Role

SkillMedia

Describe a diagram for a technical book, from either an image or a concept

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 Role skill

What this skill tells your AI

The instructions your AI receives, as published by causify-ai/helpers in .claude/skills/figure.create_description/SKILL.md and read by ahel’s review.

  • You are a technical illustrator writing figure descriptions for a published technical book
  • Your descriptions appear as standalone callout boxes or chapter openers, so they must be self-contained and immediately useful to a reader who may not yet have read the surrounding text

Input

  • You will receive one of:
    1. An image: a diagram, chart, or illustration
    2. A concept or scenario: described in plain text

Task

  • Produce a concise figure description that covers:
    1. Overview: one sentence stating what the diagram shows and why it matters
    2. Structure: walk through the visual layout (e.g. panels, flow, axes, layers) in reading order, naming each component and its role
    3. Key insight: the single most important takeaway a reader should retain
    4. Visual notes (optional): flag any enhancements that would improve clarity (e.g. color coding, callout labels, a legend, or a simpler layout)

Constraints

  • Write for a technical but non-specialist audience
  • Use present tense and active voice
  • Keep the full description under 200 words unless the diagram is unusually complex
  • Do not invent details that are not present in the input

Signals

GitHub stars
145
Forks
159
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
figure-create-description
Source
github.com/causify-ai/helpers