Smart Illustrator skill
Skill that finds illustration spots in an article and generates images, diagrams and covers with three engines
- 573 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Runs local scripts and calls the Gemini API
- Image generation is billed per use
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/smart-illustratorDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Runs local scripts and calls the Gemini API
- Image generation is billed per use
This is third-party code. Review the repository files before installing.
What it does
This Claude Code skill analyzes an article's structure, finds good spots for illustrations and creates images for the content. It picks one of three engines by material type: Gemini for expressive visuals, Excalidraw for hand-drawn diagrams and Mermaid for structured diagrams, all output as PNG. There are modes for articles, slides and covers with presets for YouTube, WeChat, Twitter and other platforms. A prompt-only flag returns just the prompts without calling the paid API. Style comes from files in the styles folder, and the palette can be swapped for your own.
Who it is for. For newsletter writers, bloggers and SMM specialists who need illustrations and covers for their content.
Good fit when
- You need to illustrate an article according to its structure
- You need a cover or thumbnail for a platform
- You need infographics for a set of slides
Not a fit when
- No access to the Gemini API or you do not want paid generation
- You need a stable production tool, not an experimental prototype
- Bun, Mermaid CLI or Playwright are not installed
Example request
/smart-illustrator article.md, add illustrations that match the article structure in the light styleLimitations
The author marks the project as an experimental prototype; quality depends on the model version and input structure. Expressive images need a Gemini API key and generation is billed. It also needs Bun and the Mermaid CLI, and Excalidraw additionally needs Playwright. Part of the documentation is in Chinese, while the command interface is in English.
How to disable. Remove the smart-illustrator folder from ~/.claude/skills.
FAQ
How is the engine chosen?
Automatically by content type: metaphor and emotion go to Gemini, simple concepts and comparisons to Excalidraw, complex structures and architectures to Mermaid. You can set the engine manually with the engine flag.
Can I skip paying for the API?
Yes, the prompt-only flag returns just the prompts as JSON, which you can run in Gemini by hand or use later.
Discussion
No questions or reviews yet.
Related
SkillsNine curated skills for content and integrations: Xiaohongshu, video storyboards, Orchard, Chatwoot and copyright filings.
A skill set for Instagram: from finding a viral format and writing a script to the caption, posting calendar and comment replies
A skill that turns text or a link into a magazine-style info card and shoots a PNG with Playwright, splitting tall ones into parts
xiaohu-ip-studio: article illustrations with a fixed character
xiaohu-ip-studio
A skill that illustrates Chinese articles: it decides which sections need a picture and draws them with a recurring character
A de-AI writing skill: it repairs the narrative architecture of fiction and edits professional documents by their venue rules
The skill lays an article or case out as a 3:4 Xiaohongshu carousel from 20 templates: storyboard first, then PNG and HTML.
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| Smart Illustrator (this card) | no | 573 | |
| xiaohu-ip-studio: article illustrations with a fixed character | no | 306 | a skill that illustrates Chinese articles |
| illo: mascot illustrations for articles | no | 424 | a skill that draws original print-style illustrations |
README in short
The README describes a Claude Code skill for smart illustration placement with a three-engine system: Gemini, Excalidraw and Mermaid. There are article, slides and cover modes, platform presets, illustration-spot detection and customizable styles. Installation is cloning into the skills folder, invoked with a slash command. The project is marked experimental and image generation needs a Gemini key. MIT licensed.
README badge
Original SKILL.md
--- name: smart-illustrator description: 智能配图与 PPT 信息图生成器。支持三种模式：(1) 文章配图模式 - 分析文章内容，生成插图；(2) PPT/Slides 模式 - 生成批量信息图；(3) Cover 模式 - 生成封面图。所有模式默认生成图片，`--prompt-only` 只输出 prompt。支持 Bento Grid 功能展示图风格（--style bento）。触发词：配图、插图、PPT、slides、封面图、thumbnail、cover、bento grid、功能展示图、feature showcase。 --- # Smart Illustrator - 智能配图与 PPT 生成器 ## 使用方式 ### 文章配图模式（默认） 分析文章结构，找到合适的配图位置，为每个位置生成插图。