oil-visual skill
A skill that draws explainer diagrams and transparent illustrations in a comic-ink style with bold outlines and halftone dots.
- 106 ★ on the repository
- Last commit
- MIT
Minimal access
Why this level
- The skill only sets style and working order and runs nothing itself
- The request text goes to the connected image-generation model
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/oil-visualDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skill only sets style and working order and runs nothing itself
- The request text goes to the connected image-generation model
This is third-party code. Review the repository files before installing.
What it does
oil-visual draws pictures in one comic-ink manner: bold black lines, round halftone dots instead of gradients, an aged-paper background. The skill produces two kinds of material: full explainer diagrams with short labels and transparent inserts for slides, articles and cards. A stick figure in round glasses and a warm yellow border collie may appear, together or alone. A folder, a tool or another object is drawn in the same manner without characters. Colours are tightly limited: yellow plus at most two semantic shades per picture. Labels are short, sans-serif and placed directly on objects. The repository examples show task flows, cost comparisons, feedback loops and pipeline bottlenecks.
Who it is for. Article authors, speakers and product teams who need diagrams and illustrations in one consistent style without drawing by hand.
Good fit when
- An article needs a diagram that explains a mechanism without a long caption.
- A deck needs transparent illustrations, such as a magnifier over folders or scissors over papers.
- A blog image series should look drawn by one hand.
- A cost comparison or feedback loop is shown in one picture with short labels.
- Cards and slides need cutout inserts without a background.
Not a fit when
- You need photorealistic or 3D imagery: the style is strictly flat comic ink.
- A brand style with an arbitrary palette is required rather than the fixed colour scheme.
- The agent has no image-generation model connected: the skill draws nothing by itself.
Example request
Use oil-visual to draw how a main agent assigns work to subagents and accepts the result, with short labels.Limitations
The skill holds style rules and a working order, while an image-generation model connected to the agent draws the pictures. Without one there is no output. The README and examples are in Chinese and labels on finished diagrams are Chinese, so Russian labels must be requested directly. The style is fixed: the stick figure with glasses and the dog are meant as permanent characters, and a different palette means rewriting the rules yourself. The repository was last updated on 25 September 2026 and uses the MIT licence.
How to disable. Delete the `oil-visual` folder from the agent skills directory. Finished pictures are stored separately and stay in place.
FAQ
What pictures does the skill make?
Two kinds: finished explainer diagrams with short labels and transparent illustrations for decks and articles.
Must the figure and the dog be drawn?
No. Characters appear when needed, and objects such as a folder or scissors are drawn in the same style without them.
How is the skill installed?
With `npx skills add oil-oil/oil-visual` or by asking the agent to install the skill from the repository address, then reloading the agent.
How many colours does the style use?
Warm yellow plus at most two semantic colours per image; grey areas are rendered with dots.
Can labels be in Russian?
The rules assume short labels in any language, but the examples are Chinese, so state the label language in the request.
Discussion
No questions or reviews yet.
Related
SkillsA Codex skill that redraws your photo as a watercolor illustration on white paper, with wide margins and a handwritten caption
A skill that draws original print-style illustrations: one idea per frame, played out by a recurring mascot
A skill that turns Chinese story copy or a set of ordered images into a vertical hand-drawn animation, a silent diary-comic picture track
A skill that generates one-ink and two-ink editorial posters: paper substrate, halftone, negative space and restrained type
A skill that draws interactive isometric illustrations in SVG, with WebGL shaders and React output, explaining an idea as a working machine
A skill that paints pictures with Python code and no image model: 77 styles from ink wash to cyberpunk, with reproducible results.
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| oil-visual (this card) | no | 106 | |
| Guizang Material Illustration | no | 1,257 | makes material-style illustrations for an article header; here a single comic manner with ink and dots |
| Ian Xiaohei Illustrations | no | 13,183 | turns an article into a 16:9 drawing series with one character; here diagrams and transparent inserts in comic style |
README in short
The README shows five finished explainer diagrams and two transparent elements, with sample requests in English and Chinese.