🎨
AI EngineeringPython

Oil Visual

by oil-oil

Oil Visual is an AI Engineering skill for Claude Code, published by oil-oil in oil-visual.

66 stars13 forkson oil-oil/oil-visualAdded 2026/08/11+6% in starsRepository updated 2026/07/20
agent-skillscodeximage-generationvisual-explainer
Install in seconds
Install Oil Visual
Copy Oil Visual into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/oil-oil/oil-visual ~/.claude/skills/oil-visual

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/oil-oil/oil-visual.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
SKILL.md in oil-oil/oil-visual
Installs to
~/.claude/skills/oil-visual
Collection
The only skill cataloged from this repository
Category
AI Engineering2451 skills

What Oil Visual does

Create consistent manga-ink illustrations in two modes: explanatory images with embedded labels, or transparent character scenes for layouts. Ideal for explaining concepts, workflows, comparisons, and hero artwork.

Oil Visual is cataloged under AI Engineering on DirSkills. Oil Visual comes from a repository tagged agent-skills, codex, image-generation and visual-explainer.

Documentation

README

oil-visual 是一套给 Codex 使用的配图规范。它把角色、线条、网点、颜色、场景和图片文字统一在一套规则里,让不同主题的图保持同一种视觉语言。

适合用来画概念解释、机制流程、对比关系和角色场景。

配图风格

  • 用粗细分明的黑色墨线画轮廓和细节。
  • 用圆形半调网点表现灰面和阴影,不使用柔和渐变。
  • 主角是戴圆框眼镜的极简小人,旁边保留一只胖胖的暖黄色边牧。
  • 场景使用米白色纸张质感,只保留少量真正帮助理解的环境物件。
  • 暖黄色是固定颜色;每张图最多再使用两种语义色。
  • 图片需要文字时,使用短而准确的无衬线标签,并直接放在对应物体上。

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Oil Visual

  • How does Oil Visual compare to other AI Engineering skills?

    Oil Visual ranks #2271 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Oil Visual against them. Open each page to compare what they document and how they install.