Explain Visually

SkillMedia

Render an explanation as a diagram, comparison, trace with real values, or annotated code. Use when the user asks to have a concept, decision, flow, or code explained, or says they do not follow.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Explain Visually skill

What this skill tells your AI

The instructions your AI receives, as published by toy-crane/claude-code-playbook-template in .agents/skills/explain-visually/SKILL.md and read by ahel’s review.

Render the subject when a visual explanation is needed.

First decide whether one sentence fully answers the question. Rendering costs the user's time, so when one sentence is enough, write it and stop.

Otherwise choose a form suited to the question: a diagram for structure, a table for comparison, a trace with real numbers for a mechanism, or annotated code.

Check the available tools and use the best renderer the session provides. Use text in the reply only when nothing in the session can draw.

Signals

GitHub stars
60
Forks
8
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
explain-visually-toy-crane
Source
github.com/toy-crane/claude-code-playbook-template