skills.rest
imMamdouhaboammar
imMamdouhaboammarCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

excalidraw

Delegate Excalidraw diagram operations to subagents for context preservation.

Updated Jul 24, 2026
Search Tags:#architecture#excalidraw#flowchart#subagent#diagrams#context-management
One-click install
npx skills add https://github.com/imMamdouhaboammar/kaku-chatgpt-harness --skill excalidraw-immamdouhaboammar
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: excalidraw
Source: https://github.com/imMamdouhaboammar/kaku-chatgpt-harness/tree/main/.agents/skills/excalidraw
Command: npx skills add https://github.com/imMamdouhaboammar/kaku-chatgpt-harness --skill excalidraw-immamdouhaboammar

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the issue of context exhaustion caused by the extreme verbosity of Excalidraw JSON files, which can consume up to 22k tokens per file and clutter the main agent's memory with irrelevant visual metadata.

Core Features & Use Cases

  • Context Preservation: Offloads heavy JSON parsing to subagents, preserving up to 97% of your main context budget.
  • Intelligent Delegation: Automatically handles diagram creation, modification, and comparison tasks through specialized subagent workflows.
  • Use Case: When you need to update an architecture diagram, this skill delegates the task to a subagent that reads the JSON, performs the edit, and returns only the necessary confirmation, keeping your main conversation clean.

Quick Start

Use the excalidraw skill to extract and explain the components in the architecture diagram file named system-design.excalidraw.json.

Frequently Asked Questions about excalidraw

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

FAQPage Schema
How do I parse Excalidraw JSON files without exhausting my main agent context window?▼

Excalidraw diagram maintenance offloads heavy JSON parsing to subagents, preserving up to 97% of your main context budget. This prevents context exhaustion caused by verbose visual metadata consuming up to 22k tokens per file.

What is the best way to update architecture diagrams stored in Excalidraw?▼

Updating architecture diagrams is handled through intelligent delegation to a subagent that reads the Excalidraw JSON, performs the edit, and returns only the confirmation, keeping your main conversation clean.

How does subagent delegation work for flowchart maintenance tasks?▼

Subagent delegation for flowchart maintenance works through isolated subagent execution that processes text labels and relationships while ignoring non-semantic visual properties, returning only necessary results to the main agent.

Can I modify Excalidraw diagrams without loading visual metadata into the main context?▼

Yes, modifying Excalidraw diagrams without loading visual metadata is possible through isolated subagent execution. The subagent processes non-semantic visual properties independently, preserving your main context budget.

Why does my agent run out of context when reading large Excalidraw files?▼

Your agent runs out of context because Excalidraw JSON files are extremely verbose, consuming up to 22k tokens per file. Offloading heavy JSON parsing to subagents prevents this context exhaustion.

Related Skills

Explore More Software Engineering Skills→
NITISH-gitbitNITISH-gitbit

excalidraw

Generate hand-drawn Excalidraw diagrams from JSON element specifications.

Community
Intermediate
stephanjstephanj
9

excalidraw

Delegate Excalidraw diagram operations to subagents to reduce context token usage.

Community
Intermediate
rafaelcallejarafaelcalleja
2

mcp-management

Coordinate MCP servers to discover, analyze and execute their capabilities without polluting the main context.

Community
Advanced
githubgithub
37.6k

excalidraw-diagram-generator

Convert natural-language diagram requests into Excalidraw-ready .excalidraw files.

Official
Intermediate