diagram needs to be read, created, modified, or compared.

Excalidraw is cataloged under AI Engineering on DirSkills. Excalidraw comes from a repository tagged agent-skills, ai, automation, claude and claude-code.

Documentation

README

Excalidraw Subagent Delegation

Overview

Core principle: Main agents NEVER read Excalidraw files directly. Always delegate to subagents to isolate context consumption.

Excalidraw files are JSON with high token cost but low information density. Single files range from 4k-22k tokens (largest can exceed read tool limits). Reading multiple diagrams quickly exhausts context budget (7 files = 67k tokens = 33% of budget).

The Problem

Excalidraw JSON structure:

  • Each shape has 20+ properties (x, y, width, height, strokeColor, seed, version, etc.)
  • Most properties are visual metadata (positioning, styling, roughness)
  • Actual content: text labels and element relationships (<10% of file)
  • Signal-to-noise ratio is extremely low

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Excalidraw

  • What else does softaworks publish alongside Excalidraw?

    Excalidraw is one of 25 skills that DirSkills catalogs from softaworks/agent-toolkit, the repository it ships in. Its siblings there include 10x Mode, Add Skill and Agent MD Refactor. Each one is a separate skill with its own page in this directory, installs the same way Excalidraw does, and is maintained by softaworks in that same repository. The rest of the collection is listed on the softaworks/agent-toolkit page.

  • How does Excalidraw compare to other AI Engineering skills?

    Excalidraw ranks #821 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Excalidraw against them. Open each page to compare what they document and how they install.

More from softaworks/agent-toolkit

Excalidraw is one of 25 skills cataloged on DirSkills from softaworks/agent-toolkit.

See all 25 skills
🚀
2w ago

10x Mode

10x Mode finds 10x product opportunities and high-leverage improvements. Use it when you need strategic product thinking, want to find high-impact features, or ask what would make a product 10x better.
AI Engineering
2.4K219
📥
2w ago

Add Skill

Add Skill copies a skill directory into an agent project. It verifies naming consistency, generates a README if missing, and adds a plugin entry to marketplace.json.
Automation
2.4K219
🗂️
2w ago

Agent MD Refactor

Agent MD Refactor restructures bloated agent instruction files like AGENTS.md and CLAUDE.md into concise root files with linked, categorized docs. Use it when an AI coding agent's instructions have grown too long, redundant, or contradictory.
AI Engineering
2.4K219
📄
2w ago

Backend to Frontend Handoff Docs

Backend to Frontend Handoff Docs produces a structured API handoff document for frontend developers when backend work is complete. Use it to document endpoints, DTOs, validation rules, business logic, and integration notes without backend Q&A.
Writing
2.4K219
🏗️
2w ago

C4 Architecture

C4 Architecture generates C4 model diagrams in Mermaid syntax for documenting software architecture at context, container, component, and deployment levels. Use it when you need to visualize system structure or communicate architecture to technical and non-technical audiences.
Writing
2.4K219
🤖
2w ago

Codex

Codex runs OpenAI Codex CLI for code analysis, refactoring, and automated editing, defaulting to GPT-5.2. Use it when a user asks to run codex exec or resume a Codex session.
AI Engineering
2.4K219