graphviz.convert_image
SkillMediaConvert an image of a graph into a Graphviz Dot in an accurate way
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the graphviz.convert_image skill
What this skill tells your AI
The instructions your AI receives, as published by causify-ai/helpers in .claude/skills/graphviz.convert_image/SKILL.md and read by ahel’s review.
- Given the input image of a graph
Step 1: Create Graphviz
- Create a Graphviz Dot to match exactly the figure
- Save the result in
graph.dot
Step 2: Render to Image
- After the graph description is generated, generate an image with:
> dot -Tpng graph.dot -o graph.png > open graph.png
Step 3: Read the PNG File
- If the generated PNG image is different from the input image:
- Find the differences in terms of layout, e.g.,
- Check the position of the nodes
- Check the colors of the nodes are the same
- Apply changes to
graph.dotto approximate the input image, e.g.,- Use rank to keep the nodes in the same relative position
- Change the color of nodes in
graph.dotto match the input image
- Find the differences in terms of layout, e.g.,
Signals
- GitHub stars
- 145
- Forks
- 159
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
graphviz-convert-image- Source
- github.com/causify-ai/helpers