excalidraw

Delegate Excalidraw file processing to subagents for concise text-only summaries.

Updated Mar 8, 2026
One-click install
npx skills add https://github.com/ZiadNagar/zeVillage-AI-Toolkit --skill excalidraw-ziadnagar
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: excalidraw
Source: https://github.com/ZiadNagar/zeVillage-AI-Toolkit/tree/main/skills/excalidraw
Command: npx skills add https://github.com/ZiadNagar/zeVillage-AI-Toolkit --skill excalidraw-ziadnagar

SYSTEM DOCUMENTATION & REQUIREMENTS

## What problem does it solve? Excalidraw files are extremely verbose and token-costly, making main-agent processing risky; delegating to subagents reduces context usage and keeps conversations efficient.

## Core Features & Use Cases

  • Delegate Excalidraw operations (read/explain/modify/create) to subagents for text-only summaries.
  • Handle large diagrams by isolating JSON processing and returning concise outputs.
  • Use cases include architecture diagrams, flowcharts, and architecture visualization tasks.

### Quick Start Provide the Excalidraw file you want analyzed and I will delegate its processing to a subagent for a concise, text-only summary.

Frequently Asked Questions about excalidraw

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I prevent context overflow when processing Excalidraw JSON files?

Delegating Excalidraw JSON processing to subagents prevents context overflow by isolating verbose JSON data and returning concise, text-only summaries to the main agent.

Why do Excalidraw diagrams consume so many tokens?

Excalidraw diagrams consume many tokens because their JSON format is extremely verbose. Delegating this JSON processing to subagents reduces context usage and keeps conversations efficient.

Can I use subagents to modify architecture diagrams without loading the full JSON?

Yes, you can delegate architecture diagram modifications to subagents. The subagent handles the heavy Excalidraw JSON manipulation and returns a brief, text-only summary of the changes to your main context.

What is the best way to visualize flowcharts without hitting token limits?

The best way to visualize flowcharts without hitting token limits is delegating Excalidraw visualization tasks to subagents. This pattern processes large diagrams and outputs concise text summaries.

Does this approach return the raw Excalidraw JSON to the main conversation?

No, this approach does not return raw Excalidraw JSON to the main conversation. It isolates JSON processing within subagents and returns only concise, text-only summaries of diagrams and architecture visuals.

When should I delegate Excalidraw tasks instead of processing them directly?

You should delegate Excalidraw tasks when working with files ending in .excalidraw or .excalidraw.json and when users request architecture visuals. This avoids context overflow from verbose, token-costly files.