excalidraw
Audited by Runlayer on Feb 21, 2026
Malicious tool definition detected
Tool: README.md [1/2] Description: # Excalidraw Skill A Claude Code skill for efficiently working with Excalidraw diagram files through intelligent subagent delegation.
Tool: README.md [2/2] Description: what's there" - Compare multiple diagrams side-by-side - Parse JSON to "extract just the text" **STOP.
Malicious tool definition detected
Tool: SKILL.md [1/2] Description: --- name: excalidraw description: "Use when working with *.excalidraw or *.excalidraw.json files, user mentions diagrams/flowcharts, or requests architecture visualization - delegates all Excalidraw operations to subagents to prevent context exhaustion from verbose JSON (single files: 4k-22k tokens, can exceed read limits)" --- # Excalidraw Subagent Delegation ## Overview **Core principle:** Main agents NEVER read Excalidraw files directly.
Tool: SKILL.md [2/2] Description: use a subagent to extract the architecture details.